--- schema_version: 3 rubric_version: "0.3" canonical_url: "https://podium.do/compare/agents/amp-vs-cmux/" data_url: "https://podium.do/compare/agents/amp-vs-cmux/data.json" generated_at: 2026-09-30 last_checked_at: 2026-09-23 last_cross_checked_at: 2026-09-23 next_check_at: 2026-10-07 publisher: "Podium" --- # Amp vs cmux > 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. The same evidence rules apply to Podium and its competitors, but they do not remove this conflict of interest. This comparison has 3 criteria with sourced findings for both products, including 3 that a second agent cross-checked for both. 14 criteria have a sourced finding for at least one product. "Sourced" findings passed publication validation. "Agent cross-checked" findings also received a separate agent source pass, not necessarily a hands-on test. Humans approve the rubric, templates and prototype; they do not review every finding. It does not declare a winner. A missing sourced finding is not evidence that a capability is absent. - Amp source checks: 2026-09-23. - cmux source checks: 2026-09-23. - Canonical HTML: https://podium.do/compare/agents/amp-vs-cmux/ - Machine-readable JSON: https://podium.do/compare/agents/amp-vs-cmux/data.json - Methodology: https://podium.do/compare/agents/methodology/ ## Access and agent choice ### ACC-01: Client access Judgment rule: List desktop OS and minimum versions, iOS, Android, browser, mobile browser, CLI and editor extensions separately. For each client, record start, steer, approve, review and resume actions, notifications and plan restrictions. Test moving the same task from desktop to phone; distinguish an installable mobile app from a mobile website and from status-only monitoring. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Amp documents web, Apple apps and terminal access. Availability: unknown Delivery: native Scope: surfaces=Amp web, Mac and iOS, Amp CLI, Amp Orbs; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - The cited launch note gives TestFlight distribution, not App Store availability. - desktop_os — Desktop os [supported]: macOS app. Sources: amp:intro. - mobile_apps — Mobile apps [supported]: iPhone and iPad app access is documented; the iOS launch note specifies TestFlight distribution. Sources: amp:intro, amp:ios-announcement. - browser — Browser [supported]: Web client. Sources: amp:intro. - mobile_browser — Mobile browser [unknown]: Mobile browser: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - cli — Cli [supported]: Terminal CLI. Sources: amp:intro. - editor_extensions — Editor extensions [unknown]: Editor extensions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - task_actions — Task actions [unknown]: Task actions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - notifications — Notifications [supported]: Apple apps notify when threads need input. Sources: amp:intro. - cross_device_continuity — Cross device continuity [unknown]: Cross device continuity: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: amp:intro, amp:ios-announcement #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Mac desktop and gated iOS beta are advertised. Availability: unknown Delivery: unknown Scope: surfaces=desktop, ios-beta; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Other builds announced; no installation test. - desktop_os — Desktop os [supported]: macOS. Sources: cmux:site. - mobile_apps — Mobile apps [supported]: iPhone/iPad TestFlight; Founder early access. Sources: cmux:site. - browser — Browser [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - mobile_browser — Mobile browser [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - cli — Cli [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - editor_extensions — Editor extensions [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - task_actions — Task actions [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - notifications — Notifications [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - cross_device_continuity — Cross device continuity [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: cmux:site ### ACC-02: Agent and model choice Judgment rule: List supported harnesses and model providers separately, including custom adapters. Record whether the product embeds a harness, controls its sessions through an API, or only launches its terminal command. Verify at least two different harnesses before describing mixed-harness operation as observed. #### Amp 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. #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Agent support is terminal-based. Availability: unknown Delivery: unknown Scope: surfaces=desktop, ios-beta, remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Terminal compatibility does not establish structured feature parity. - harnesses — Harnesses [supported]: Runs terminal CLIs such as Claude Code, Codex and OpenCode. Sources: cmux:site. - model_providers — Model providers [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - custom_adapters — Custom adapters [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - session_integration — Session integration [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - mixed_harness_operation — Mixed harness operation [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: cmux:site ### ACC-03: Subscriptions, API keys and vendor credits Judgment rule: Record bring-your-own agent subscription, bring-your-own API account, vendor credits and local models as separate routes. List supported plans, models/modes, multiple-account switching and what works without a vendor account or token purchase. Existing subscription support cannot be inferred from API-key support. Record required extra payments and documented provider restrictions. