---
schema_version: 7
rubric_version: "0.3"
canonical_url: "https://podium.do/compare/agents/products/replit/"
data_url: "https://podium.do/compare/agents/products/replit/data.json"
generated_at: 2026-11-22
oldest_checked_at: 2026-11-08
last_checked_at: 2026-11-13
publisher: "Podium"
---

# Replit: ADE findings

> Podium publishes this catalog and sells an agent development environment. Podium chooses the products, criteria, sources and wording, so treat these pages as vendor-authored research. Check important claims against the linked primary sources. Sourced findings follow the same evidence rules for Podium and its competitors. Facts labeled Podium team research come from Podium's own team and have no linked source. None of this removes the conflict of interest.

> Based on data from adecomparison.com by Podium (https://adecomparison.com; source repository https://github.com/madeinorbit/ade-comparison, snapshot 4322f0c of 2026-11-22), used under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Source links and check dates are kept. Podium arranges the findings into pairs, applies its publication checks, and added its own research where marked "Podium team research". Data license terms: https://github.com/madeinorbit/ade-comparison/blob/4322f0c035f303791413639d1462a138443d8c1e/DATA-LICENSE.md

42 of 51 criteria have a sourced finding; 28 were also cross-checked by a second agent. Source checks: 2026-11-08 to 2026-11-13. A missing sourced finding is not evidence that a capability is absent.

- Website: https://replit.com/
- Canonical HTML: https://podium.do/compare/agents/products/replit/
- Machine-readable JSON: https://podium.do/compare/agents/products/replit/data.json
- Rubric: https://podium.do/compare/agents/rubric/index.md
- Comparisons with Replit on podium.do: 1 (listed in the JSON and HTML)
- Compare Replit with any other product on adecomparison.com by Podium: https://adecomparison.com/compare/?products=replit

## Access and agent choice

### ACC-01: Client access

Verification status: Sourced (sourced)
Support: partial

Replit offers browser and phone-browser access, native iOS/Android clients, and native desktop apps on Mac, Windows and Debian-based Linux.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: cli, editor_extensions.

- desktop_os — Desktop os [supported]: The current native desktop guide explicitly supports Mac, Windows and Debian-based Linux. Sources: replit:gaps-desktop-platforms.
- mobile_apps — Mobile apps [supported]: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications. Sources: replit:nov08-acc-01-2.
- browser — Browser [supported]: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser. Sources: replit:nov08-acc-01-1.
- mobile_browser — Mobile browser [supported]: The first-party code editor page explicitly offers the cloud development workspace in a phone browser. Sources: replit:gaps-phone-browser.
- cli — Cli [unknown]: Cli remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- editor_extensions — Editor extensions [unknown]: Editor extensions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_actions — Task actions [supported]: The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser. Sources: replit:nov08-acc-01-1.
- notifications — Notifications [supported]: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications. Sources: replit:nov08-acc-01-2.
- cross_device_continuity — Cross device continuity [supported]: Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications. Sources: replit:nov08-acc-01-2.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-acc-01-1, replit:nov08-acc-01-2, replit:gaps-desktop-platforms, replit:gaps-phone-browser

### ACC-02: Agent and model choice

Verification status: Sourced (sourced)
Support: partial

The documented development experience runs Replit Agent with selectable modes/models. The checked sources do not establish named third-party coding-harness integrations; building an app that calls a provider or installing arbitrary shell software is separate.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: custom_adapters, session_integration, mixed_harness_operation.

- harnesses — Harnesses [unknown]: No Replit-owned launch/steer/session integration for the audited third-party coding harnesses is established by the current Agent documentation. Sources: replit:gaps-agent-provider-boundary.
- model_providers — Model providers [partial]: Agent uses Replit-managed model infrastructure; app API keys are separate from the Agent model. Sources: replit:gaps-agent-provider-boundary.
- custom_adapters — Custom adapters [unknown]: Custom adapters remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- session_integration — Session integration [unknown]: Session integration remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- mixed_harness_operation — Mixed harness operation [unknown]: Mixed harness operation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-acc-02-1, replit:gaps-agent-provider-boundary

### ACC-03: Subscriptions, API keys and vendor credits

Verification status: Sourced (sourced)
Support: partial

Replit plan credits pay for Agent. User API keys power calls made by built apps, while the Agent itself remains Replit-managed rather than using the app API keys. A native external coding-agent subscription login remains unestablished.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: local_models, account_switching, vendor_account_requirement, provider_restrictions.

- agent_subscriptions — Agent subscriptions [unknown]: The checked billing/Agent FAQ does not establish native subscription-login reuse. Sources: replit:gaps-agent-provider-boundary.
- api_accounts — Api accounts [unsupported]: Own provider keys in Secrets power the app, not the Replit Agent itself. Sources: replit:gaps-agent-provider-boundary.
- vendor_credits — Vendor credits [supported]: Replit plan credits pay for Agent and other cloud services; paid actions use effort-based pricing after confirmation. Sources: replit:nov08-acc-03-1.
- local_models — Local models [unknown]: Local models remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- account_switching — Account switching [unknown]: Account switching remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- vendor_account_requirement — Vendor account requirement [unknown]: Vendor account requirement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- provider_restrictions — Provider restrictions [unknown]: Provider restrictions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-acc-03-1, replit:gaps-agent-provider-boundary

### ACC-04: Onboarding and project prerequisites

Verification status: Sourced (sourced)
Support: partial

Start a project by describing an idea in plain language, or bring it in from GitHub, Figma or uploaded files, in the cloud Project Editor.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- first_task_setup — First task setup [supported]: A project can start from a plain-language description or an import from GitHub, Figma or uploaded files. Sources: replit:nov08-acc-04-1.
- no_git — No git [unknown]: No git remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- local_git_without_remote — Local git without remote [unknown]: Local git without remote remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- hosted_git — Hosted git [supported]: Existing GitHub projects can be imported into the cloud Project Editor. Sources: replit:nov08-acc-04-1.
- prerequisite_guidance — Prerequisite guidance [unknown]: Prerequisite guidance remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- managed_cloud_setup — Managed cloud setup [supported]: Projects are created and saved in Replit's cloud Project Editor; the page does not itself state that no local environment is required. Sources: replit:nov08-acc-04-1.
- byo_vps_onboarding — Byo vps onboarding [unknown]: Byo vps onboarding remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-acc-04-1

### ACC-05: Programmable access

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### ACC-06: External tools and extensions

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### ACC-07: Client implementation

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Planning and context

### PLAN-01: Intake and external tracker relationship

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- local_creation — Local creation [supported]: A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread. Sources: replit:nov08-plan-01-1.
- prompt_intake — Prompt intake [supported]: A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread. Sources: replit:nov08-plan-01-1.
- external_import — External import [unknown]: External import remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- chat_git_triggers — Chat git triggers [unknown]: Chat git triggers remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- authoritative_tracker — Authoritative tracker [unknown]: Authoritative tracker remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- stable_ids — Stable ids [unknown]: Stable ids remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- sync — Sync [unknown]: Sync remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- supported_edits — Supported edits [unknown]: Supported edits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- external_roundtrips — External roundtrips [unknown]: External roundtrips remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-01-1

### PLAN-02: Durable task plans

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- plans — Plans [supported]: Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution. Sources: replit:nov08-plan-02-1.
- acceptance_criteria — Acceptance criteria [supported]: Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution. Sources: replit:nov08-plan-02-1.
- editors — Editors [unknown]: Editors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- revisions — Revisions [unknown]: Revisions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- implementation_links — Implementation links [unknown]: Implementation links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- amendment — Amendment [supported]: Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution. Sources: replit:nov08-plan-02-1.
- restart_persistence — Restart persistence [unknown]: Restart persistence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-02-1

