Skip to content

Part 7 · Integration Blueprints

The first six parts are a reference. This part is a cookbook — seven end-to-end blueprints that weave sandbox, permission, event, and skill into real customer scenarios.

Each blueprint answers the same four questions:

  1. Who & why — what kind of product / what pain
  2. Architecture — where Agentao sits, what it talks to
  3. Key code — the 50–150 lines that matter
  4. Pitfalls — what tends to break on day two

Key terms in this Part

  • In-product assistant — chat / agent embedded inside an existing SaaS UI; the most common shape · §7.1, G.4
  • IDE plugin (ACP) — host = editor, agent = subprocess speaking ACP; uses session/load + request_permission · §7.2, G.3
  • Ticket automation — async handler reading from a queue; prompt_once style, no streaming UI · §7.3, G.4
  • Data workbench — interactive analyst session with shell + sandbox + skills · §7.4
  • Batch scheduler — cron-driven prompt_once for offline / nightly jobs; no end-user · §7.5, G.4
  • WeChat intelligent bot (ilink-style) — long-polling personal-account bot API; one agent per message; contact-scoped permissions · §7.6
  • Multi-agent kanban scheduling — external derivative project (agentao-kanban); board-driven scheduler over planner / worker / reviewer sub-agents; per-card git worktree · §7.7

The seven blueprints

#BlueprintIntegration modeStar extensions
7.1SaaS in-product assistantIn-process SDK + FastAPICustom tool + PermissionEngine
7.2IDE / editor pluginACP stdiosession/load + request_permission
7.3Customer-support / ticket automationIn-process SDKCustom tools hitting CRM
7.4Data analyst workbenchIn-process SDKShell + sandbox + custom skill
7.5Offline batch / scheduled jobsprompt_onceSkills + cron
7.6WeChat intelligent bot (ilink-style)asyncio long-poll daemonWeChatClient Protocol + contact-scoped permissions
7.7Multi-agent kanban scheduling (external repo)External orchestrator over agentao sub-agents + ACP CLIsplanner/worker/reviewer routing + per-card git worktree

How to read this part

  • If you already picked your scenario, jump straight to that section.
  • If you're undecided, 7.1 covers the most common case (in-product assistant) — the other five are specializations.
  • Every blueprint links back to the relevant reference sections so you can drill down when needed.

Choose by product shape

Product you are buildingStart withWhy
Chat assistant inside a SaaS page7.1Covers the main path: web UI, FastAPI, tools, and permissions
IDE, editor, or desktop host7.2ACP, stdio, permission requests, and session loading are the key differences
Queue-driven background automation7.3Focuses on idempotency, retries, CRM tools, and unattended policy
Analyst workbench or notebook-like product7.4Focuses on shell, sandboxing, file isolation, and analysis skills
Nightly jobs, reporting, or offline processing7.5Focuses on prompt_once, scheduling, budgets, and failure handling
IM / WeChat / enterprise messaging bot7.6Focuses on long polling, contact-scoped permissions, and per-message isolation
Multi-agent system over a queue of work (CI, eval, autonomous research)7.7Focuses on external orchestrators, role routing across sub-agents and ACP CLIs, per-task isolation

Runnable code

Blueprints 7.1–7.6 ship as self-contained projects inside the main repo at examples/ — each subdirectory (saas-assistant/, ide-plugin-ts/, ticket-automation/, data-workbench/, batch-scheduler/, wechat-bot/) is a standalone uv run / npm run project. Every blueprint page below links to its matching subdirectory.

Blueprint 7.7 lives in a separate repository — jin-bo/agentao-kanban — because it's a derivative project with its own release cadence, not an in-tree example.

Start with 7.1 SaaS Assistant →