# Guide URL: https://docs.hanzo.ai/docs/openapi/guide > The AI that builds an agentic company with you, one measured step at a time. Also for this capability: **API** · [CLI](https://docs.hanzo.ai/docs/cli/guide) · [MCP](https://docs.hanzo.ai/docs/mcp-tools/guide) · [SDKs](https://docs.hanzo.ai/docs/sdks) The AI that builds an agentic company with you, one measured step at a time. > [All API references →](https://docs.hanzo.ai/docs/openapi) · [Get started →](https://docs.hanzo.ai/docs/guides) | | | | -------------- | -------------------------------------- | | **Base URL** | `https://api.hanzo.ai` | | **Operations** | 15 | | **Auth** | `Authorization: Bearer $HANZO_API_KEY` | ## Specification > **HIP-1130 · Guide — The Launch Journey** — Draft · [read the specification →](https://github.com/hanzoai/hips/blob/7ed737180339cd05b5f2935eafe7f7b83d2449a2/HIPs/hip-1130-guide-launch-journey.md) `/v1/guide` is the Business AI Guide: an interactive launch checklist every org completes on-site — a checklist engine over a machine-readable curriculum, a Business AI agent that can execute a step through the caller's own tool plane, and a versioned brand blueprint the whole journey is projected from. It is implemented in `hanzoai/cloud` at `apps/guide` (HIP-0106). ### Motivation Onboarding advice that lives in prose goes stale and cannot be acted on. A journey that is data — steps with dependencies, done-criteria mapped to real signals, tools bound to steps — can be auto-marked when the org has demonstrably done the work, and executed by an agent when the org asks. The three concerns are kept orthogonal on purpose: the engine is pure functions over plain data, the agent acts only through the caller's own authority, and the blueprint is content a SuperAdmin authors live (`apps/guide/curriculum.go:6-31`). ### Specification The key words MUST, MUST NOT, SHOULD, SHOULD NOT and MAY are to be interpreted as in RFC 2119. #### §1 Two stores, two tiers Per-org progress and the org's own curriculum override live in that org's own database, opened through `cloud.OrgStore` — one file per org, resolved through the one namespace door (`apps/guide/guide.go:47-63`). The shared brand blueprint is a second, deployment-wide store (`apps/guide/blueprint_store.go:45`), seeded idempotently from embedded fixtures — the base journey plus one YAML file per brand (`apps/guide/brands.go`) — after which the database is authoritative and the fixture is only the fail-safe fallback. A redeploy MUST NOT clobber a live edit; seeding is if-absent (`apps/guide/guide.go:78-88`). #### §2 The address Nineteen operations under `/v1/guide`. All are typed except six, each declared with prose beside its route (`apps/guide/guide.go:262-360`) because its body has no declarable shape: the curriculum and blueprint writes accept YAML **or** JSON as a raw body (the canonical parsed form is what is stored); the blueprint PATCH is a shallow merge whose keys are the patched item's, not the route's; and `steps/{id}/do` answers either JSON or a Server-Sent-Event stream of the agent's actions. Every declared description renders only while the router serves the route, so the prose can never invent a path. A step transition is dependency-gated: a blocked start or done is 409 carrying `blockedBy` naming the exact steps in the way. A write that does not parse or does not validate (unique ids, acyclic dependencies) is 422 and the journey in force is untouched. #### §3 Tenancy, and the gate that differs by tier The tenant is `principal.Org` — the org minted from the validated bearer (HIP-0026), never a header (`apps/guide/guide.go:382-385`). The per-org curriculum override is any validated member's surface. The brand blueprint is platform content: authoring it requires SuperAdmin (`apps/guide/admin.go:39`), a per-org admin is 403, and every write is audited and versioned with the prior versions kept as a recovery trail. #### §4 Money Guide is free (`cloud.Free`, `plugin/guide/main.go`). The one executing path — "do it for me" — runs the step's tool through the calling principal's own MCP plane (`automations.InvokeTool`), so the work is metered and audited by the plane that owns it, against the caller's ledger (`apps/guide/agent.go:61`). Guide itself debits nothing and MUST NOT acquire an authority the caller does not hold. #### §5 Events and observability It publishes nothing on the bus. It emits nothing beyond the request span every route gets; the audit trail for blueprint authoring is the shared audit plane, not a telemetry stream. #### §6 Stage `beta`: a vertical application — a guided launch product over the core planes, not one of them. #### §7 Upstream It derives from none. The curriculum fixtures are embedded YAML authored here; the growth signals are injected read seams bound at the composition root, so guide imports none of the subsystems it observes (`apps/guide/signals.go`). ### Rationale The alternative to a data blueprint is a hard-coded journey, which makes every white-label brand and every content edit a code change. The alternative to executing through the caller's own tool plane is a service identity that acts for orgs — which is an escalation surface, and the reason the agent runs AS the caller instead. ### Security Considerations The two tiers are the exposure. If the per-org gate could reach the shared blueprint, one tenant would edit every org's journey — including which MCP tools the Business AI runs for a step, which is a lever over agents in every org; the SuperAdmin gate and the audit trail on that tier exist for exactly this. On the executing path, the wrong implementation runs tools under an authority wider than the caller's; here the invocation is per-principal, so a step can never do what its asker could not. ## Four surfaces | Surface | Reaches this capability as | Coverage | | -------- | --------------------------------------------- | -------------------------------------------------------------------------- | | **REST** | `guide` at its own prefix | 15 operations | | **CLI** | `hanzo guide …` | 15 of 15 | | **SDK** | `GuideApi` in every published client | 15 methods | | **MCP** | tool `guide` on `https://api.hanzo.ai/v1/mcp` | 13 operations, 4 under the document's own id — ask `describe` for the rest | ## Quickstart ```bash export HANZO_API_KEY=sk-... # console.hanzo.ai → API keys ``` Then the first call — a read that needs nothing but the key. `GET /v1/guide`, operation `get_guide`: **CLI** ```bash hanzo guide get ``` **SDK** **.ts** ```ts import { Configuration, GuideApi } from 'hanzoai'; const api = new GuideApi(new Configuration({ accessToken: process.env.HANZO_API_KEY })); const { data } = await api.getGuide(); ``` **.py** ```python from hanzoai.cloud import ApiClient, Configuration from hanzoai.cloud.api import GuideApi client = ApiClient(Configuration(access_token=os.environ["HANZO_API_KEY"])) result = GuideApi(client).get_guide() ``` **.go** ```go cfg := hanzoai.NewConfiguration() cfg.AddDefaultHeader("Authorization", "Bearer "+os.Getenv("HANZO_API_KEY")) client := hanzoai.NewAPIClient(cfg) resp, _, err := client.GuideAPI.GetGuide(context.Background()).Execute() if err != nil { return err } ``` **.rs** ```rust use hanzo_client::apis::{configuration::Configuration, guide_api}; let mut cfg = Configuration::new(); cfg.bearer_access_token = std::env::var("HANZO_API_KEY").ok(); let result = guide_api::get_guide(&cfg, Default::default()).await?; ``` **.java** ```java import ai.hanzo.cloud.ApiClient; import ai.hanzo.cloud.api.GuideApi; ApiClient client = new ApiClient(); client.setBearerToken(System.getenv("HANZO_API_KEY")); var result = new GuideApi(client).getGuide(); ``` **HTTP** ```bash curl https://api.hanzo.ai/v1/guide \ -H "Authorization: Bearer $HANZO_API_KEY" ``` **MCP** MCP reaches **guide** through the `guide` tool, which names its 13 operations with its own verbs — this one among them, under a name only MCP declares. `describe` explains any of them: ```bash curl -X POST https://api.hanzo.ai/v1/mcp \ -H "Content-Type: application/json" \ -d '{ "jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": { "name": "describe", "arguments": { "op": "list_guides" } } }' ``` Answers `200` with `object` — ok. ## Endpoints | Endpoint | What it does | | ---------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [`GET /v1/guide/actions`](https://docs.hanzo.ai/docs/openapi/guide/get-guide-actions) | Returns the caller org's Business AI action ledger, most recent first: every "do it for me" tool call, the arguments it ran with, its result and whether it succeeded. | | [`GET /v1/guide/analytics`](https://docs.hanzo.ai/docs/openapi/guide/get-guide-analytics) | Returns the caller org's funnel from the analytics lens plus the GTM recommendations derived from it. | | [`POST /v1/guide/chat`](https://docs.hanzo.ai/docs/openapi/guide/post-guide-chat) | Answers a founder's question about their launch journey as the Business AI coach: it grounds the reply in the org's REAL progress, its ranked available quests and its analytics funnel, and returns those candidate quests alongside so the caller can act on one. | | [`GET /v1/guide/curriculum`](https://docs.hanzo.ai/docs/openapi/guide/get-guide-curriculum) | Returns the journey the caller's org is actually running, and whether it comes from the org's OWN override (custom) or from the platform default — the brand blueprint, else the embedded fixture. | | [`PUT /v1/guide/curriculum`](https://docs.hanzo.ai/docs/openapi/guide/put-guide-curriculum) | Replace your org's journey with a curriculum you author | | [`DELETE /v1/guide/curriculum`](https://docs.hanzo.ai/docs/openapi/guide/delete-guide-curriculum) | Clears the caller org's curriculum override and returns the journey it falls back to — the brand blueprint, else the embedded fixture. | | [`GET /v1/guide/profile`](https://docs.hanzo.ai/docs/openapi/guide/get-guide-profile) | Returns the caller org's OBSERVED growth profile — the signal set, the classified growth stage, and the org's own key metrics. | | [`POST /v1/guide/steps/{id}/do`](https://docs.hanzo.ai/docs/openapi/guide/post-guide-steps-by-id-do) | Have the Business AI actually do the step for you | | [`POST /v1/guide/steps/{id}/done`](https://docs.hanzo.ai/docs/openapi/guide/post-guide-steps-by-id-done) | Marks one step of the caller org's journey complete and returns the refreshed journey. | | [`POST /v1/guide/steps/{id}/reset`](https://docs.hanzo.ai/docs/openapi/guide/post-guide-steps-by-id-reset) | Returns one step of the caller org's journey to todo — clearing a manual mark or a skip — and returns the refreshed journey. | | [`POST /v1/guide/steps/{id}/skip`](https://docs.hanzo.ai/docs/openapi/guide/post-guide-steps-by-id-skip) | Marks one step of the caller org's journey skipped and returns the refreshed journey. | | [`POST /v1/guide/steps/{id}/start`](https://docs.hanzo.ai/docs/openapi/guide/post-guide-steps-by-id-start) | Marks one step of the caller org's journey in progress and returns the refreshed journey. | | [`GET /v1/guide/strategies`](https://docs.hanzo.ai/docs/openapi/guide/get-guide-strategies) | Returns the ENABLED tactics corpus for the caller's org: the tactics library narrowed by the explicit category/workload filters AND by the org's OBSERVED growth stage and capability signals (a tactic's tags are preconditions, so it surfaces only once the org can act on it). | | [`GET /v1/guide/suggest`](https://docs.hanzo.ai/docs/openapi/guide/get-guide-suggest) | Returns the caller org's next-best quests: the available, non-terminal steps of its journey ranked by how much downstream work each unblocks, each with the grounded reason it is a good next move and whether the Business AI can run it, plus the org's funnel and the GTM recommendations derived from it. | | [`GET /v1/guide`](https://docs.hanzo.ai/docs/openapi/guide/get-guide) | Returns the caller org's launch journey: the active curriculum's version and title, every step with its state, whether it is available, what blocks it and whether the Business AI can run it, the done/total/percent progress with the next step to take, and the org's analytics funnel folded in. | --- [All Hanzo APIs](https://docs.hanzo.ai/docs/openapi) · [Interactive reference](https://docs.hanzo.ai/docs/openapi/reference)