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Amp supports linked subscriptions, BYOK and usage credits. Availability: unknown Delivery: native Scope: surfaces=Amp web, Mac and iOS, Amp CLI, Amp Orbs; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - agent_subscriptions — Agent subscriptions [supported]: ChatGPT subscription linking documented. Sources: amp:pricing. - api_accounts — Api accounts [supported]: BYOK. Sources: amp:pricing. - vendor_credits — Vendor credits [supported]: Purchased credits cover model/tool usage. Sources: amp:pricing. - local_models — Local models [unknown]: Local models: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - account_switching — Account switching [unknown]: Account switching: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - vendor_account_requirement — Vendor account requirement [unknown]: Vendor account requirement: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provider_restrictions — Provider restrictions [unknown]: Provider restrictions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: amp:pricing #### cmux 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-04: Onboarding and project prerequisites Judgment rule: Measure fresh install to first successful task, with manual steps and failures. Test a local directory without Git, a local Git repo without a remote, and a GitHub-backed repo separately. Record whether account, project, host, credential and permission prerequisites are explained before accepting an unusable prompt. Evaluate managed-cloud setup and first-class BYO VPS installer/onboarding independently of hidden settings or a DIY shell recipe. #### Amp 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. #### cmux 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-05: Programmable access Judgment rule: Inventory actual CLI, API, SDK, MCP and webhook operations for create, inspect, steer, stop and review. Record authentication and API stability. Having an MCP client that uses external tools is different from exposing the product to other agents over MCP. #### Amp 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. #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Pinned CLI implements session listing. Availability: source-only Delivery: unknown Scope: surfaces=desktop; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Other API operations and authentication were not code-audited. - cli — Cli [supported]: sessions list filters and JSON output. Sources: cmux:code. - api — Api [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - sdk — Sdk [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - mcp_server — Mcp server [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - webhooks — Webhooks [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - operations — Operations [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - authentication — Authentication [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - stability — Stability [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: cmux:code ### ACC-06: External tools and extensions Judgment rule: Record MCP client support, plugins, custom tools, skill/instruction import, integration authentication and permission scope. Name which component provides each connection and whether setup is product-managed or inherited from the underlying harness. Verify one external-tool call and its access boundary where available. #### Amp 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. #### cmux 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 Judgment rule: For each desktop/mobile client, record native platform UI, Electron, Tauri, React Native, web/PWA or unknown, plus hybrids. Require official technical docs or pinned source/build evidence. Tauri is not synonymous with fully native UI. Keep implementation choice separate from measured responsiveness and usability. #### Amp 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. #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Vendor describes a native Mac implementation. Availability: unknown Delivery: unknown Scope: surfaces=desktop, ios-beta, remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Other atomic questions remain unverified; no shared hands-on scenario was run. - desktop_implementation — Desktop implementation [supported]: Swift/AppKit using libghostty. Sources: cmux:site. - mobile_implementation — Mobile implementation [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - hybrids — Hybrids [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - implementation_evidence — Implementation evidence [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-12-22. Sources: cmux:site ## Planning and context ### PLAN-01: Intake and external tracker relationship Judgment rule: Record local creation, prompt intake, issue import and chat/Git triggers. Identify the authoritative tracker, stable issue IDs, one-way or two-way sync, supported edits and operations requiring a trip back to Linear/GitHub/Jira. Importing or attaching a ticket is not native issue management. Answer PLAN-06 and PLAN-07 separately. #### Amp 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. #### cmux 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. ### PLAN-02: Durable task plans Judgment rule: Record task plans and acceptance criteria, editors, revision history and links to implementation. Test amending a task while work is running, restarting and revisiting it later. A task-specific starting brief, reusable memory and a persistent product specification are different objects; product specs are judged in PLAN-08. #### Amp 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. #### cmux 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. ### PLAN-03: Hierarchy, dependencies and evolving scope Judgment rule: Record epics, arbitrary parent/child depth, blockers, readiness, dependency enforcement and state propagation. Start with a simple interactive task, grow it into an epic and retain its identity, discussion, history and outputs. Verify blockers actually prevent dispatch. Record whether a rigid preselected workflow is required, and whether changing scope requires recreating work. #### Amp 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. #### cmux 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. ### PLAN-04: Shared context and memory Judgment rule: List repository instructions, skills, project docs and cross-session/cross-harness memory. Record scope, provenance, citation, correction/deletion and stale-context controls. Test what survives a new session or colleague takeover. A notes page or shared file is not automatically a maintained spec or managed memory. #### Amp 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. #### cmux 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. ### PLAN-05: Architecture and API awareness Judgment rule: Record code search, repository indexing, external knowledge and multimodal inputs, with source freshness and access scope. Ask an agent to use an existing API under a documented architecture