### PLAN-03: Hierarchy, dependencies and evolving scope

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- epics — Epics [unknown]: Epics remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- hierarchy — Hierarchy [unknown]: Hierarchy remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- blockers — Blockers [supported]: Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker. Sources: replit:nov08-plan-03-1.
- readiness — Readiness [supported]: Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker. Sources: replit:nov08-plan-03-1.
- enforcement — Enforcement [supported]: Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker. Sources: replit:nov08-plan-03-1.
- state_propagation — State propagation [supported]: Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker. Sources: replit:nov08-plan-03-1.
- task_to_epic — Task to epic [unknown]: Task to epic remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- identity_retention — Identity retention [unknown]: Identity retention remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- workflow_constraints — Workflow constraints [unknown]: Workflow constraints remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-03-1

### PLAN-04: Shared context and memory

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Each background task inherits the project context and receives its own Agent and project copy.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- instructions — Instructions [unknown]: Instructions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- skills — Skills [unknown]: Skills remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- project_docs — Project docs [unknown]: Project docs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- memory — Memory [unknown]: Memory remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- scope — Scope [supported]: Each background task inherits the project context and receives its own Agent and project copy. Sources: replit:nov08-plan-04-1.
- provenance — Provenance [unknown]: Provenance remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- correction — Correction [unknown]: Correction remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deletion — Deletion [unknown]: Deletion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- freshness — Freshness [unknown]: Freshness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- takeover_continuity — Takeover continuity [unknown]: Takeover continuity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-04-1

### PLAN-05: Architecture and API awareness

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Projects can begin from GitHub, Figma or uploaded files; this establishes input channels, not verified architecture comprehension.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- code_search — Code search [unknown]: Code search remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- indexing — Indexing [unknown]: Indexing remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- external_knowledge — External knowledge [unknown]: External knowledge remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- multimodal_inputs — Multimodal inputs [supported]: Projects can begin from GitHub, Figma or uploaded files; this establishes input channels, not verified architecture comprehension. Sources: replit:nov08-plan-05-1.
- freshness — Freshness [unknown]: Freshness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- access_scope — Access scope [unknown]: Access scope remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- api_retrieval — Api retrieval [unknown]: Api retrieval remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- citations — Citations [unknown]: Citations remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- conflict_detection — Conflict detection [unknown]: Conflict detection remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- review_enforcement — Review enforcement [unknown]: Review enforcement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-05-1

### PLAN-06: Native issue management and idea backlog

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- create — Create [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- edit — Edit [unknown]: Edit remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- discuss — Discuss [unknown]: Discuss remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prioritize — Prioritize [unknown]: Prioritize remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- label — Label [unknown]: Label remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- assign — Assign [unknown]: Assign remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- search — Search [unknown]: Search remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- filter — Filter [unknown]: Filter remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- archive — Archive [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- reopen — Reopen [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- project_epic_views — Project epic views [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- idea_parking — Idea parking [unknown]: Idea parking remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- explicit_dispatch — Explicit dispatch [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- task_session_separation — Task session separation [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- metadata — Metadata [unknown]: Metadata remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- durable_states — Durable states [supported]: Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it. Sources: replit:nov08-plan-06-1.
- external_tracker_requirement — External tracker requirement [unknown]: External tracker requirement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-06-1

### PLAN-07: Agent-native issue operations

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent can split a request into tasks and put them on the human-visible task board.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- shared_ids — Shared ids [unknown]: Shared ids remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- read — Read [unknown]: Read remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- create — Create [supported]: Agent can split a request into tasks and put them on the human-visible task board. Sources: replit:nov08-plan-07-1.
- update — Update [unknown]: Update remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- claim — Claim [unknown]: Claim remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- assign — Assign [unknown]: Assign remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- state_changes — State changes [unknown]: State changes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- dependencies — Dependencies [unknown]: Dependencies remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- children — Children [unknown]: Children remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- results — Results [unknown]: Results remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- human_visibility — Human visibility [supported]: Agent can split a request into tasks and put them on the human-visible task board. Sources: replit:nov08-plan-07-1.
- attribution — Attribution [unknown]: Attribution remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- permissions — Permissions [unknown]: Permissions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- conflicts — Conflicts [unknown]: Conflicts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-plan-07-1

### PLAN-08: Living product specifications

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Coordination and automation

### COORD-01: Parallel work

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=Core 1; Pro 10; Enterprise 64; Starter no background tasks; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- concurrent_sessions — Concurrent sessions [supported]: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue. Sources: replit:nov08-recheck-01-1.
- concurrent_tasks — Concurrent tasks [supported]: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue. Sources: replit:nov08-recheck-01-1.
- quotas — Quotas [supported]: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue. Sources: replit:nov08-recheck-01-1.
- observed_concurrency — Observed concurrency [unknown]: Observed concurrency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- status_visibility — Status visibility [supported]: Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue. Sources: replit:nov08-recheck-01-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-01-1

### COORD-02: Ownership and dispatch

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- human_assignment — Human assignment [unknown]: Human assignment remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- agent_assignment — Agent assignment [unknown]: Agent assignment remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- claims — Claims [unknown]: Claims remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- queues — Queues [supported]: Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied. Sources: replit:nov08-recheck-02-1.
- routing — Routing [supported]: Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied. Sources: replit:nov08-recheck-02-1.
- duplicate_prevention — Duplicate prevention [unknown]: Duplicate prevention remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ownership_enforcement — Ownership enforcement [unknown]: Ownership enforcement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-02-1

### COORD-03: Inspectable delegation and communication

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- roles — Roles [unknown]: Roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- model_harness_effort — Model harness effort [unknown]: Model harness effort remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- messages — Messages [unknown]: Messages remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- results_return — Results return [supported]: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow. Sources: replit:nov08-recheck-03-1.
- cross_harness — Cross harness [unknown]: Cross harness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- orchestration_owner — Orchestration owner [supported]: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow. Sources: replit:nov08-recheck-03-1.
- activation — Activation [supported]: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow. Sources: replit:nov08-recheck-03-1.
- authentication — Authentication [unknown]: Authentication remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- live_progress — Live progress [supported]: Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow. Sources: replit:nov08-recheck-03-1.
- retained_results — Retained results [unknown]: Retained results remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- followup — Followup [unknown]: Followup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- invocation — Invocation [unknown]: Invocation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-03-1

### COORD-04: Unattended triggers

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=Core, Pro or Enterprise; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- schedules — Schedules [supported]: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing. Sources: replit:nov08-recheck-04-1.
- events — Events [unknown]: Events remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- recurring_tasks — Recurring tasks [supported]: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing. Sources: replit:nov08-recheck-04-1.
- completion_conditions — Completion conditions [unknown]: Completion conditions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- scheduler_location — Scheduler location [unknown]: Scheduler location remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- overlaps — Overlaps [supported]: Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing. Sources: replit:nov08-recheck-04-1.
- retries — Retries [unknown]: Retries remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- client_independence — Client independence [unknown]: Client independence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-04-1

