Skip to main content

Documentation Index

Fetch the complete documentation index at: https://developers.autoplay.ai/llms.txt

Use this file to discover all available pages before exploring further.

What this means in practice: an admin is reviewing vendors in a vendor-management app. One vendor is blocked because required compliance documents are missing. The admin tries to unblock the vendor from the vendor profile, but the action does not complete. Without context, the chat has to ask which vendor and what happened. With Autoplay wired in, Inkeep already knows the admin is on a blocked vendor profile and can explain the real blocker: compliance documents still need to be requested and completed. The admin opens chat and gets a specific answer: “This vendor is still blocked because the W-9 and insurance certificate are missing. Request those documents first, then the Unblock action will be available.” The bot can also point them to the exact document-request workflow instead of giving a generic vendor-status explanation. This tutorial shows you how to build that full flow using the Inkeep agents framework (open-source, self-hosted) and InkeepEmbeddedChat from @inkeep/agents-ui. Your events, conversation history, and LLM keys never leave your infrastructure. Who this is for:
  • You use or are evaluating Inkeep for in-product AI support.
  • You want the chat and in-app guidance to react to what admins actually do, not just answer generic questions.
  • You’re comfortable with Python, TypeScript/React, and running a small FastAPI service.
Tech you’ll use: Inkeep agents framework (Docker), @inkeep/agents-ui (InkeepEmbeddedChat), Next.js 14, Python 3.10+, FastAPI, uv, and any LLM provider (Anthropic or OpenAI).

​
✨ Final result

Admin: why can't I unblock this vendor?

Bot: Vendors may be blocked for several reasons, including policy
violations, expired approvals, or missing compliance information.
Check the vendor details page for more information.

(Generic reply — the bot doesn't know which vendor the admin is viewing
or that the unblock attempt just failed.)
Video walkthrough — Open on Loom if the player does not load.

​
📋 Prerequisites

Before you start, you need:
  • Node.js 18+ and Python 3.10+ on the host.
  • uv — the Python package manager used in this tutorial. 
    curl -LsSf https://astral.sh/uv/install.sh | sh
  • pnpm — the Inkeep agents monorepo uses pnpm workspaces. 
    npm i -g pnpm
  • Docker Desktop — for running Inkeep’s backing services (PostgreSQL, Doltgres, SpiceDB).
  • An Anthropic or OpenAI API key — the Inkeep agents framework calls your LLM directly; no Inkeep cloud key required.
That’s it. The tutorial covers every code file step by step — copy-paste runnable.
The Inkeep CDN widget (@inkeep/cxkit-js) requires a paid Inkeep cloud API key. This tutorial uses the open-source Inkeep agents framework (@inkeep/agents-ui) which you self-host with your own LLM key — no per-seat or per-call fee to Inkeep for the chat itself.

​
Architecture

┌─────────────────────────────────────────────────────┐
│  VendorOps  (Next.js, :3000)                        │
│                                                     │
│  ┌────────────────────────────────────────────────┐ │
│  │  Vendor profile                                │ │
│  │  Status: blocked                               │ │
│  │  Missing docs: W-9, certificate of insurance   │ │
│  └────────────────────────────────────────────────┘ │
│       │ sendVendorUnblockAttempt()                  │
│       │ POST /demo/actions                          │
│       ▼                                             │
│  ┌───────────────────────────────────────────────┐  │
│  │  Context fetch                                 │  │
│  │  GET /context/{session_id}                     │  │
│  └───────────────────────────────────────────────┘  │
│       │                                             │
│       ▼                                             │
│  ┌───────────────────────────────────────────────┐  │
│  │  InkeepEmbeddedChat                           │  │
│  │  → explains missing compliance documents      │  │
│  │  → points admin to request-documents flow     │  │
│  └───────────────────────────────────────────────┘  │
└─────────────────────────────────────────────────────┘
               │ POST /demo/actions
               │ GET  /context/{session_id}
               ▼
┌─────────────────────────────────────────────────────┐
│  Bridge  (FastAPI, :8787)                           │
│                                                     │
│  AsyncConnectorClient → AsyncContextStore           │
│    + AsyncSessionSummarizer (rolling 30-event window│
│      per session)                                   │
│                                                     │
│  Context: vendor_unblock_attempt + blocked status   │
│    + missing compliance documents                   │
│                                                     │
│  GET  /context/{session_id}  → assembled context   │
└─────────────────────────────────────────────────────┘
               │
               ▼
┌─────────────────────────────────────────────────────┐
│  Inkeep agents framework  (:3002)                   │
│  (self-hosted, your LLM key)                        │
│                                                     │
│  project: vendor-ops                                │
│  agent:   vendor-support                            │
│  sub-agent: compliance-support-worker               │
│                                                     │
│  InkeepEmbeddedChat ↔ AI sub-agent                  │
│  introMessage ← context from /context/{session_id} │
└─────────────────────────────────────────────────────┘
Two inputs feed the context layer: the vendor profile reports the admin’s action directly to the bridge (POST /demo/actions), and the bridge keeps the vendor’s blocked status plus missing compliance-document state available for chat grounding. The bridge owns all context logic; Inkeep stays a clean conversational surface. The GET /context/{session_id} endpoint assembles a human-readable summary of the admin’s recent activity and the vendor’s compliance state. When the admin opens chat, this summary becomes the introMessage passed to InkeepEmbeddedChat — so the AI’s first message references the blocked vendor and missing documents, not a generic greeting.

​
The tutorial

  1. Step 1 — Connect real-time events — Build the vendor-management frontend, wire unblock attempts and vendor context into a FastAPI bridge, run the Inkeep agents framework in Docker, and embed InkeepEmbeddedChat. At the end of this step you have a working AI chat widget on the vendor profile. ~45 minutes.
  2. Step 2 — Define proactive triggers — Add blocked-vendor detection to the bridge, wire the guidance channel to the frontend, and build the proactive handoff that opens Inkeep chat with the vendor’s missing compliance documents pre-loaded. ~45 minutes.