rule, then propose a conflicting change. Check retrieval, citation, conflict detection and review-time enforcement separately. A large context window or an instruction file alone does not prove architectural consistency. #### Amp 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. #### cmux 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. ### PLAN-06: Native issue management and idea backlog Judgment rule: Enumerate create, edit, discuss, prioritize, label, assign, search, filter, archive, reopen and project/epic views within the product. Save an idea without creating a running agent, refine it with another person, and explicitly mark it ready or dispatch it later. Record separate task/session entities, metadata depth, multiple sessions per task, durable state transitions and whether an external tracker remains necessary. #### Amp 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. #### cmux 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. ### PLAN-07: Agent-native issue operations Judgment rule: Verify an agent can read/create/update the same durable issue IDs and fields humans use, claim/assign work, change state, create dependencies/children and report blockers/results through documented CLI/API/MCP. Check that human views reflect actual writes with attribution, permissions and conflict handling. Distinguish shared authoritative records, synchronized external records, agent-private metadata and prompt-only conventions. #### Amp 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. #### cmux 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. ### PLAN-08: Living product specifications Judgment rule: Record persistent requirements across tasks/releases, editable by humans and agents with attributable revisions and approval rules. Verify requirement-to-task/implementation links, retrieval during later tasks, drift detection and consideration during review/quality control. Amend a requirement after one task ships, then implement another. A one-time spec-to-plan workflow, per-task brief, memory store or unreferenced document does not establish a living product spec. #### Amp 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. #### cmux 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 Judgment rule: Record independently running sessions and tasks, documented quotas and observed concurrency. Describe how a user sees running, waiting, failed and finished work. Several chat tabs are not proof that runs execute concurrently. #### Amp 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. #### cmux 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. ### COORD-02: Ownership and dispatch Judgment rule: Record assignment to humans or agents, claims, queues, routing and duplicate-work prevention. Test two workers attempting the same task. Distinguish a display label, an advisory lock and enforced exclusive ownership. #### Amp 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. #### cmux 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. ### COORD-03: Inspectable delegation and communication Judgment rule: Record parent/child roles, model/harness/effort choice, messages, result return and cross-harness teams. Distinguish product orchestration, provider-native subagents, installed orchestration skills and scripts. Record activation, auth and experimental flags. Verify actual child identity, live progress, retained results and ability to reopen or follow up after completion. A final sentence claiming two reviewers ran is not proof. Test the documented invocation as well as the shared natural-language request. #### Amp 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. #### cmux 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. ### COORD-04: Unattended triggers Judgment rule: Record schedules, event triggers, recurring tasks and completion conditions. Name where the scheduler runs, overlap handling, retries and whether closing the client stops it. A desktop cron recipe is a manual integration unless the product owns it. #### Amp 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. #### cmux 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. ### COORD-05: Intervention and attention Judgment rule: Record pause, stop, resume, steering, notifications, pending decisions and escalation. Test an in-run amendment and a harmless approval prompt in both chat and terminal modes. Record silent waits, hidden CLI-only questions and whether stop terminates execution while preserving history. Require discoverable errors rather than inferring success from silence. #### Amp 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. #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Attention indicators are advertised. Availability: unknown Delivery: unknown Scope: surfaces=desktop, ios-beta, remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Other atomic questions remain unverified; no shared hands-on scenario was run. - pause — Pause [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - stop — Stop [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - resume — Resume [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - steer — Steer [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - notifications — Notifications [supported]: Pane rings, sidebar badges and desktop notifications. Sources: cmux:site. - pending_decisions — Pending decisions [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - escalation — Escalation [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - visible_errors — Visible errors [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - chat_terminal_parity — Chat terminal parity [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - retained_history — Retained history [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: cmux:site ### COORD-06: Fleet and epic management UI Judgment rule: Use a disclosed fixture of 12 task/agent states across several epics, including blocked, failed, awaiting input, reviewing and completed work. Locate parent/child relationships, dependencies, attention needs, history and workload without reading every transcript. Record navigation steps and errors. Boards, graphs, waterfalls, timelines or another interface can qualify; no required visual form. State whether the fixture was simulated or used live agents. #### Amp 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. #### cmux 