### COORD-05: Intervention and attention

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- pause — Pause [unknown]: Pause remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- stop — Stop [supported]: Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction. Sources: replit:nov08-recheck-05-1.
- resume — Resume [unknown]: Resume remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- steer — Steer [supported]: Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction. Sources: replit:nov08-recheck-05-1.
- notifications — Notifications [unknown]: Notifications remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- pending_decisions — Pending decisions [unknown]: Pending decisions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- escalation — Escalation [unknown]: Escalation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- visible_errors — Visible errors [unknown]: Visible errors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- chat_terminal_parity — Chat terminal parity [unknown]: Chat terminal parity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_history — Retained history [unknown]: Retained history remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-05-1

### COORD-06: Fleet and epic management UI

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- fleet_fixture — Fleet fixture [unknown]: Fleet fixture remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- parent_child — Parent child [unknown]: Parent child remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- dependencies — Dependencies [unknown]: Dependencies remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- attention — Attention [supported]: A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested. Sources: replit:nov08-recheck-06-1.
- history — History [supported]: A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested. Sources: replit:nov08-recheck-06-1.
- workload — Workload [unknown]: Workload remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- navigation_errors — Navigation errors [unknown]: Navigation errors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- fixture_mode — Fixture mode [unknown]: Fixture mode remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-06-1

### COORD-07: Workflow flexibility and orchestration visibility

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Users start with ordinary chat, refine plans and let Agent create task lists before approving work.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- quick_task — Quick task [supported]: Users start with ordinary chat, refine plans and let Agent create task lists before approving work. Sources: replit:nov08-recheck-07-1.
- growing_epic — Growing epic [unknown]: Growing epic remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- presets — Presets [unknown]: Presets remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- natural_language — Natural language [supported]: Users start with ordinary chat, refine plans and let Agent create task lists before approving work. Sources: replit:nov08-recheck-07-1.
- agent_configuration — Agent configuration [unknown]: Agent configuration remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- in_run_changes — In run changes [unknown]: In run changes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- live_roles — Live roles [unknown]: Live roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_relationships — Retained relationships [unknown]: Retained relationships remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- discoverability — Discoverability [unknown]: Discoverability remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- auth_friction — Auth friction [unknown]: Auth friction remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-recheck-07-1

## Execution and reliability

### RUN-01: Laptop-independent execution

Verification status: Sourced (sourced)
Support: partial

Replit provides managed cloud development, and the current desktop page also offers local Agent code/build execution on supported Mac/Windows devices. Full BYOC Agent execution is private preview, while published-app exports do not move development.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: self_hosted, hybrid, provisioning, payer, resources, region, expiry, other_device_continuation.

- local — Local [supported]: The desktop product page explicitly offers Agent build/run in the selected local environment on supported Mac/Windows devices. Sources: replit:gaps-local-desktop-execution.
- byo_remote — Byo remote [unsupported]: The currently described Full BYOC Agent runtime is private preview; published-app BYOC/exports do not provide public Agent execution on an operator server. Sources: replit:gaps-byoc-boundary.
- self_hosted — Self hosted [unknown]: Self hosted remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- managed_cloud — Managed cloud [supported]: Repository development runs in Replit cloud sandboxes. Sources: replit:gaps-cloud-microvm.
- hybrid — Hybrid [unknown]: Hybrid remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- provisioning — Provisioning [unknown]: Provisioning remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- payer — Payer [unknown]: Payer remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- resources — Resources [unknown]: Resources remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- region — Region [unknown]: Region remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- expiry — Expiry [unknown]: Expiry remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- client_disconnect — Client disconnect [supported]: The cloud Project Editor retains project state and running app when the browser closes; this does not establish unlimited Agent runtime. Sources: replit:nov08-run-01-1.
- other_device_continuation — Other device continuation [unknown]: Other device continuation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-run-01-1, replit:gaps-local-desktop-execution, replit:gaps-byoc-boundary, replit:gaps-cloud-microvm

### RUN-02: Workspace and process isolation

Verification status: Sourced (sourced)
Support: partial

Replit repository development sandboxes explicitly use microVMs. Its current local desktop offering names Microsoft Execution Containers on supported Mac/Windows devices; background task copies are not established as Git worktrees.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: branch, worktree, os_sandbox, filesystem, process, network, secrets, security_boundary.

- checkout — Checkout [supported]: Background tasks run in isolated project copies and do not change the main version until applied. The docs do not name these copies as containers, VMs or worktrees. Sources: replit:nov08-run-02-1.
- branch — Branch [unknown]: Branch remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- worktree — Worktree [unknown]: Worktree remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- container — Container [supported]: The desktop page explicitly names Microsoft Execution Containers for local code/build execution on supported Windows/macOS devices. Sources: replit:gaps-local-desktop-execution.
- vm — Vm [supported]: The repository-development guide explicitly names a microVM boundary. Sources: replit:gaps-cloud-microvm.
- os_sandbox — Os sandbox [unknown]: Os sandbox remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- filesystem — Filesystem [unknown]: Filesystem remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- process — Process [unknown]: Process remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- network — Network [unknown]: Network remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- secrets — Secrets [unknown]: Secrets remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- code_separation — Code separation [supported]: Background tasks run in isolated project copies and do not change the main version until applied. The docs do not name these copies as containers, VMs or worktrees. Sources: replit:nov08-run-02-1.
- security_boundary — Security boundary [unknown]: Security boundary remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-run-02-1, replit:gaps-cloud-microvm, replit:gaps-local-desktop-execution

### RUN-03: Recovery, expiry and continuity

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Files, history and running app are preserved in the cloud for a later visit. No worker-crash recovery test was performed.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- client_disconnect — Client disconnect [unknown]: Client disconnect remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- worker_crash — Worker crash [unknown]: Worker crash remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- service_restart — Service restart [unknown]: Service restart remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- expiry — Expiry [unknown]: Expiry remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- transcript_reload — Transcript reload [supported]: Files, history and running app are preserved in the cloud for a later visit. No worker-crash recovery test was performed. Sources: replit:nov08-run-03-1.
- process_reconnect — Process reconnect [unknown]: Process reconnect remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_resume — Task resume [unknown]: Task resume remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- state_reconstruction — State reconstruction [unknown]: State reconstruction remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- context_loss — Context loss [unknown]: Context loss remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- duplicate_actions — Duplicate actions [unknown]: Duplicate actions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- manual_repair — Manual repair [unknown]: Manual repair remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- multi_day_continuity — Multi day continuity [unknown]: Multi day continuity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-run-03-1

### RUN-04: Development environment reliability

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent sets up the project and infrastructure. Specific dependency-cache, port-collision and clean-remote-host behavior remains untested.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- dependencies — Dependencies [supported]: Agent sets up the project and infrastructure. Specific dependency-cache, port-collision and clean-remote-host behavior remains untested. Sources: replit:nov08-run-04-1.
- caches — Caches [unknown]: Caches remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- snapshots — Snapshots [unknown]: Snapshots remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- services — Services [unknown]: Services remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ports — Ports [unknown]: Ports remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- secrets — Secrets [unknown]: Secrets remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- duplicate_installs — Duplicate installs [unknown]: Duplicate installs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- collisions — Collisions [unknown]: Collisions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- remote_setup — Remote setup [unknown]: Remote setup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- automatic_repair — Automatic repair [unknown]: Automatic repair remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-run-04-1

### RUN-05: Limits and failure handling

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- time_limits — Time limits [unknown]: Time limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- turn_limits — Turn limits [unknown]: Turn limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- token_limits — Token limits [unknown]: Token limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- spend_limits — Spend limits [supported]: Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget. Sources: replit:nov08-run-05-1.
- timeouts — Timeouts [unknown]: Timeouts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retries — Retries [unknown]: Retries remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- provider_failures — Provider failures [unknown]: Provider failures remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- enforcement — Enforcement [supported]: Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget. Sources: replit:nov08-run-05-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-run-05-1

