A source-linked comparison across the complete Podium ADE rubric. 43 criteria sourced for both products; 33 criteria also agent cross-checked for both. 49 rows have at least one sourced finding, including 48 with an agent-cross-checked finding. No score or winner is inferred.
Each row shows a finding's verification status, support, check date and answer. Its scope, limitations, atomic answers and sources are on the product's page. Humans approve the rubric, templates and prototype; they do not review every finding. An agent source cross-check is not a hands-on product test. A missing sourced finding is not evidence that a capability is absent.
Client access: Jules has a browser client; mobile action parity was not established. Jules Tools is an npm-installed remote-session CLI with a TUI dashboard. Web: start, approve or revise the plan, chat feedback, pause and resume, publish branch or PR. CLI: start, list and pull sessions. Browser notifications can signal completion or need for input. The same Google account sees its sessions in the web app and in Jules Tools (remote list); a device handoff was not tested. Not established: desktop os, mobile apps, mobile browser, editor extensions.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Podium ships desktop, CLI and browser clients, including phone-browser control. The native iPhone app is private beta; the complete download offering contains no native Android app.
Agent and model choice: Only the Jules agent runs tasks; the complete plan comparison lists Gemini models only and no other coding harness. Jules documents Gemini model access across its plans; separate external coding harness support is not established. No other harness can run, so mixed operation does not apply. Not established: custom adapters, session integration.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium launches the native Claude Code, Codex, Grok, OpenCode, Cursor and Pi CLIs in persistent terminals on machines you control. The 0.2.0 release calls Pi fully supported. Models come from each harness catalog, and capabilities differ per harness: Pi declares no quota, handoff or hooks. Mixed-harness operation was not exercised.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Subscriptions, API keys and vendor credits: Jules Pro/Ultra benefits are included in corresponding Google AI plans for individual Gmail accounts. This is not Claude or ChatGPT coding-harness subscription reuse. Jules API keys (at most 3) access Jules itself; no bring-your-own model key is documented. Google account eligibility controls Jules access and paid upgrades. Paid plan upgrades require an individual Gmail account; Workspace/business upgrades are not established. Not established: vendor credits, local models, account switching.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium supports native coding-agent logins and managed provider credentials. Claude subscriptions (via native login or a managed setup-token) and local ChatGPT/Codex login are supported paths, alongside Anthropic and OpenAI API keys. Docs list billing and hosted metering as not implemented product claims.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Repoless REST API sessions create an ephemeral cloud environment from a prompt without a source repository. Onboarding connects a Google account and grants the Jules GitHub App selected repository access. A task selects a repository/branch and optional setup script before cloud provisioning. Sign in with Google, connect GitHub, choose repo and branch, write a prompt and approve the plan. Jules works only on GitHub repositories the user grants; other version control is future work. Jules infers setup from the repository, AGENTS.md or README, and setup scripts can be validated with Run and Snapshot. Tasks run only in Google-hosted cloud VMs; no user-host onboarding exists.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Docs describe a first-run flow (install, podium, register a Git repository, confirm a detected logged-in harness) and a headless VPS installer with machine joining. Setup time and failure rate were not measured, and no self-serve managed cloud setup is documented. The current README and installation guide use podium.do/download and podium.do/install.sh as the canonical stable entrypoints.