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. ### COORD-07: Workflow flexibility and orchestration visibility Judgment rule: Compare a quick interactive change with a growing epic. Record mandatory workflow/preset selection, natural-language configuration, per-agent model/effort control, changes during execution and whether the UI exposes what actually ran. Test a coordinator with two reviewer children; capture roles, relationships and results during work and after completion. Document discoverability and auth friction without judging an unsupported magic prompt as proof of missing capability. #### Amp 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. #### cmux 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. ## Execution and reliability ### RUN-01: Laptop-independent execution Judgment rule: List local, user-owned VPS/remote host, self-hosted service, vendor cloud and hybrid modes. Record provisioning, payer, compute resources, region, idle/max lifetime and disconnection rules. Close/disconnect the originating client and continue from another device. A hosted UI or keep-awake setting is not evidence of remote execution. Record managed-cloud convenience separately from BYO setup effort in ACC-04. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Orbs provide cloud execution per thread. Availability: unknown Delivery: native Scope: surfaces=Amp Orbs; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - local — Local [unknown]: Local: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - byo_remote — Byo remote [unknown]: Byo remote: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - self_hosted — Self hosted [unknown]: Self hosted: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - managed_cloud — Managed cloud [supported]: Per-thread cloud machine. Sources: amp:intro. - hybrid — Hybrid [unknown]: Hybrid: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provisioning — Provisioning [unknown]: Provisioning: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - payer — Payer [unknown]: Payer: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - resources — Resources [unknown]: Resources: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - region — Region [unknown]: Region: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - expiry — Expiry [unknown]: Expiry: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - client_disconnect — Client disconnect [supported]: Docs say agents continue after laptop closure. Sources: amp:intro. - other_device_continuation — Other device continuation [unknown]: Other device continuation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: amp:intro #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Existing remote hosts are supported. Availability: unknown Delivery: unknown Scope: surfaces=remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Managed cloud VM announcement is not treated as generally available. - local — Local [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - byo_remote — Byo remote [supported]: SSH or Mosh workspace; host supplied by user. Sources: cmux:ssh. - self_hosted — Self hosted [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - managed_cloud — Managed cloud [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - hybrid — Hybrid [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - provisioning — Provisioning [supported]: Uploads a versioned remote relay. Sources: cmux:ssh. - payer — Payer [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - resources — Resources [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - region — Region [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - expiry — Expiry [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - client_disconnect — Client disconnect [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - other_device_continuation — Other device continuation [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: cmux:ssh ### RUN-02: Workspace and process isolation Judgment rule: Record shared checkout, branch, worktree, container, VM and OS sandbox separately. Name filesystem, process, network and secret boundaries. Validate code separation with two changes; do not claim hostile-code containment without separate security evidence. #### Amp 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. #### cmux 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. ### RUN-03: Recovery, expiry and continuity Judgment rule: Test client disconnect, worker crash, service restart and documented sandbox expiry safely. Separate transcript reload, process reconnection, task resumption and state reconstruction. Record lost context, duplicated actions, manual repair and ability to continue a multi-day epic after compute replacement. Short sandbox lifetimes are reported with their continuity behavior, not automatically treated as failure. #### Amp 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. #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Remote reconnect behavior is documented. Availability: unknown Delivery: unknown Scope: surfaces=remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - No disconnect, restart or multi-day test. - client_disconnect — Client disconnect [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - worker_crash — Worker crash [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - service_restart — Service restart [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - expiry — Expiry [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - transcript_reload — Transcript reload [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - process_reconnect — Process reconnect [supported]: Retries 3, 6, 12 seconds up to 60; reattaches persistent remote session. Sources: cmux:ssh. - task_resume — Task resume [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - state_reconstruction — State reconstruction [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - context_loss — Context loss [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - duplicate_actions — Duplicate actions [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - manual_repair — Manual repair [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - multi_day_continuity — Multi day continuity [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: cmux:ssh ### RUN-04: Development environment reliability Judgment rule: Record dependency setup, node_modules/cache handling, snapshots, services, port