### RUN-06: Truthful status and operational statistics

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Finished tasks expose a work log, test results and preview; active threads and board cards show task status.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- logs — Logs [supported]: Finished tasks expose a work log, test results and preview; active threads and board cards show task status. Sources: replit:nov08-run-06-1.
- traces — Traces [unknown]: Traces remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- failure_reasons — Failure reasons [unknown]: Failure reasons remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- usage_export — Usage export [unknown]: Usage export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_stats — Task stats [unknown]: A work log and test results are documented, but aggregate task statistics are not established by that source.
- agent_stats — Agent stats [unknown]: Agent stats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- project_stats — Project stats [unknown]: Project stats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- time_stats — Time stats [unknown]: Time stats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- failure_status — Failure status [unknown]: Failure status remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- approval_status — Approval status [unknown]: Approval status remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- reconnect_consistency — Reconnect consistency [unknown]: Reconnect consistency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- performance_method — Performance method [unknown]: Performance method remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- responsiveness — Responsiveness [unknown]: Responsiveness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-run-06-1

### RUN-07: Per-task API and compute cost

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent billing is effort-based and uses plan credits shared with cloud services. A controlled reconciliation against provider billing was not performed.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- task_cost — Task cost [unknown]: Task cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- session_cost — Session cost [unknown]: Session cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- child_cost — Child cost [unknown]: Child cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- epic_cost — Epic cost [unknown]: Epic cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- harness_aggregation — Harness aggregation [unknown]: Harness aggregation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- billed_vs_estimated — Billed vs estimated [unknown]: Billed vs estimated remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- tokens — Tokens [unknown]: Tokens remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- subscription_allowance — Subscription allowance [supported]: Agent billing is effort-based and uses plan credits shared with cloud services. A controlled reconciliation against provider billing was not performed. Sources: replit:nov08-run-07-1.
- provider_reconciliation — Provider reconciliation [unknown]: Provider reconciliation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- compute_cost — Compute cost [unknown]: Compute cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- refresh_delay — Refresh delay [unknown]: Refresh delay remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- alerts — Alerts [unknown]: Alerts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- export — Export [unknown]: Export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- drilldown — Drilldown [unknown]: Drilldown remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-run-07-1

### RUN-08: Compute-aware scheduling and verification

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- concurrency — Concurrency [supported]: Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling. Sources: replit:nov08-run-08-1.
- queues — Queues [supported]: Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling. Sources: replit:nov08-run-08-1.
- cpu_ram — Cpu ram [unknown]: Cpu ram remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- backpressure — Backpressure [supported]: Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling. Sources: replit:nov08-run-08-1.
- host_awareness — Host awareness [unknown]: Host awareness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- check_reuse — Check reuse [unknown]: Check reuse remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- check_deduplication — Check deduplication [unknown]: Check deduplication remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- bounded_tests — Bounded tests [unknown]: Bounded tests remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cancellation — Cancellation [unknown]: Cancellation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- fairness — Fairness [unknown]: Fairness remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- recovery — Recovery [unknown]: Recovery remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- shared_limits — Shared limits [unknown]: Shared limits remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-run-08-1

## Human collaboration and control

### TEAM-01: Live human collaboration

Verification status: Sourced (sourced)
Support: partial

Invited teammates work on one project through separate Agent threads and shared task boards. Multiple humans steering the same active Agent conversation or work item remains unestablished.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: discussion, comments, presence, ordering, conflicts, attribution, owner_online.

- visibility — Visibility [supported]: Team workspaces share projects with members; Core includes five collaboration seats and Pro fifteen. Simultaneous co-prompt ordering is not established by this source. Sources: replit:nov08-team-01-1.
- discussion — Discussion [unknown]: Discussion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- comments — Comments [unknown]: Comments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- presence — Presence [unknown]: Presence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- coprompting — Coprompting [unknown]: The guide establishes distinct humans and separate Agent threads, but not shared-human instructions into one active Agent work item. Sources: replit:gaps-shared-project-boundary.
- ordering — Ordering [unknown]: Ordering remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- conflicts — Conflicts [unknown]: Conflicts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- attribution — Attribution [unknown]: Attribution remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- permissions — Permissions [supported]: Team workspaces share projects with members; Core includes five collaboration seats and Pro fifteen. Simultaneous co-prompt ordering is not established by this source. Sources: replit:nov08-team-01-1.
- plan_restrictions — Plan restrictions [supported]: Team workspaces share projects with members; Core includes five collaboration seats and Pro fifteen. Simultaneous co-prompt ordering is not established by this source. Sources: replit:nov08-team-01-1.
- owner_online — Owner online [unknown]: Owner online remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-team-01-1, replit:gaps-shared-project-boundary

### TEAM-02: Roles and access boundaries

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=Enterprise for SAML SSO; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- organization_roles — Organization roles [supported]: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. Sources: replit:nov08-team-02-1.
- project_roles — Project roles [unknown]: Project roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_roles — Task roles [unknown]: Task roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- membership — Membership [supported]: Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members. Sources: replit:nov08-team-02-1.
- sso — Sso [supported]: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership. Sources: replit:nov08-team-02-2.
- provisioning — Provisioning [supported]: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership. Sources: replit:nov08-team-02-2.
- unauthorized_access — Unauthorized access [unknown]: Unauthorized access remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- revocation — Revocation [unknown]: Revocation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- plan_scope — Plan scope [supported]: SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership. Sources: replit:nov08-team-02-2.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-team-02-1, replit:nov08-team-02-2

### TEAM-03: Approvals and temporary access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- command — Command [unknown]: Command remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- tool — Tool [unknown]: Tool remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- network — Network [unknown]: Network remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- secret — Secret [unknown]: Secret remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- delivery — Delivery [supported]: Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version. Sources: replit:nov08-team-03-1.
- approver_identity — Approver identity [unknown]: Approver identity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- lifetime — Lifetime [unknown]: Lifetime remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- allow — Allow [supported]: Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version. Sources: replit:nov08-team-03-1.
- deny — Deny [supported]: Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version. Sources: replit:nov08-team-03-1.
- revoke — Revoke [unknown]: Revoke remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- tunnels — Tunnels [unknown]: Tunnels remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- defaults — Defaults [unknown]: Defaults remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- safer_modes — Safer modes [unknown]: Safer modes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- enforcement — Enforcement [unknown]: Enforcement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-team-03-1

### TEAM-04: Decision and activity history

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### TEAM-05: Review experience and guidance

Verification status: Sourced (sourced)
Support: partial

Replit displays code diffs in its Changes pane, alongside local changes or linked PRs, in addition to task logs, tests and previews for review decisions.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: evidence_navigation, comments, request_changes, effort, missed_evidence, keyboard, narrow_screen, context_switching, roles, retained_context.