remote list, remote new and remote pull manage cloud sessions; --parallel creates several runs. REST resources include sources, sessions and activities for programmatic coding workflows. The TUI exposes session monitoring and side-by-side diffs; CLI operations require Google sign-in. Jules REST API authenticates with X-Goog-Api-Key; at most three keys exist at a time. The REST API is explicitly alpha and experimental, with changing schemas and keys possible. The @google/jules-sdk TypeScript SDK starts and monitors sessions. @google/jules-mcp exposes session create, list, state, reply/approve, review-context, diff and cache tools to other agents.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
The podium CLI covers issue create, show, update, claim, dependencies, artifacts, session send/status/read/stop and review actions, and the server exposes the same issue commands as a bearer-token MCP tool endpoint. No documented public HTTP API, SDK or webhooks were found.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
External tools and extensions: MCP client support covers only Linear, Stitch, Neon, Tinybird, Context7 and Supabase. Jules deliberately limits MCP to hand-selected servers; users cannot add their own servers or tools. Jules reads AGENTS.md at the repository root. Each MCP service connection uses that service's API key, entered in Settings and stored encrypted. Integrations request read-only access by default and servers are vetted for minimal permissions; per-tool user controls are not documented. Each user adds service connections in their own Jules Settings page; Jules provides the vetted servers. Not established: plugins.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium gives agents its own issue tools over CLI and MCP, and agent profiles import and export Claude Code agent files. No Podium documentation for user-configured MCP clients, plugins or custom tools was found.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources
Client implementation: No desktop app is documented; Jules Tools is a terminal CLI/TUI. The @google/jules 0.1.42 npm package is a Node.js installer that downloads and runs a prebuilt Go platform binary. Not established: mobile implementation, hybrids.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Desktop releases use a Tauri 2 shell that serves the Podium web UI; mobile source uses Expo and React Native. A native iPhone release is described as private beta.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Applying the jules label to a GitHub issue starts work and returns a PR link; GitHub remains the issue system. Tasks are created from the web prompt box. Natural-language prompts with optional PNG/JPEG images. The jules label on a GitHub issue starts a task; no other import is documented. Sessions have stable IDs in the API and CLI. Jules comments on the labelled issue and links the pull request; issue edits stay in GitHub.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium issue records are native and authoritative with stable references, CLI creation and editing, and agent-driven filing from conversation. The in-product assistant has Linear search, create and move tools when a key is configured, but no import or two-way tracker sync was found.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
A task presents step-by-step implementation plans with assumptions and setup details. Users request plan revisions through task chat. Plan steps and resulting implementation share the same task session. Jules revises plan steps in response to feedback. Jules replans on feedback; no plan revision history is documented. Session activities are immutable and retrievable through the API.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Issue brief, acceptance criteria, state paragraph and todos persist on the durable issue record. Release 0.3.0 removed the separate design and notes fields and appended their text to the brief. On the human issue page the title, description and acceptance are editable and the brief is read-only; agents edit the brief and other fields through issue commands.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Podium
Agent cross-checkedpartial
Podium supports persistent parent and child issues, phases and typed dependency links, including reparenting an existing issue without replacing its identity. Since 0.3.0 issue types are task, phase and decision: epic and other kinds are retired, and any issue with children acts as a parent. Dependency types are fixed to blocked-by, related, discovered-from, supersedes and duplicates. Cycles are refused and docs list an open blocker as a reason an issue cannot start. No mandatory workflow preset applies in the baseline.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Jules loads AGENTS.md at the repository root. During a task Jules saves preferences, nudges and corrections and references them in later tasks in the same repository; memory can be toggled per repository. README and AGENTS.md give environment setup hints. Memory is kept per repository. Memory can be turned off per repository; deleting individual memories is not documented.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
v0.3.0 routes Podium issue instructions and relay environment through terminal and engine session launch. Claude stream sessions use appended instructions and boundary callbacks; Codex server sessions use developer instructions, Grok ACP uses rules, and OpenCode uses the prompt system field. Claude and Codex boundary hooks can re-prime after compaction. Transcript mirroring is on by default; full-text indexing needs the command-palette flag, which defaults off. Agent profiles can carry markdown instructions. Curated memory, skills and memory correction or deletion controls remain unestablished. No instruction-delivery or compaction scenario was run.
Task creation accepts PNG/JPEG images totaling under 5 MB; this guide excludes follow-up image attachments. The agent works on the cloned repository in its VM; no indexing feature is documented. Context7 is among the allow-listed MCP servers. Only GitHub repositories the user grants are accessible.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Not established. Podium mirrors daemon transcripts by default, keeps a full-text index only when the command-palette flag is on, and stores session attachments. No repository code search, architecture awareness or API retrieval feature was found.
Native issue management and idea backlog: Users create tasks, not issues. Tasks can be deleted permanently; there is no archive. Suggested TODO cards can be started or dismissed. Suggested tasks start with Start, and plans need approval unless the timer auto-approves. No external tracker is required; a prompt alone starts a task. Not established: edit, discuss, prioritize, label, assign, search, filter, reopen, project epic views, task session separation, metadata, durable states.
Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium exposes native issue creation with an optional start flag, separate dispatch, editing, comments, labels, assignment, search, board filters, archive, sibling ordering and an issue tree. Issue records have their own identity separate from sessions and stages are durable. The idea-to-mission scenario was not run. v0.3.0 refuses an agent close or done update while issue sessions are computing unless --confirm-interrupt is supplied; guidance says to request review and close only on user instruction.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Agent-native issue operations: Session IDs are shared across the API, CLI and web URLs. Agents read session state and lists through MCP tools or the API. Agents create sessions through the API or MCP; Linear issues are reachable through the Linear MCP server. Not established: update, claim, assign, state changes, dependencies, children, results, human visibility, attribution, permissions, conflicts.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
CLI and MCP address the same canonical issue records for reads, creation, edits, claims, state, dependencies and artifacts. Relayed agents have worker capability scoped to their issue subtree, with --outside-scope confirmation for other existing issues. attachSession is not subtree-gated, but direct rehoming from a real issue is refused and an agent attach naming a Proposed target is refused. That does not make every Proposed subtree inert: operator attachment or spawn-time cwd binding can leave a session attached to a Proposed issue; newSubissue without targetId then bypasses the proposed-parent guard, creates a human-audience backlog child and attaches the existing session. This path remains at v0.3.0 source and was not exercised live. Concurrent-edit handling remains unknown.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Humans request edits to the proposed plan through chat; direct structured requirements editing is not established. Jules revises its task plan from feedback. Approve plan permits implementation, but the docs also describe timer-based automatic approval.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Sourcedpartial
The spec CLI and service (living specs under pspec with stable SP IDs) are in v0.3.0. Specs is an experimental, default-off feature listed on the edge channel: the flag controls the Specs UI, the spec line in CLI help and whether agents are told about the spec CLI. The podium spec command itself is dispatched, and the server specs service has no flag check, so direct CLI use does not need the flag. This agrees with the docs, which call specs not baseline rather than blocked. Not run end to end.
The guide lists Free/Pro/Ultra daily task caps of 15/100/300 and concurrent caps of 3/15/60, checked 7 November 2026; shutdown timing takes precedence. Several tasks run simultaneously, each in its own VM. Plans allow 3, 15 or 60 concurrent tasks. The repo view lists running, completed, failed and waiting tasks; API sessions report eight states.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Docs and release notes describe many sessions running as independent terminals, one worktree per issue, and several paired machines under one server, with session and issue state visible on the flight deck, board and CLI. Agent-initiated spawns are limited to 10 per target issue per UTC day. Achieved concurrency is unmeasured.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Ownership and dispatch: Adding the jules label to a GitHub issue assigns it to Jules; there is no other assignment model. Not established: human assignment, claims, queues, routing, duplicate prevention, ownership enforcement.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Issues carry an assignee, claim sets assignee and in_progress, a coordinator session can be set per issue, sessions have seats, and work can be placed on a chosen machine or agent profile. claim has no exclusivity check of its own, locks are advisory leases and Podium does not serialize agents editing one worktree, so exclusive ownership is not enforced.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Inspectable delegation and communication: A code critic and a Planning Critic review Jules's work; users cannot define roles. A real-time activity feed shows each step, and the critic's analysis is visible as it works. Completed tasks keep full logs and diffs and can be reopened. Chat follow-ups continue a session, and the API sends messages to it. Critic agents run automatically inside Jules; external agents invoke Jules through the MCP server or SDK. Not established: model harness effort, messages, results return, cross harness, orchestration owner, activation, authentication.
Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium orchestrates delegation itself: podium agent spawn starts a full child session on an issue with a chosen harness, model, effort or agent profile, mail carries messages, and bounded await reports the child result. Children are real sessions shown as seats on the flight deck. Agent-initiated spawns take a daily budget per issue. A complete delegated task with retained child findings was not run.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Podium
Sourcedpartial
The server owns a scheduler for cron and one-time automations that spawn agent sessions, skipping overlaps and not backfilling occurrences more than an hour late. The Automations UI is an edge-visibility feature that defaults off and docs list automations as non-baseline. Agents can subscribe to issue and session events.