allocation and secret injection. Start two workspaces with the same service requirements; note installation duplication, port collisions and repair steps. Repeat on a clean remote host. Record which problems the product handles automatically and which the user must diagnose. #### Amp 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. #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Remote browser forwarding is integrated. Availability: unknown Delivery: unknown Scope: surfaces=desktop, ios-beta, remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - Other atomic questions remain unverified; no shared hands-on scenario was run. - dependencies — Dependencies [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - caches — Caches [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - snapshots — Snapshots [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - services — Services [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - ports — Ports [supported]: Browser traffic routes through remote host; localhost targets remote services. Sources: cmux:ssh. - secrets — Secrets [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - duplicate_installs — Duplicate installs [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - collisions — Collisions [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - remote_setup — Remote setup [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - automatic_repair — Automatic repair [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: cmux:ssh ### RUN-05: Limits and failure handling Judgment rule: Record time, turn, token and spend limits; timeout, retry and provider-failure behavior. Test one controlled failure and a small safe budget. Record whether limits are warnings, enforced stops, or external billing controls. #### Amp 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. #### cmux 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. ### RUN-06: Truthful status and operational statistics Judgment rule: Record logs, traces, failure reasons, usage exports and statistics by task, agent, project and time. Induce a worker failure and an approval wait: check agent, task and board state agree and remain correct after reconnect. Distinguish working, blocked, failed, idle, ready for review and delivered. For speed/success claims disclose fixture, model, hardware, attempts and failures. UI responsiveness needs observed interaction timings; never infer a framework from lag. #### Amp 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. #### cmux 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. ### RUN-07: Per-task API and compute cost Judgment rule: Record visible model/API spend per task, session, child and epic, including aggregation across harness changes. Distinguish billed charges, estimates, tokens, subscription allowance and unavailable amounts; never render unknown subscription marginal cost as zero. Reconcile totals with provider evidence where available. Record compute fees separately, refresh delay, budget alerts, export and drill-down from summary statistics. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Per-thread cost detail is documented. Availability: unknown Delivery: native Scope: surfaces=Amp web, Mac and iOS, Amp CLI, Amp Orbs; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - task_cost — Task cost [unknown]: Task cost: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - session_cost — Session cost [supported]: Thread sidebar dollar amount opens detail. Sources: amp:pricing. - child_cost — Child cost [unknown]: Child cost: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - epic_cost — Epic cost [unknown]: Epic cost: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - harness_aggregation — Harness aggregation [unknown]: Harness aggregation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - billed_vs_estimated — Billed vs estimated [unknown]: Billed vs estimated: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - tokens — Tokens [unknown]: Tokens: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - subscription_allowance — Subscription allowance [unknown]: Subscription allowance: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - provider_reconciliation — Provider reconciliation [unknown]: Provider reconciliation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - compute_cost — Compute cost [unknown]: Compute cost: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - refresh_delay — Refresh delay [unknown]: Refresh delay: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - alerts — Alerts [unknown]: Alerts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - export — Export [unknown]: Export: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - drilldown — Drilldown [supported]: Usage explanation and credit breakdown. Sources: amp:pricing. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: amp:pricing #### cmux 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. ### RUN-08: Compute-aware scheduling and verification Judgment rule: Record concurrency limits, queues, CPU/RAM limits, backpressure, per-host resource awareness and reuse/deduplication of checks. Queue multiple browser end-to-end tests under a declared safe capacity; verify excess work queues or throttles rather than overloading the host. Inspect cancellation, fairness, recovery and whether overlapping epics share limits. Do not run an uncontrolled load test. #### Amp 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. #### cmux 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. ## Human collaboration and control ### TEAM-01: Live human collaboration Judgment rule: Record shared visibility, issue discussion, comments, presence and simultaneous co-prompting as independent capabilities. Use two named accounts to steer the same agent and record input ordering/conflict handling, attribution and permission controls. Read-only links and shared issues do not establish co-steering. Record team/free-tier restrictions and whether the original owner must stay online. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Multiplayer permits shared prompts within enabled Orb threads. Availability: unknown Delivery: native Scope: surfaces=Amp Orbs, Amp web, Mac and iOS; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - visibility — Visibility [unknown]: Visibility: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - discussion — Discussion [unknown]: Discussion: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - comments — Comments [unknown]: Comments: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - presence — Presence [unknown]: Presence: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - coprompting — Coprompting [supported]: Workspace colleagues prompt the same agent. Sources: amp:multiplayer. - ordering — Ordering [unknown]: Ordering: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - conflicts — Conflicts [unknown]: Conflicts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - attribution — Attribution [unknown]: Attribution: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - permissions — Permissions [supported]: All members can access enabled thread, files, terminal and secrets. Sources: amp:multiplayer. - plan_restrictions — Plan restrictions [supported]: Only non-private Orb threads; activation expires, one week default. Sources: amp:multiplayer. - owner_online — Owner online [unknown]: Owner online: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: amp:multiplayer #### cmux 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-02: Roles and access boundaries Judgment rule: Record organization/project/task roles, membership lifecycle, SSO and provisioning where offered. Test unauthorized access and revocation with consenting test accounts. Describe documented versus observed enforcement, including which plan provides it. #### Amp 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. #### cmux 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-03: Approvals and temporary access Judgment rule: Record command, tool, network, secret and delivery approvals, approver identity and scope lifetime. Demonstrate allow, deny and revocation, including temporary tunnels or shared access after its thread/session ends. Separate default full access, available safer modes and product-enforced policy from instructions the model is expected to follow. #### Amp 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. #### cmux 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-04: Decision and activity history Judgment rule: Record attributed actions, approvals, edits, discussion and decision links. Check whether history persists across users and sessions, can be exported, and can be altered. Use the word audit only with a defined retention and integrity model. #### Amp 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. #### cmux 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 Judgment rule: Evaluate locating pending reviews, understanding a change, navigating evidence, commenting, requesting changes and finding the next shipping action. Measure steps/time and missed evidence on a shared fixture. Record keyboard/narrow-screen usability, context switching, clarity of agent roles and preservation of review context. Generic diff/PR access and a guided review workflow are different capabilities. Link high-volume review findings to SHIP-06. #### Amp 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. #### cmux 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-06: Colleague takeover and continuity Judgment rule: Have a second authorized person take over ongoing work with the same task, session history, decisions, artifacts, permissions and runtime context. Test after the first person disconnects. Record ownership transfer, attribution and lost context. Separately record transferring to another model/harness; a forked transcript or shared link alone is not full human takeover. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Colleagues can use the same active thread and Orb. Availability: unknown Delivery: native Scope: surfaces=Amp Orbs, Amp web, Mac and iOS; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - ongoing_takeover — Ongoing takeover [supported]: Shared prompting. Sources: amp:multiplayer. - same_task — Same task [supported]: Same thread retained. Sources: amp:multiplayer. - session_history — Session history [unknown]: Session history: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - decisions — Decisions [unknown]: Decisions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - artifacts — Artifacts [unknown]: Artifacts: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - permissions — Permissions [unknown]: Permissions: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - runtime_context — Runtime context [supported]: Shared Orb terminal, files and portals. Sources: amp:multiplayer. - owner_disconnect — Owner disconnect [unknown]: Owner disconnect: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - ownership — Ownership [unknown]: Ownership: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - attribution — Attribution [unknown]: Attribution: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - context_loss — Context loss [unknown]: Context loss: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - harness_transfer — Harness transfer [unknown]: Harness transfer: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-23. Sources: amp:multiplayer #### cmux 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 Judgment rule: Record diffs, documents, screenshots, recordings, previews and test/reviewer outputs. Check for a searchable/browsable artifact gallery or equivalent retrieval, linked to task and exact revision, usable after sessions end. Reopen a completed child reviewer and retrieve its full findings. Check whether internal prompts or tool metadata unintentionally appear in the produced application or other user-facing output. In-chat attachments, persistent review evidence and a cross-task gallery get distinct answers. #### Amp 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. #### cmux 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. ### SHIP-02: Verification and spec gates Judgment rule: Record tests, lint, types, CI, independent review and persistent-spec conformance checks as required versus optional. Cause a failed test and a conflict with an existing product requirement. Verify review catches the conflict and delivery blocks where claimed. An agent saying checks passed is not a passing gate; record configured and enforced policy separately. #### Amp 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. #### cmux 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. ### SHIP-03: Git and pull request workflow Judgment rule: Record