- pending_reviews — Pending reviews [supported]: Ready tasks expose a work log, test results and live preview with Apply or Dismiss decisions. Review effort and missed evidence were not measured. Sources: replit:nov08-team-05-1.
- change_understanding — Change understanding [supported]: Changes displays proposed-code additions/deletions and linked PR metadata; local and PR diffs are product-rendered. Sources: replit:gaps-code-review-pane.
- evidence_navigation — Evidence navigation [unknown]: Evidence navigation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- comments — Comments [unknown]: Comments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- request_changes — Request changes [unknown]: Request changes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- shipping_guidance — Shipping guidance [supported]: Ready tasks expose a work log, test results and live preview with Apply or Dismiss decisions. Review effort and missed evidence were not measured. Sources: replit:nov08-team-05-1.
- effort — Effort [unknown]: Effort remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- missed_evidence — Missed evidence [unknown]: Missed evidence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- keyboard — Keyboard [unknown]: Keyboard remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- narrow_screen — Narrow screen [unknown]: Narrow screen remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- context_switching — Context switching [unknown]: Context switching remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- roles — Roles [unknown]: Roles remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_context — Retained context [unknown]: Retained context remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-team-05-1, replit:gaps-code-review-pane

### TEAM-06: Colleague takeover and continuity

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Verification and delivery

### SHIP-01: Retained artifacts and outputs

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- diffs — Diffs [unknown]: Diffs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- documents — Documents [unknown]: Documents remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- screenshots — Screenshots [unknown]: Screenshots remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- recordings — Recordings [unknown]: Recordings remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- previews — Previews [supported]: Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established. Sources: replit:nov08-ship-01-1.
- test_outputs — Test outputs [supported]: Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established. Sources: replit:nov08-ship-01-1.
- reviewer_outputs — Reviewer outputs [unknown]: Reviewer outputs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- gallery — Gallery [unknown]: Gallery remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- task_links — Task links [supported]: Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established. Sources: replit:nov08-ship-01-1.
- revision_links — Revision links [unknown]: Revision links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- persistence — Persistence [unknown]: Persistence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- child_findings — Child findings [unknown]: Child findings remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prompt_leakage — Prompt leakage [unknown]: Prompt leakage remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-ship-01-1

### SHIP-02: Verification and spec gates

Verification status: Sourced (sourced)
Support: partial

With App Testing enabled, Agent periodically tests apps it builds in an actual browser and fixes issues it finds. It is available for Full Stack JavaScript and Streamlit Python web apps. Documentation is not proof of mandatory independent review or an enforced passing test gate.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- App Testing covers Full Stack JavaScript and Streamlit Python web apps only, and Agent decides when to test rather than testing after every message.
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- tests — Tests [supported]: Agent periodically tests Full Stack JavaScript and Streamlit Python web apps in an actual browser when App Testing is enabled. Sources: replit:nov08-ship-02-1.
- lint — Lint [unknown]: Lint remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- types — Types [unknown]: Types remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- ci — Ci [unknown]: Ci remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- independent_review — Independent review [unknown]: Independent review remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- spec_checks — Spec checks [unknown]: Spec checks remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- required_checks — Required checks [unknown]: Required checks remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- failure_blocking — Failure blocking [unknown]: Failure blocking remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- requirement_conflicts — Requirement conflicts [unknown]: Requirement conflicts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- configured_policy — Configured policy [unknown]: Configured policy remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- enforced_policy — Enforced policy [unknown]: Enforced policy remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-ship-02-1

### SHIP-03: Git and pull request workflow

Verification status: Sourced (sourced)
Support: partial

The repository contribution workflow creates branches, commits/pushes code and opens draft GitHub PRs or GitLab MRs, then can revise the same request after review.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: worktrees, ci_response, rebase, product_state.

- branches — Branches [supported]: Replit creates the contribution branch in its owned repository workflow. Sources: replit:nov08-ship-03-1, replit:gaps-cloud-microvm, replit:gaps-code-review-pane.
- worktrees — Worktrees [unknown]: Worktrees remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- commits — Commits [supported]: The workflow commits and pushes the contribution. Sources: replit:nov08-ship-03-1, replit:gaps-cloud-microvm, replit:gaps-code-review-pane.
- pull_requests — Pull requests [supported]: It opens a draft PR/MR and links it in the product Changes/Details interface. Sources: replit:nov08-ship-03-1, replit:gaps-cloud-microvm, replit:gaps-code-review-pane.
- comments — Comments [supported]: Review follow-up can update the same request and reply to review comments. Sources: replit:nov08-ship-03-1, replit:gaps-cloud-microvm, replit:gaps-code-review-pane.
- ci_response — Ci response [unknown]: Ci response remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- rebase — Rebase [unknown]: Rebase remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- conflicts — Conflicts [supported]: Applying tasks invokes AI-assisted conflict resolution. The source does not establish a GitHub PR workflow. Sources: replit:nov08-ship-03-1.
- product_state — Product state [unknown]: Product state remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-ship-03-1, replit:gaps-cloud-microvm, replit:gaps-code-review-pane

### SHIP-04: Merge and deployment authority

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Users publish to a live URL from the Project Editor. Production authorization and revision binding were not tested.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- approve — Approve [unknown]: Approve remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- merge — Merge [unknown]: Merge remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- release — Release [unknown]: Release remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deploy — Deploy [supported]: Users publish to a live URL from the Project Editor. Production authorization and revision binding were not tested. Sources: replit:nov08-ship-04-1.
- exact_revision — Exact revision [unknown]: Exact revision remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- authority_enforcement — Authority enforcement [unknown]: Authority enforcement remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-ship-04-1

### SHIP-05: Completion evidence and rollback

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent creates checkpoints that users can roll back to when a change is wrong.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- commit_links — Commit links [unknown]: Commit links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- pr_links — Pr links [unknown]: Pr links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- build_links — Build links [unknown]: Build links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deployment_links — Deployment links [unknown]: Deployment links remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- delivery_status — Delivery status [unknown]: Delivery status remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retained_evidence — Retained evidence [unknown]: Retained evidence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- rollback — Rollback [supported]: Agent creates checkpoints that users can roll back to when a change is wrong. Sources: replit:nov08-ship-05-1.
- revert — Revert [unknown]: Revert remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- stale_approval_invalidation — Stale approval invalidation [unknown]: Stale approval invalidation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-ship-05-1

### SHIP-06: Batch review and high-volume shipping

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

## Ownership, privacy and economics

### OWN-01: Source and license

Verification status: Sourced (sourced)
Support: partial

The main Replit Agent/platform is proprietary software supplied under Replit service terms, which reserve its intellectual-property rights and grant users limited service access.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: client_license, hosted_extensions, source_revision, hosted_parity.

- client_license — Client license [unknown]: Client license remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- server_license — Server license [supported]: The service terms reserve rights in the Service and related software to Replit; user access is limited by that agreement. Sources: replit:gaps-main-app-license.
- hosted_extensions — Hosted extensions [unknown]: Hosted extensions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- source_visibility — Source visibility [partial]: The main hosted Agent/platform is proprietary; separately licensed public client/SDK components and user app code do not establish an open-source main platform. Sources: replit:gaps-main-app-license.
- source_revision — Source revision [unknown]: Source revision remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- hosted_parity — Hosted parity [unknown]: Hosted parity remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-13 (9 days old on 2026-11-22); not separately cross-checked.

Sources: replit:gaps-main-app-license

### OWN-02: Hosting and exit

Verification status: Sourced (sourced)
Support: partial

Replit imports/exports project artifacts and offers Enterprise deployment options, but even Full BYOC explicitly leaves the control plane external and does not provide an entirely self-hosted Replit installation.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: export, formats, cancellation, account_independence, history_portability.

