> ## Documentation Index > Fetch the complete documentation index at: https://docs.agentsentinel.dev/llms.txt > Use this file to discover all available pages before exploring further. # Launch Path > The focused launch plan for Agent Sentinel. This is the active launch plan. It replaces the older scattered priority matrices, immediate action lists, fix summaries, and phase reports now kept in `docs/archive/`. ## Launch Objective Ship a credible beta for teams that need runtime control of AI agents: * instrument Python agents quickly; * enforce budgets, policies, guardrails, approvals, and kill switches; * sync telemetry to the platform; * operate from the console; * prove what happened through the ledger, exports, replay, and compliance metadata. ## Positioning Agent Sentinel is runtime authority for AI agents. Keep product language focused on shipped capabilities: * **Use**: runtime policy enforcement, intervention tracking, approvals, replay, ledger, cost controls, kill switch, and compliance/audit workflows. * **Avoid**: unqualified certification claims such as "SOC 2 certified" unless certification exists. * **Clarify**: cost tracking is based on SDK/integration estimates unless actual provider reconciliation has shipped. * **Label**: roadmap items as roadmap, not current product. ## Launch Pillars ### 1. SDK Adoption The SDK launch path is strongest when a developer can install, instrument, and see value in minutes. Required launch state: * clear installation and quickstart docs; * `@guarded_action` examples for sync and async functions; * policy, guardrail, approval, replay, and integration examples; * local ledger docs that explain exactly what is recorded; * remote sync docs with API key setup and shutdown/flush behavior. Canonical docs: * `/quickstart` * `/sdk/python/installation` * `/sdk/python/instrumentation` * `/sdk/python/policies` * `/sdk/python/guardrails` * `/sdk/python/replay` * `/sdk/python/framework-integrations` * `/sdk/python/llm-integrations` ### 2. Platform Reliability The platform must make SDK telemetry useful and trustworthy. Required launch state: * authenticated ingest with API keys; * tenant-scoped runs/actions/ledger APIs; * policy sync; * approval APIs and decision history; * intervention and replay APIs; * WebSocket updates for console workflows; * deployment and migration notes for the chosen production path. Canonical docs: * `/platform/overview` * `/platform/ingest` * `/platform/auth` * `/platform/runs` * `/platform/policies` * `/platform/approvals` * `/platform/interventions` * `/platform/replay` * `/platform/websockets` * `/platform/self-hosting` ### 3. Console Operations The console should support the operator workflows that make runtime control credible. Required launch state: * quickstart/onboarding path; * runs explorer; * intervention review; * approval inbox; * policy management; * kill switch; * replay hub and determinism analysis; * agent overview; * ledger export and audit workflows; * analytics sufficient to show cost and operational signals. Canonical docs: * `/console/overview` * `/console/quickstart` * `/console/runs` * `/console/interventions` * `/console/approvals` * `/console/kill-switch` * `/console/replay` * `/console/ledger` * `/console/agents` * `/console/analytics` * `/console/settings` ## Critical Launch Work Track active delivery here instead of creating new root-level plan docs. Every row has a named owner and an evidence link. A claim with no evidence link is not a claim we make publicly. | Area | Outcome | Owner | Status | Evidence | | ---------------------- | --------------------------------------------------------------------- | ------------ | ---------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | Claims accuracy | Public docs and marketing match shipped behavior | @jimmystacks | Active maintenance | This table + [readiness run 2026-07-27](#launch-readiness-checklist) | | SDK quickstart | Install, instrument, local ledger, remote sync path is clear | @jimmystacks | **Verified 2026-07-27** | Clean-venv run: install → `@guarded_action` → `.agent-sentinel/ledger.jsonl` written | | Replay | Replay docs and examples explain cost-free debugging and determinism | @jimmystacks | **Verified 2026-07-27** | Record + replay: 0 real calls, output matched, 0 divergences, \$0.50 avoided | | Approvals | Console approval flow and API behavior are documented | @jimmystacks | **Verified 2026-07-27** | `pending → approved`, `decided_by_id` populated, pending drains to 0 | | Notifications | Slack/email approval notification path | @jimmystacks | **Shipped, needs an end-to-end test** | `routes/slack_webhook.py`, `models/notification_channel.py`, referenced from `routes/approvals.py:124` | | Compliance exports | Ledger/compliance export path is documented and testable | @jimmystacks | **Ledger export verified; compliance export still a stub** | Ledger: `GET /ledger/export?start_date&end_date` returns JSONL. Stub: `routes/compliance.py:370` returns `download_url=None` | | Framework integrations | LangChain, CrewAI, AutoGen, LangGraph claims map to code and examples | @jimmystacks | Validate before each release | `agent_sentinel/integrations/` — langchain, crewai, autogen, langgraph all present | | Production deployment | Deployment checklist reflects current hosting choice | @jimmystacks | **Migration chain fixed 2026-07-27** | `alembic upgrade head` on an empty DB failed until `ev1d3nc3gr4ph` gained `depends_on`; now applies all 36 revisions, 26 tables | | Kill switch | Blocks the intended scope and is auditable | @jimmystacks | **Verified 2026-07-27** | SDK raises `AgentKilledError`; `/kill-switch/active` records `killed_by` + `killed_at` | | Policy enforcement | A denied action is blocked and recorded as an intervention | @jimmystacks | **Verified 2026-07-27** | `PolicyViolationError` raised; intervention `hard_block` with `reason_code: DENIED_ACTION` synced to platform | | Test CI | Every commit runs the SDK, platform and console suites | @jimmystacks | **Landed 2026-07-27** | `.github/workflows/test.yml` — SDK + gym + console blocking; platform reporting-only until the two gaps below are closed; a `migrations` job asserts `alembic upgrade head` on an empty DB | ## Launch Readiness Checklist Last run **2026-07-27** against local infrastructure: Postgres 18.1 + Redis in Docker, migrations applied, API on `:8848`, SDK installed into a clean venv from a local build. **8 pass, 1 partial, 1 was failing and is now closed.