The UI can pause work and later unpause it; this was documented rather than tested. The chat accepts feedback while the task runs and can revise the approach or plan. The activity feed and notification badge expose errors and intervention requests. Tasks can be paused or permanently deleted; no separate stop that keeps history is documented. Paused tasks can be resumed. Browser notifications report completion or a need for input. Plans wait for approval but auto-approve on a timer; feedback requests show in the feed and as an awaiting-feedback state. Completed tasks keep their logs and diffs.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Chat and native CLI views share a session. v0.3.0 defaults human controller chat to steer and immediately types it into running Claude Code, Codex, Grok and OpenCode TUIs that declare native busy-input queuing; undeclared harnesses wait for a boundary, and compaction waits. Mail and automation keep when-ready delivery. Stop, resume, questions, decision issues and offers remain available. This is inspected implementation, not a cross-harness runtime parity result.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Fleet and epic management UI: Failed and waiting tasks are labelled, and a red badge marks errors. Each repository view keeps its task history. Not established: fleet fixture, parent child, dependencies, workload, navigation errors, fixture mode.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Release 0.3.0 ships a flight deck showing a whole mission in one view: phases, every task and its state, who works on what, what is blocked and by what, and proposals. Done work stays visible. The CLI prints the same snapshot. The waterfall source is dormant and the Timeline view was deleted, so per-task timeline history is not shown. The shared 12-task UX scenario has not been run.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
Workflow flexibility and orchestration visibility: A prompt produces a plan to approve, then the task runs. Three templated scheduled tasks (performance, design, security) are offered; no workflow preset is required. Tasks are plain-language prompts. Feedback during a task makes Jules revise its approach or replan. Not established: growing epic, agent configuration, live roles, retained relationships, discoverability, auth friction.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
A quick task can be an interactive session or an issue; an issue can grow into a mission by gaining children while keeping its identity; no mandatory workflow preset applies in the baseline. Per-agent harness, model and effort are chosen at spawn or through agent profiles, and the deck shows seats. The coordinator-with-two-reviewers scenario was not run.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Laptop-independent execution: Jules Tools is a remote-session client; the coding worker executes in Google cloud VMs. The published worker architecture is Google-hosted cloud VMs, not user-operated execution servers. Jules is hosted only. Tasks run in cloud-based VMs, separate from the browser client. A VM is provisioned automatically for each task. Compute is included in the Jules plan. Task VMs are short-lived; the service has been read-only since 2026-11-11 and ends 2026-12-31. Jules explicitly lets users leave the app after submitting a task; it continues autonomously. Notifications report completion or plan readiness; cross-device task takeover was not established. Not established: hybrid, resources, region.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
The published Podium execution choices are local user machines and a user-owned VPS or paired machine. No vendor-operated agent host is in the complete download offering.
Each task runs in its own short-lived VM; no adversarial isolation test was run. Work starts from a chosen branch and is published as a new branch. Task VMs have internet access; no egress controls are documented. Repository environment variables are opt-in per task and fixed once it starts. Each task has its own VM, logs, environment and code changes.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Podium separates issue files with Git branches and worktrees, but its released daemon launches native host processes without product-managed container or VM provisioning.