- self_hosting — Self hosting [unsupported]: The BYOC guide explicitly says Full BYOC is not an entirely self-hosted or air-gapped Replit installation. Sources: replit:nov08-own-02-1, replit:gaps-byoc-boundary.
- vendor_dependencies — Vendor dependencies [supported]: Full BYOC keeps an external Replit control plane and managed model inference; published-app export is a separate artifact deployment. Sources: replit:nov08-own-02-1, replit:gaps-byoc-boundary.
- export — Export [unknown]: Export remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- import — Import [supported]: Users can import GitHub projects and uploaded files. Exported task history and complete self-hosting are not established. Sources: replit:nov08-own-02-1.
- formats — Formats [unknown]: Formats remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cancellation — Cancellation [unknown]: Cancellation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- account_independence — Account independence [unknown]: Account independence remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- history_portability — History portability [unknown]: History portability remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-own-02-1, replit:gaps-byoc-boundary

### OWN-03: Data handling and telemetry

Verification status: Sourced (sourced)
Support: partial

Pro users can opt out of Model Improvement in Personalization settings, and Replit states it does not train on Enterprise customer content. No such control is named for Starter or Core. This is distinct from telemetry opt-out.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=Pro opt-out; Enterprise excluded from training; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- code_data — Code data [unknown]: Code data remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- prompts — Prompts [unknown]: Prompts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- credentials — Credentials [unknown]: Credentials remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- logs — Logs [unknown]: Logs remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- artifacts — Artifacts [unknown]: Artifacts remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- retention — Retention [unknown]: Retention remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deletion — Deletion [unknown]: Deletion remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- training — Training [supported]: Pro users can opt out of Model Improvement; Enterprise customer content is not used for training. No control is named for Starter or Core. Sources: replit:nov08-own-03-1.
- residency — Residency [unknown]: Residency remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- subprocessors — Subprocessors [unknown]: Subprocessors remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- telemetry_disclosure — Telemetry disclosure [unknown]: Telemetry disclosure remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- telemetry_defaults — Telemetry defaults [unknown]: Telemetry defaults remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- telemetry_controls — Telemetry controls [unknown]: Telemetry controls remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- consent_prompt — Consent prompt [unknown]: Consent prompt remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- provider_separation — Provider separation [unknown]: Provider separation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-own-03-1

### OWN-04: Price and included usage

Verification status: Sourced (sourced)
Support: partial

Replit supplies recurring Core/Pro plans and metered Agent/cloud credits. The default public Core plan is USD 20 per month at monthly billing; regional offers can differ. Pro has no per-user fees. App BYOK is separate from the managed Agent model and no one-time software license is offered.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Current public pricing page and its immutable first-party pricing catalog retrieved 2026-11-13; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=Default public web pricing; restricted regional offers can differ; harness=not specified.

Limitations:
- Documentation and pinned source inspection only; no hands-on scenario was run.
- Other atomic questions remain unestablished: seat_minimum, workspace_fees, included_usage, trial, taxes.

- currency — Currency [supported]: The first-party current pricing catalog explicitly identifies USD for the default Core monthly price/allocation. Sources: replit:gaps-default-core-price.
- interval — Interval [supported]: The default non-legacy Core monthly option is USD 20/month; annual and restricted regional options are separate. Sources: replit:gaps-default-core-price, replit:gaps-current-plan-offering, replit:gaps-flat-plan-billing.
- seats — Seats [supported]: Pro includes up to 15 builders with no per-user fees. Sources: replit:gaps-flat-plan-billing.
- seat_minimum — Seat minimum [unknown]: Seat minimum remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- workspace_fees — Workspace fees [unknown]: Workspace fees remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- included_usage — Included usage [unknown]: Included usage remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- credits — Credits [supported]: Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases. Sources: replit:nov08-own-04-1.
- trial — Trial [unknown]: Trial remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- overages — Overages [partial]: Core monthly credits also let users pay as they go, and credit packs can be bought; the cited pages state no overage rate. Sources: replit:nov08-own-04-1, replit:nov08-own-04-2.
- taxes — Taxes [unknown]: Taxes remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- model_cost — Model cost [supported]: The Replit Agent itself is billed through Replit credits; app provider-key charges are separate. Sources: replit:gaps-agent-provider-boundary.
- compute_cost — Compute cost [supported]: Cloud services such as published apps, storage and databases draw on the same plan credits as Agent under usage-based billing. Sources: replit:nov08-own-04-1.

Checked 2026-11-08 (14 days old on 2026-11-22); not separately cross-checked.

Sources: replit:nov08-own-04-1, replit:nov08-own-04-2, replit:gaps-flat-plan-billing, replit:gaps-current-plan-offering, replit:gaps-agent-provider-boundary, replit:gaps-default-core-price

### OWN-05: Scenario cost and controls

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-06: Availability and support

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- release_stage — Release stage [unknown]: Release stage remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- access_restrictions — Access restrictions [unknown]: Access restrictions remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- support — Support [supported]: The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice. Sources: replit:nov08-own-06-1.
- response_commitments — Response commitments [unknown]: Response commitments remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- release_activity — Release activity [supported]: The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice. Sources: replit:nov08-own-06-1.
- status_history — Status history [unknown]: Status history remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- deprecation — Deprecation [unknown]: Deprecation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- export_options — Export options [unknown]: Export options remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-own-06-1

### OWN-07: Enterprise assurance

Verification status: No sourced public finding (not-published)
Support: not-published

No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.

### OWN-08: Useful free tier and evaluation access

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- ongoing_free — Ongoing free [supported]: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core. Sources: replit:nov08-own-08-1.
- trial — Trial [unknown]: Trial remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- credits_trial — Credits trial [unknown]: Credits trial remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- self_host_cost — Self host cost [unknown]: Self host cost remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- paid_only — Paid only [unknown]: Paid only remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- early_access — Early access [unknown]: Early access remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- free_scenarios — Free scenarios [supported]: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core. Sources: replit:nov08-own-08-1.
- card_required — Card required [unknown]: Card required remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- usage_caps — Usage caps [supported]: Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core. Sources: replit:nov08-own-08-1.
- paid_evaluation — Paid evaluation [unknown]: Paid evaluation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-own-08-1

### OWN-09: Pricing transparency

Verification status: Agent cross-checked (agent-cross-checked)
Support: partial

Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented.

Availability: generally-available
Delivery: native
Scope: surfaces=Replit hosted Project Editor and Agent; mobile apps and paid team features where named; version=Public documentation retrieved 2026-11-08; plan=not specified; os=not specified; execution_modes=vendor-cloud; region=not specified; harness=not specified.

Limitations:
- Documentation evidence only. Remaining atomic questions and enforcement under failure have not been established by a bounded workflow test.

- units — Units [supported]: Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented. Sources: replit:nov08-own-09-1.
- included_limits — Included limits [supported]: Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented. Sources: replit:nov08-own-09-1.
- overages — Overages [unknown]: Overages remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- compute_markup — Compute markup [unknown]: Compute markup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- model_markup — Model markup [unknown]: Model markup remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- minimum_commitment — Minimum commitment [unknown]: Minimum commitment remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- cancellation — Cancellation [unknown]: Cancellation remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- sales_only_unknowns — Sales only unknowns [unknown]: Sales only unknowns remains unestablished in the recorded documentation, release and issue pass; no bounded hands-on test.
- transparency_classification — Transparency classification [supported]: Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented. Sources: replit:nov08-own-09-1.

Checked 2026-11-08 (14 days old on 2026-11-22); agent cross-checked 2026-11-08.

Sources: replit:nov08-own-09-1

## Sources

### replit:nov08-acc-01-1

Replit: The Project Editor. The hosted Project Editor provides Agent chat, project tools, live preview and a task board in the browser.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: The Project Editor
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-acc-01-2

Replit: Mobile features; Navigate your project. Native iOS and Android clients support Agent, Tools and Tasks panes, project continuation and completion or help notifications.