** | # | Item | Result | | -- | --------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | | 1 | SDK quickstart succeeds from a clean virtual environment | ✅ | | 2 | Remote sync works against staging or production with a new API key | ✅ 3 ledger entries, 1 run, 1 intervention synced | | 3 | Console onboarding produces at least one visible run | ✅ closed 2026-07-27 — offline auth implemented (PR #18); signed-in console verified in **production** against 71 real runs | | 4 | Policy enforcement blocks a denied action and records an intervention | ✅ | | 5 | Approval workflow can be requested, decided, and reflected | ✅ | | 6 | Kill switch blocks the intended scope and is auditable | ✅ | | 7 | Replay example runs locally and displays a replay summary | ✅ after fixing a `str` ledger path | | 8 | Ledger export works for a bounded date range | ✅ | | 9 | Documentation has no top-level stale phase reports or duplicate architecture docs | ✅ | | 10 | Public claims have an owner and evidence link | ✅ closed 2026-07-27 — see the Owner and Evidence columns above | ### Known gaps, owned **Resolved 2026-07-27:** email templates now built; gym budget test fixed; root `uv run pytest` collision fixed; platform coverage gate set to a real ratchet. The platform and gym CI jobs are blocking as a result. * ~~**Console lint backlog — 115 errors**~~ — resolved 2026-07-27 (PR #18). 115 errors and 74 warnings are now zero, with **no `eslint-disable` suppressions**: the four `set-state-in-effect` sites were fixed by moving design/theme/quick-start from a localStorage mount effect to server-resolved cookies. The console lint job is blocking, and a `tsc --noEmit` gate was added alongside it — typing `useApi`'s wrapper (previously `as any`) surfaced 20 real mismatches, including compliance signing metadata the console could never render and a crash on a missing `intervention_type`. * **Marketing site collects no analytics.** `agentsentinel.dev` throws three console errors, all telemetry: `/_vercel/insights/script.js` 404 (Vercel Web Analytics referenced but not enabled for the project), `events.agentsentinel.dev/.../sw_iframe.html` 503, and the GA4 `collect` call blocked by CORS — no `Access-Control-Allow-Origin` on `events.agentsentinel.dev`. Found 2026-07-27 while browser-testing the production deploy; predates PR #18, which did not touch `apps/web`. Net effect is zero analytics on the public site, so any traffic claim is currently unevidenced. Owner: @jimmystacks. * **Railway environment is named `staging` but serves production.** The GitHub deployment environment for the platform is `agent-sentinel / staging`, and it is what backs `api.agentsentinel.dev`. Nothing is broken, but the label will eventually cause someone to deploy believing production is untouched. Rename when convenient. Owner: @jimmystacks. * **Platform coverage is 58%.** `--cov-fail-under` is set to 55 — a ratchet at the measured baseline, not an aspiration. The previous 80 was never met, so the gate never ran green and was effectively off. Raise the number as coverage improves. Owner: @jimmystacks. * ~~**Console onboarding (checklist item 3) — offline auth bypass**~~ — resolved 2026-07-27 (PR #18). The five `NEXT_PUBLIC_OFFLINE_*` / `CLERK_DISABLED` vars really were referenced zero times in the console, but the *platform* half had existed all along in `app/core/clerk_dev.py`. The console half is now implemented: `lib/offline-auth.ts` gates it (explicit flag **and** a non-production deploy; a flag reaching production is ignored and reported), `components/auth.tsx` is the single decision point, and `scripts/mint_dev_token.py` regenerates the token — the hardcoded one had expired on 2026-07-06 with no `email` claim, which is why the path silently did nothing. It is a token swap, not a bypass: no token 401, dev token 200, tampered token 401\. `get_current_user_ws` gained the same dev-token branch, without which offline WebSocket handshakes 403'd and real-time updates never arrived. Verified 2026-07-27 in **production**, signed in: all 15 routes 200 with zero console errors and zero hydration warnings, real data loading (71 runs, 100 ledger rows, 25 agents), tab deep-links, `?run=` legacy aliases, and sidebar navigation. Protected routes still refuse an unauthenticated visitor. * ~~**First-run log noise**~~ — resolved 2026-07-27. `mcp.py` logged `httpx not installed` via `logging.warning` on the **root** logger at import, so a bare `pip install` printed `WARNING:root:` before the user did anything; now a module-logger debug, matching `approval.py`. The fail-open warning is kept — for a safety product, "nothing is being enforced" warrants one, and it fires once per process — but the quickstart now explains it instead of being surprised by it. ### Rule A row in the table above may not move to a "Verified" status without an evidence link naming what was run and what was observed. Re-run this checklist before each release. ## Historical Sources The launch plan condenses these archived inputs: * `docs/archive/legacy-plans/EXECUTIVE_SUMMARY.md` * `docs/archive/legacy-plans/CODEBASE_REVIEW_AND_ROADMAP.md` * `docs/archive/legacy-plans/IMPLEMENTATION_PRIORITY_MATRIX.md` * `docs/archive/legacy-plans/IMMEDIATE_ACTIONS.md` * `docs/archive/legacy-plans/HONEST_CLAIMS_AUDIT.md` * `docs/archive/legacy-plans/PHASE_7_SUMMARY.md`