branches/worktrees, commits, PR creation, review comments, CI response, rebase and conflict handling. Complete one fixture change through a draft PR. Distinguish an integrated workflow from the agent running Git commands without product state. #### Amp 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. #### cmux 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. ### SHIP-04: Merge and deployment authority Judgment rule: Record who can approve, merge, release and deploy, plus checks against the exact revision. Verify the documented authority boundary without publishing real changes. PR creation, merge and production deployment are separate capabilities. #### Amp 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. #### cmux 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. ### SHIP-05: Completion evidence and rollback Judgment rule: Record task-to-commit/PR/build/deployment links, delivery status, retained evidence and rollback or revert support. Change the candidate revision after review and examine whether approval/evidence is invalidated. Agent exit alone does not prove delivery. #### Amp 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. #### cmux 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. ### SHIP-06: Batch review and high-volume shipping Judgment rule: Return to a queue of at least six completed fixture tasks and review a subset. Record summaries, grouping, risk/size filters, retained reviewer findings, artifact navigation, request-changes flow, approval of exact revisions, dependency-aware merge/release queues and clear next actions. Check stale approvals invalidate after edits and duplicate checks respect RUN-08. Distinguish basic diff/PR actions from a coordinated review-and-delivery queue; do not require Podium terminology. #### Amp 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. #### cmux 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 Judgment rule: Record license and revision per component, including client, server and hosted extensions. Distinguish open source, source-available and closed components. Repository visibility is not a license classification or proof of hosted parity. #### Amp 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. #### cmux 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-02: Hosting and exit Judgment rule: Record self-hosting scope, required vendor services, data export/import, standard formats and account cancellation behavior. Verify what remains usable without the vendor account. Exported code alone does not mean tasks, context and history are portable. #### Amp 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. #### cmux 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-03: Data handling and telemetry Judgment rule: Record where code, prompts, credentials, logs and artifacts go, retention/deletion, training use, residency and subprocessors. Separately record telemetry disclosure, collection defaults, opt-in/opt-out controls and observed first-run prompts. No consent dialog is an observation, not proof of no telemetry, secret telemetry or unlawful processing. Separate orchestration-vendor and model-provider policies. #### Amp 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. #### cmux 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-04: Price and included usage Judgment rule: Record currency, billing interval, seats/seat minimums, workspace charges, included usage, credits, trial conditions, overages, taxes treatment and separate model/compute costs. Map billing routes to ACC-03. Cite public prices or dated quotes. Per-seat versus pooled billing is a fact, not a universal quality judgment. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Model and Orb usage are separate billing dimensions. Availability: unknown Delivery: native Scope: surfaces=Amp web, Mac and iOS, Amp CLI, Amp Orbs; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - currency — Currency [unknown]: Currency: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - interval — Interval [unknown]: Interval: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - seats — Seats [unknown]: Seats: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - seat_minimum — Seat minimum [unknown]: Seat minimum: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - workspace_fees — Workspace fees [unknown]: Workspace fees: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - included_usage — Included usage [unknown]: Included usage: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - credits — Credits [unknown]: Credits: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - trial — Trial [unknown]: Trial: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - overages — Overages [supported]: Purchased credits; 12-month expiry. Sources: amp:pricing. - taxes — Taxes [unknown]: Taxes: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - model_cost — Model cost [supported]: Credits for actual model/tool usage. Sources: amp:pricing. - compute_cost — Compute cost [supported]: Separate Orb minute allowance. Sources: amp:pricing. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: amp:pricing #### cmux 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-05: Scenario cost and controls Judgment rule: Price stated workloads for one, two and five developers, with fixed tasks, concurrency, tokens and compute-hours. The two-person scenario models Till and Michael collaborating. Include subscription, platform, model and compute charges; separate fixed, variable, included and unknown costs. No invented average task cost. Link cost visibility and reconciliation to RUN-07. #### Amp 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. #### cmux 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 Judgment rule: Record GA/beta/access restrictions, support channels, documented response commitments, release activity, status history and deprecation/export options. Funding, stars and popularity can be context but are not reliability scores. An archived repository does not prove the hosted service is discontinued. #### Amp 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. #### cmux 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-07: Enterprise assurance Judgment rule: Record each claimed assurance separately: ISO standard/certificate scope, issuer and validity; SOC 2 report type, covered service and audit period; report/certificate access and verification