- URL: https://docs.replit.com/platforms/mobile-app
- Locator: Mobile features; Navigate your project
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-desktop-platforms

Replit: What is the Replit Desktop App; install and sync. The current first-party desktop guide explicitly offers a native app for Windows, Mac and Debian-based Linux, including Agent, Project Editor and publishing. This establishes desktop clients rather than inferring them from a companion CLI.

- URL: https://docs.replit.com/features/platforms/desktop-app.md
- Locator: What is the Replit Desktop App; install and sync
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:gaps-phone-browser

Replit: From your browser or mobile phone. The first-party AI code editor page explicitly offers the full cloud development workspace from a browser on desktop or mobile devices, alongside the native mobile apps.

- URL: https://replit.com/usecases/ai-code-editor
- Locator: From your browser or mobile phone
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-acc-02-1

Replit: Agent modes. Replit Agent has Free, Power and Max modes; Auto routes paid work to models. Model routing does not establish support for a third-party coding harness.

- URL: https://docs.replit.com/features/agent/overview
- Locator: Agent modes
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-agent-provider-boundary

Replit: Can I use my own API keys with Agent?. The first-party FAQ separates app API credentials from the Agent itself: user provider keys in Secrets power calls made by the built app, while the Agent experience uses Replit-managed model infrastructure rather than the user-key route. Curated in-product model selection is separate from replacing that infrastructure with an independently keyed endpoint. Replit AI billing charges its own plan credits. This is not evidence of a third-party coding harness or a native subscription-login path.

- URL: https://docs.replit.com/help/agent-and-ai.md
- Locator: Can I use my own API keys with Agent?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-acc-03-1

Replit: Agent billing. Replit plan credits pay for Agent and other cloud services; paid actions use effort-based pricing after confirmation.

- URL: https://docs.replit.com/billing/ai-billing
- Locator: Agent billing
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-acc-04-1

Replit: Getting started; Import code and design. Start a project by describing an idea in plain language, or bring it in from GitHub, Figma or uploaded files, in the cloud Project Editor. The page names no templates and does not itself state that no local environment is needed.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: Getting started; Import code and design
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-01-1

Replit: How background tasks work. A main-thread prompt can create titled tasks with descriptions and plans, or users can start a planning thread.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: How background tasks work
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-02-1

Replit: Plan your tasks; Review and accept. Agent proposes detailed plans and definitions of done; users inspect View plan, accept tasks or request a revised plan before execution.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Plan your tasks; Review and accept
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-03-1

Replit: Create and approve remaining tasks; Let Agent schedule the work. Agent identifies prerequisite tasks and queues dependent work until the prerequisite is applied. The board shows the blocker.

- URL: https://docs.replit.com/learn/build-in-parallel
- Locator: Create and approve remaining tasks; Let Agent schedule the work
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-04-1

Replit: Your app is safe while tasks run. Each background task inherits the project context and receives its own Agent and project copy.

- URL: https://docs.replit.com/learn/build-in-parallel
- Locator: Your app is safe while tasks run
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-05-1

Replit: Import code and design. Projects can begin from GitHub, Figma or uploaded files; this establishes input channels, not verified architecture comprehension.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: Import code and design
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-06-1

Replit: What is the task system; Frequently asked questions. Native tasks have Drafts, Active, Ready and Done states, a board, separate threads and explicit acceptance. Draft planning sessions can be archived and restored; cancelling building work discards it.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: What is the task system; Frequently asked questions
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-plan-07-1

Replit: What is the task system. Agent can split a request into tasks and put them on the human-visible task board.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: What is the task system
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-01-1

Replit: Tasks start running; Availability. Core supports one active background task, Pro up to ten and Enterprise up to sixty-four. Additional tasks queue.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Tasks start running; Availability
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-02-1

Replit: Let Agent schedule the work. Agent schedules independent tasks when capacity exists and holds dependent tasks until prerequisites are applied.

- URL: https://docs.replit.com/learn/build-in-parallel
- Locator: Let Agent schedule the work
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-03-1

Replit: What is the task system; Review and apply. Replit Agent decomposes a request into background Agent tasks with separate threads and returns work logs, tests and previews to the main-version review flow.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: What is the task system; Review and apply
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-04-1

Replit: How Routines run; Availability and limits. Paid-plan chat Routines repeat hourly, daily or weekly without a new request. They run in Power or Max, queue behind other chat work and do not schedule publishing.

- URL: https://docs.replit.com/features/agent/automations
- Locator: How Routines run; Availability and limits
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-05-1

Replit: Frequently asked questions. Cancel stops building and discards its work. The main thread and each task thread permit follow-up direction.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Frequently asked questions
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-06-1

Replit: Board view. A project board displays Drafts, Active, Ready and Done tasks alongside task conversations. Fleet-scale navigation has not been tested.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Board view
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-recheck-07-1

Replit: Plan mode; What you can build. Users start with ordinary chat, refine plans and let Agent create task lists before approving work.

- URL: https://docs.replit.com/features/agent/overview
- Locator: Plan mode; What you can build
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-01-1

Replit: Frequently asked questions. The cloud Project Editor saves files, history and the running app when the browser closes. This documents cloud persistence, not an unlimited Agent process lifetime.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: Frequently asked questions
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-local-desktop-execution

Replit: Build locally; Isolate builds in local sandboxes. The current desktop product page explicitly says Agent can build and run apps using the local environment and selected local folders. On supported Windows and macOS devices it names Microsoft Execution Containers for code/build-tool isolation. This does not establish a Linux local-execution sandbox.

- URL: https://replit.com/desktop
- Locator: Build locally; Isolate builds in local sandboxes
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:gaps-byoc-boundary

Replit: Compare deployment options; Full BYOC warning and availability. Full BYOC includes Agent/development execution in a customer tenant but is explicitly private preview, with eligibility/configurations confirmed through Enterprise onboarding. Published-app BYOC and Image Exports are early access and do not move the development/Agent control plane. Even Full BYOC leaves the control plane external and explicitly is not an entirely self-hosted or air-gapped Replit installation.

- URL: https://docs.replit.com/teams/bring-your-own-cloud.md
- Locator: Compare deployment options; Full BYOC warning and availability
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:gaps-cloud-microvm

Replit: Sandbox architecture; draft PR and review workflow. The current repository-contribution guide explicitly says the development sandbox runs in a microVM. Replit owns the contribution workflow: it creates a branch, commits/pushes changes, opens a GitHub draft PR or GitLab MR, and updates the request after review.

- URL: https://docs.replit.com/build/code/working-with-code.md
- Locator: Sandbox architecture; draft PR and review workflow
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-run-02-1

Replit: Tasks start running. Background tasks run in isolated project copies and do not change the main version until applied. The docs do not name these copies as containers, VMs or worktrees.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Tasks start running
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-03-1

Replit: What happens when I close my browser?. Files, history and running app are preserved in the cloud for a later visit. No worker-crash recovery test was performed.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: What happens when I close my browser?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-04-1

Replit: What is Replit Agent?. Agent sets up the project and infrastructure. Specific dependency-cache, port-collision and clean-remote-host behavior remains untested.

- URL: https://docs.replit.com/features/agent/overview
- Locator: What is Replit Agent?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-05-1

Replit: Control spending. Core and Pro Routines have per-run budgets checked after each step; an in-progress step can complete beyond the budget. Enterprise lacks the per-run budget.

- URL: https://docs.replit.com/features/agent/automations
- Locator: Control spending
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-06-1

Replit: Review and apply. Finished tasks expose a work log, test results and preview; active threads and board cards show task status.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Review and apply
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-07-1

Replit: Viewing Agent usage. Agent billing is effort-based and uses plan credits shared with cloud services. A controlled reconciliation against provider billing was not performed.