Immutable API activities can be used to reconstruct the session’s history; this does not prove process recovery. Tasks continue after the user leaves the app. The service has been read-only since 2026-11-11 and ends 2026-12-31. Immutable session activities can reconstruct a session. Paused tasks resume. Users can rerun a task from its summary after editing the setup script or prompt.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Closing a browser tab does not stop the agent process on a running Podium host. Idle sessions may hibernate under configurable policies; a stopped session keeps its transcript, branch and resume reference. Release 0.2.0 says a failed update rolls back and running sessions keep running through the upgrade; database rollback remains a manual restore. Terminal reattachment goes through the driver adopt contract with process-identity and observation-lease checks. Worker-crash and multi-day behavior were not tested.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Development environment reliability: Repository setup scripts install project dependencies. Successful setup snapshots are reused by future tasks from the repository. Run and Snapshot executes the script and captures the resulting prepared environment. Long-running development servers and watchers are not supported in setup scripts; discrete install/test commands are supported. Repository-level environment variables can be enabled for a task. Future tasks can reuse a successful prepared environment snapshot; exact invalidation behavior is not established. Jules infers setup from the repository, AGENTS.md or README. Not established: ports, collisions, automatic repair.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Only machine setup is documented: the installer installs missing runtime tools and pairs a host, and the state directory holds server-managed secrets. Dependency caching, services, ports and automatic repair for project environments were not found.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Jules retries eligible failed steps such as network or transient install failures. Persistent failures produce a failed task; the source does not specify provider-specific retries. Published rolling 24-hour task limits are 15/100/300, with concurrent limits 3/15/60 for Free/Pro/Ultra. Limits count tasks per rolling 24 hours; no per-task turn limit is documented.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium exposes retryable errors, optional auto-continue with backoff, bounded waits and provider quota. Claude stream and hosted headless drivers enforce a supplied turn deadline, with no deadline when timeoutMs is absent. The one-shot headless server runner supplies its budget, default ten minutes. Agent spawns have a daily per-issue budget. Operator-configurable task-wide turn, token and spend caps remain unestablished; quota display is not enforcement.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The live activity feed reports steps, outputs, errors and feedback requests. Activity records surface outputs and errors for completed steps. Completion summary includes changed files and added/changed lines. Completion summary includes total runtime. A failed step is shown in the feed and a red notification badge; persistent errors mark the task failed.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
Podium offers local logs and crash export, structured session status, issue stats, a usage and analytics sheet with hourly list-price cost, per-task costs and host load panels. The 0.3.0 notes report a vendor benchmark of about 330 MB server memory against about 1.2 GB for an earlier Podium build, and 8 to 52 percent faster start; the method is published in the repository and was not reproduced here. Usage export and cross-reconnect consistency were not established.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
Per-task API and compute cost: The allowance is tasks per day and concurrent tasks by plan; no per-task cost is shown. Not established: task cost, session cost, child cost, epic cost, harness aggregation, billed vs estimated, tokens, provider reconciliation, compute cost, refresh delay, alerts, export, drilldown.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Since 0.2.0 Podium shows what each task costs, on the task header and the usage sheet, with per-session rows and descendant rollups. The 0.3.0 deck adds a mission cost chip. Figures are token estimates at public model list prices, not subscription invoices or provider bills.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Free, Pro and Ultra allow 3, 15 or 60 concurrent tasks. Task quotas are rolling 24-hour limits of 15, 100 or 300 by plan.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
Podium reports host memory, load and disk, auto-hibernates idle sessions under pressure, and provides named advisory resource leases. The merge-queue panel was removed; a shipping queue remains behind the Shipping flag. Concurrency limits and bounded test queuing were not established.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Live human collaboration: Paid plans are for individual accounts only; Workspace upgrades are not offered. Not established: visibility, discussion, comments, presence, coprompting, ordering, conflicts, attribution, permissions, owner online.
Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
The issue UI displays owner and visibility read-only and deliberately omits sharing controls. Backend share handlers and a Members settings section with invites and admin or member roles exist; they do not establish a finished human collaboration workflow. Docs say small teams can share an instance but the interface prioritizes one operator.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Roles and access boundaries: Paid plans cover individual Google accounts only. Not established: organization roles, project roles, task roles, membership, sso, provisioning, unauthorized access, revocation.
Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Podium defines member/admin instance roles and admin-only membership management. The released client authentication uses password-backed sessions and paired-device tokens without enterprise SSO.
The guide says an unattended plan eventually auto-approves on a timer; plan review is not an indefinite authorization gate. Environment variables are enabled per task and cannot change mid-task. Users publish the branch or PR; the API can auto-create PRs when asked. The API can require plan approval, and Reactive Mode limits PR-comment actions to @Jules mentions.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Agent-session management requests go through an operator approval broker with approve and deny; the privacy docs say lifecycle commands and automation requests may require operator approval. Harness permission prompts appear as a Permission needed state; credential copying during pairing is a per-grant opt-in. Command-level policy enforcement beyond the harness own modes was not established.