date. Distinguish public documentation, vendor assertion, independently accessible evidence and unavailable evidence. A logo, enterprise pricing tier, SSO or a provider certification does not prove this product is certified or audited. Report controls in TEAM-02 separately; no legal-compliance verdict. #### Amp 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. #### cmux 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 Judgment rule: Distinguish an ongoing free tier, time-limited trial, credits-only trial, open-source self-hosting costs, paid-only access and gated early access. Map which shared scenarios work for free, especially two-person collaboration, BYO subscriptions, remote compute, mobile, issue management and review. Record card requirement, usage caps and whether meaningful evaluation needs payment or sales approval. #### Amp Verification status: Agent cross-checked (agent-cross-checked) Support: partial Hobby includes product features; inference and managed compute can cost extra. Availability: unknown Delivery: native Scope: surfaces=Amp web, Mac and iOS, Amp CLI, Amp Orbs; version=Public documentation checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - This is a source pass; unfilled atomic questions remain unknown and no shared scenario was run. - ongoing_free — Ongoing free [supported]: Hobby product access. Sources: amp:pricing. - trial — Trial [unknown]: Trial: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - credits_trial — Credits trial [unknown]: Credits trial: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - self_host_cost — Self host cost [supported]: Own runners permitted; provider charges remain. Sources: amp:pricing. - paid_only — Paid only [unknown]: Paid only: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - early_access — Early access [unknown]: Early access: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - free_scenarios — Free scenarios [supported]: Use own credentials and runner. Sources: amp:pricing. - card_required — Card required [unknown]: Card required: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - usage_caps — Usage caps [unknown]: Usage caps: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. - paid_evaluation — Paid evaluation [unknown]: Paid evaluation: Initial primary-source pass did not establish this question. No installed-product or shared-scenario test was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: amp:pricing #### cmux Verification status: Agent cross-checked (agent-cross-checked) Support: partial Desktop use is advertised as free. Availability: unknown Delivery: unknown Scope: surfaces=desktop, ios-beta, remote; version=Official sources checked 2026-09-23; plan=not specified; os=not specified; execution_modes=not specified; region=not specified; harness=not specified. Limitations: - iOS early access and future cloud offerings are separate. - ongoing_free — Ongoing free [supported]: Free desktop terminal. Sources: cmux:site. - trial — Trial [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - credits_trial — Credits trial [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - self_host_cost — Self host cost [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - paid_only — Paid only [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - early_access — Early access [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - free_scenarios — Free scenarios [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - card_required — Card required [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - usage_caps — Usage caps [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. - paid_evaluation — Paid evaluation [unknown]: Initial official-source pass did not establish this question; no hands-on scenario was run. Checked 2026-09-23; agent cross-checked 2026-09-23; check again by 2026-10-07. Sources: cmux:site ### OWN-09: Pricing transparency Judgment rule: Record publicly stated units, included limits, overage rates, compute/model pass-through or markup, minimum commitment, cancellation and sales-only unknowns. Use transparent, partially specified, quote-only or unknown, with named missing fields. A quote-only enterprise price is a disclosed procurement constraint, not proof of dishonesty. #### Amp 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. #### cmux 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. ## Sources ### amp:intro Amp introduction. Documents web, Apple apps, CLI and per-thread cloud Orbs. - URL: https://ampcode.com/docs - Locator: Quickstart and surfaces - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### amp:ios-announcement Amp on iOS & macOS. iOS app is available through TestFlight; macOS app is a direct download. - URL: https://ampcode.com/news/amp-on-ios-and-macos - Locator: August 28, 2026 launch note - Evidence kind: documented - Source date: 2026-08-28 - Retrieved: 2026-09-23 ### cmux:site cmux. Terminal workspace with native panes and an iOS TestFlight companion. - URL: https://cmux.com/ - Locator: Features; FAQ - Evidence kind: vendor-claimed - Source date: Not stated - Retrieved: 2026-09-23 ### amp:pricing Amp pricing. Free product features with separate model/Orb costs, subscription and BYOK routes, thread cost detail. - URL: https://ampcode.com/docs/pricing - Locator: Hobby; charging; notes - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### cmux:code cmux source: CLI/CMUXCLI+SessionsList.swift. runSessionsCommand parses agent/session/workspace filters and optional JSON output. - URL: https://github.com/manaflow-ai/cmux/blob/8c53ab55d2e33f785f1bdafda53d99a561d8c098/CLI/CMUXCLI+SessionsList.swift - Locator: Named definitions and implementation in pinned file - Evidence kind: source-inspected - Source date: Not stated - Retrieved: 2026-09-23 - Commit: 8c53ab55d2e33f785f1bdafda53d99a561d8c098 - Path: CLI/CMUXCLI+SessionsList.swift ### cmux:ssh cmux SSH. Remote sessions use a relay and reconnect with bounded exponential backoff. - URL: https://cmux.com/docs/ssh - Locator: Usage; Mosh; Browser panes; Reconnect - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23 ### amp:multiplayer Amp multiplayer. Non-private Orb threads can enable time-limited shared prompting and environment access; owner pays. - URL: https://ampcode.com/docs/collaborate/multiplayer - Locator: Activation and access - Evidence kind: documented - Source date: Not stated - Retrieved: 2026-09-23