- URL: https://docs.replit.com/billing/ai-billing
- Locator: Viewing Agent usage
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-run-08-1

Replit: Tasks start running. Plan-based task limits cause additional background tasks to queue until slots are available. This is not evidence of per-host CPU or RAM scheduling.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Tasks start running
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-team-01-1

Replit: Personal vs. team workspaces. Team workspaces share projects with members; Core includes five collaboration seats and Pro fifteen. Simultaneous co-prompt ordering is not established by this source.

- URL: https://docs.replit.com/features/collaboration/team-workspaces
- Locator: Personal vs. team workspaces
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-shared-project-boundary

Replit: Build with teammates; independent threads and shared board. Distinct invited teammates can start their own Agent threads and tasks in the same project, share the board, view history and review/apply ready work. The guide emphasizes separate threads; it does not establish multiple humans sending instructions into the same active Agent conversation/work item.

- URL: https://docs.replit.com/build/invite-teammates.md
- Locator: Build with teammates; independent threads and shared board
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-team-02-1

Replit: Personal vs. team workspaces; Managing members. Personal workspaces have an admin and project guests; team workspaces add members with access to all workspace projects. Admins can invite and remove members.

- URL: https://docs.replit.com/features/collaboration/team-workspaces
- Locator: Personal vs. team workspaces; Managing members
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-team-02-2

Replit: Configure single sign-on. SAML SSO requires Enterprise and organization/identity-provider admin access. SSO does not automatically invite users; invitations or SCIM manage membership.

- URL: https://docs.replit.com/teams/configure-saml-sso
- Locator: Configure single sign-on
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-team-03-1

Replit: Review and accept; Review and apply. Humans approve plans before background execution and apply or dismiss finished changes before they affect the main version.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Review and accept; Review and apply
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-team-05-1

Replit: Review and apply. Ready tasks expose a work log, test results and live preview with Apply or Dismiss decisions. Review effort and missed evidence were not measured.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Review and apply
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-code-review-pane

Replit: Changes and pull requests. The product Changes pane switches between local changes and linked pull requests, shows branch/description details and renders the proposed code diff with added/removed lines. Linked requests also appear in Details and review feedback can be addressed through Agent.

- URL: https://docs.replit.com/build/code/navigate-your-workspace.md
- Locator: Changes and pull requests
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-ship-01-1

Replit: Review and apply. Task review retains a work log, test results and a live preview in the task flow. A cross-task artifact gallery was not established.

- URL: https://docs.replit.com/core-concepts/agent/task-system
- Locator: Review and apply
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-ship-02-1

Replit: App Testing. With App Testing enabled, Agent periodically tests apps it builds in an actual browser and fixes issues it finds; it is available for Full Stack JavaScript and Streamlit Python web apps. Documentation is not proof of mandatory independent review or an enforced passing test gate.

- URL: https://docs.replit.com/features/agent/app-testing
- Locator: App Testing
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-ship-03-1

Replit: Apply changes safely. Applying tasks invokes AI-assisted conflict resolution. The source does not establish a GitHub PR workflow.

- URL: https://docs.replit.com/learn/build-in-parallel
- Locator: Apply changes safely
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-ship-04-1

Replit: How do I publish my app?. Users publish to a live URL from the Project Editor. Production authorization and revision binding were not tested.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: How do I publish my app?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-ship-05-1

Replit: What happens if Agent makes a mistake?. Agent creates checkpoints that users can roll back to when a change is wrong.

- URL: https://docs.replit.com/features/agent/overview
- Locator: What happens if Agent makes a mistake?
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-main-app-license

Replit: Replit Ownership; limited access rights. The current service terms reserve all rights in the Replit Service and related software to Replit and give users only the expressly granted limited access rights. This classifies the main Agent/platform as proprietary, separately from user-created code and any separately licensed public client/SDK components.

- URL: https://replit.com/terms-of-service
- Locator: Replit Ownership; limited access rights
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-own-02-1

Replit: Import code and design. Users can import GitHub projects and uploaded files. Exported task history and complete self-hosting are not established.

- URL: https://docs.replit.com/learn/projects-and-artifacts/project-editor
- Locator: Import code and design
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-own-03-1

Replit: Model improvement. Pro users can opt out of Model Improvement in Personalization settings; Replit states it does not use Enterprise customer content to train models. The page names no such control for Starter or Core.

- URL: https://docs.replit.com/legal-and-security-info/model-improvement
- Locator: Model improvement
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-own-04-1

Replit: How billing works. Monthly plan credits cover Agent and other cloud services such as published apps, storage and databases under usage-based billing, with alerts, budget limits and purchasable credit packs. The page does not list network transfer or state an overage rate.

- URL: https://docs.replit.com/billing/ai-billing
- Locator: Getting started; Managing your spend
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-own-04-2

Replit: Starter Plan. Upgrading to Core gives more storage and monthly credits that also let users pay as they go.

- URL: https://docs.replit.com/billing/plans/starter-plan
- Locator: Upgrading to Core
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:gaps-flat-plan-billing

Replit: Tiered monthly credits; up to 15 builders; no per-user fees. The current Pro documentation explicitly supplies a flat recurring team plan with tiered monthly credits and up to 15 builders, with no per-user fees. Core/Pro subscriptions and usage credits are documented; one-off credit-pack top-ups are prepaid consumption rather than a one-time software license.

- URL: https://docs.replit.com/billing/plans/replit-pro.md
- Locator: Tiered monthly credits; up to 15 builders; no per-user fees
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:gaps-current-plan-offering

Replit: Monthly/Yearly Core, Pro and Enterprise plan offering. The current public plan offering lists recurring Core and Pro subscriptions and an Enterprise sales plan. It does not offer the whole ADE free without a paid tier or a one-time software license. The page defaults to annual-billing display; this pass does not convert annual prices or infer a USD monthly price from a dollar sign.

- URL: https://replit.com/pricing
- Locator: Monthly/Yearly Core, Pro and Enterprise plan offering
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:gaps-default-core-price

Replit: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation. The immutable first-party script loaded by the public pricing page defines the non-legacy default Core monthly price as 2000 cents with a 20-USD monthly allocation. The old 2500-cent option is explicitly legacy-only. Annual pricing and restricted regional Core offers are separate entries. This establishes the default public Core plan at USD 20 per month without converting an annual rate.

- URL: https://cdn.replit.com/_next/static/chunks/2kybev8fpsqw3.js
- Locator: Pricing catalog module 596139; Core default monthly Stripe price and USD allocation
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-13

### replit:nov08-own-06-1

Replit: Get support directly from Agent. The November 6 changelog documents Agent-assisted support investigation and Pro ticket submission. This is shipped release activity, not a shutdown notice.

- URL: https://docs.replit.com/updates/2026/11/06/changelog
- Locator: Get support directly from Agent
- Evidence kind: documented
- Source date: 2026-11-06
- Retrieved: 2026-11-08

### replit:nov08-own-08-1

Replit: What you get; Limitations. Starter offers recurring daily Agent credits capped monthly and monthly cloud credits, with one published app whose public link expires after thirty days. Full build, connectors and Plan mode require Core.

- URL: https://docs.replit.com/billing/plans/starter-plan
- Locator: What you get; Limitations
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08

### replit:nov08-own-09-1

Replit: Effort-based pricing. Agent uses effort-based paid pricing with plan credits; actual charges depend on request complexity and cloud services. A fixed average task price is not documented.

- URL: https://docs.replit.com/billing/ai-billing
- Locator: Effort-based pricing
- Evidence kind: documented
- Source date: Not stated
- Retrieved: 2026-11-08