Session activities record the steps taken by user and agent. The API exposes activity collections with timestamp filters. API activities are documented as immutable once created. Activity immutability is a documented event-source contract; tamper resistance was not tested. Task history persists per repository.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Sourcedpartial
Issue actions, approval steps, comments and mail are recorded server-side. Issue activity events, including approval steps, are pruned by the server's janitor once they are older than 14 days or fall outside the newest 50,000 rows. That policy does not define all content retention, export or tamper-evident audit guarantees.
The expanded diff editor shows all files Jules changed. Users give real-time review feedback through the task chat. Users can ask Jules to revise logic, add tests or fix behavior from chat.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
Review is a documented loop: issue stage review, diff and checks, artifacts, offers with merge or send-back buttons, and a Tray of review-ready work. Release 0.3.0 adds quoting text from a reply or review finding into the next message and a full-height reading view with an outline. The board has a key map with a help sheet. Guided-review quality and narrow-screen use were not measured.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Podium
Agent cross-checkedpartial
The durable issue, session transcript, artifacts and mail persist for any later agent, and a live session can be handed to another machine in an edge feature. Colleague takeover by a second person was not established.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The feed includes mini diffs and a full changed-file diff editor. Jules can return a screenshot of the rendered frontend. Frontend verification can return visual test evidence with changes. Task logs and diffs are kept until shutdown and can be exported. Uploaded task images are not committed to the repository; other leakage paths are not documented.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Artifact commands store immutable server-side copies of issue-linked files, including images, video, HTML and documents, which render in the issue sidebar and offers and stay readable after the worktree is gone. Each task has an artifacts page grouped into screens, documents and reports, with filters and search. Revision linking remains untested.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources
Verification and spec gates: Setup scripts can run tests before snapshotting. Setup scripts can include linters. CI Fixer responds to GitHub Actions failures on Jules-created PRs. A critic agent reviews code and a Planning Critic reviews auto-approved plans before execution. CI Fixer repairs and resubmits; the source does not establish an immutable merge gate. Users configure repository setup/validation commands; immutable required delivery gates were not established. Not established: types, spec checks, required checks, requirement conflicts, enforced policy.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
In the experimental Shipping path a configured validation profile runs before landing (default argv bun run test with a 10 minute timeout) and a failed validation holds the order. Lint, type, CI and spec conformance gates and independent review requirements were not found as product-enforced policy.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Commit authorship is configurable as Jules, coauthored or user-only. Publish branch and Publish PR push results to GitHub; PR creation is separate from merging. Jules automatically detects and fixes failing GitHub Actions checks on the PRs it creates. Publish branch pushes the work to a new GitHub branch. Jules responds to PR review comments with commits; Reactive Mode limits it to @Jules mentions.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Issues own branches and worktrees, and issue actions rebase, open a pull request with gh (pr create --fill) and merge, subject to a merge-style setting (ff-only by default, with auto-rebase before merge). Podium does not resolve branch conflicts, and PR review comments and CI response were not established.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Merge and deployment authority: Users merge PRs in GitHub; the experimental fleet package can merge PRs sequentially. Not established: approve, release, deploy, exact revision, authority enforcement.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
The operator accepts work through offers and runs the merge action under a branch merge-lock; in the experimental Shipping path approval is frozen to an exact head and delivery lands on a local target branch by default. Release and deployment are not product features found in the sources.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The task summary identifies branch and commit details; a direct commit permalink was not established. Issue-triggered work returns a link to the PR for review. Publish branch or Publish PR exports work to GitHub; source distinguishes branch author and PR creator.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-07. Scope and sources
Podium
Agent cross-checkedpartial
Shipping orders record approved base and head SHAs, tested integration SHA, landed ref and validation result in a durable delivery receipt, and stale approvals hold the order. Shipping is experimental. The pr action records a PR URL on the issue. Build and deployment links and rollback were not found.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Podium
Agent cross-checkedpartial
The shipping service records revision-specific approval, configured validation and delivery receipts. The Shipping panel is an experimental edge toggle, off by default; the separate Queues panel was removed.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-07. Scope and sources
The hosted Jules application is governed by the vendor-authored Google Terms of Service linked from Jules. This does not assign that license to separate SDK/example code. The SDK and fleet packages are Apache-2.0, the MCP package is ISC and the GitHub Action is MIT. Public GitHub repositories exist for the Jules GitHub Action (MIT), Jules agent skills (Apache-2.0) and the jules-awesome-list prompt collection named as the @google/jules package repository. The jules-sdk repository returned 404 on 2026-11-22, but the published SDK, MCP and fleet npm packages ship readable code, and the SDK package's source map embeds its original TypeScript sources. The Jules Tools npm package only downloads a prebuilt binary, and the hosted Jules service and worker are closed.
Checked 2026-11-13 (9 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
The public repository is licensed Apache 2.0, and the website presents Podium as an open-source agent development environment. Hosted extensions and hosted-service terms are not established.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
The diff editor has download/copy controls for generated changes. REST changed-file outputs are Git patches. Jules runs only as a Google-hosted service in cloud VMs. A Google account, the Jules GitHub app and Google cloud VMs are required. Code, branches and PRs stay in GitHub; Jules configuration and history need a signed-in export before shutdown. The turndown export saves every session's prompt, plan, activity log and patches, but its script relies on undocumented endpoints.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Local desktop and self-hosted installs run on user-controlled machines with a documented state directory. The docs describe stopped full-state backup and automatic pre-migration database-only snapshots retaining three copies. Those snapshots omit artifacts, transcripts, uploads, configuration and secrets; no portable structured export/import contract was established.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-11. Scope and sources
Jules explicitly does not train models on private repository content. Integration API keys are stored encrypted and never shown in chat; the turndown export writes environment variable values in plaintext.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Docs state repositories and native harness credentials stay on machines you control and server state lives in a documented directory. Since 0.2.0 a daily usage report is on by default and can be turned off; crash reports stay opt-in. Usage reports carry an install id, schema version, Podium version, OS, architecture, bucketed install age and machine count, session counts per harness and whether issues were used. Crash reports carry the same install id, versions, OS and architecture, a fixed error type and up to 20 stack frames, each with a Podium source file path, line and function when there is one; error messages and frames outside Podium are dropped. Neither tier sends prompts, transcripts, your code or paths outside the Podium source tree. Model-provider handling is the harness own. Hosted analytics and website analytics are separate paths.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-21. Scope and sources
Price and included usage: Plans are per individual account; family plan members each get their own limits, and business users use an interest form. Paid quotas are accessed through Google AI Pro or Ultra; currency and regional subscription prices were not established here. Not established: currency, interval, seat minimum, workspace fees, credits, trial, overages, taxes, model cost, compute cost.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
No Podium price is published: podium.do/pricing returns 404 and the docs list billing as not implemented. The software is open source and free to download; model and compute costs are the user's own.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
No publishable sourced finding is available for this criterion. This does not mean the product lacks the capability.
Podium
Agent cross-checkedpartial
Podium is pre-1.0. Stable v0.3.1 (2026-11-06), an update fix, follows v0.3.0 (2026-11-05), v0.2.0 (2026-10-11) and v0.1.0 (2026-08-21), with edge and dev prerelease channels. Windows and Linux desktop are Experimental, the native iPhone app is in private beta and hosted Podium is unconfirmed. Support runs through GitHub issues, Discord and private vulnerability reporting.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources
Jules documents a recurring plan available without cost; service turndown restricts the remaining availability window. Free allows 15 tasks per rolling 24 hours and three concurrent tasks. Not paid-only: a no-cost plan was offered; since 2026-11-11 the service is read-only for everyone.
Checked 2026-11-07 (15 days old); agent cross-checked 2026-11-22. Scope and sources
Podium
Agent cross-checkedpartial
Podium is open-source Apache-2.0 software, and the download page calls it free and open source. Download links for macOS, Linux and Windows redirect to GitHub release assets without a login (observed by HTTP requests; not installed). No Podium charge is documented for self-hosting; agent provider usage is separate. The native iPhone app is private beta and hosted access is unconfirmed.
Checked 2026-11-06 (16 days old); agent cross-checked 2026-11-06. Scope and sources