> ## 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.

# The proactive onboarding and adoption agent gold standard

> Step-by-step guide to building a proactive onboarding and adoption agent that knows what users are doing in real time — and helps before they have to ask.

🚫 **Most customer support AI agents are reactive.** No context. No memory. No idea what users actually need next.

✅ **A proactive onboarding agent is different.** It watches, learns, and acts — surfacing the right next step before users have to ask.

|     |                                  |
| --- | -------------------------------- |
| 📡  | Real-time event tracking         |
| 🧠  | LLM context assembly             |
| 💬  | Proactive chat + visual triggers |
| 🗂️ | User memory & workflow ontology  |

**This is the blueprint for going from a reactive support AI agent to a proactive onboarding and adoption agent.**

**Walkthrough** — same recipe in video form. [Open on YouTube](https://www.youtube.com/watch?v=N33U3nGNpaQ) if the player does not load.

<iframe className="doc-embed" src="https://www.youtube.com/embed/N33U3nGNpaQ" title="Proactive onboarding agent walkthrough" frameBorder={0} loading="lazy" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowFullScreen />

***

## The building blocks

Follow the steps in order — each page stands alone so you can ship incrementally.

1. **[Connect real-time actions](./step-1-connect-real-time-actions)** — Stream structured `ActionsPayload` events into your stack.
2. **[Add actions to LLM context](./step-2-add-actions-to-llm-context)** — Combine live actions, chat history, and optional KB into one inference-ready context.
3. **[Define proactive triggers](./step-3-define-proactive-triggers)** — Define when to interrupt, with Agent State v2 gating so proactive delivery stays non-intrusive and non-overlapping.
4. **[Connect relevant visual guidance](./step-4-enhance-with-user-memory)** — Route qualifying proactive outcomes into on-screen tours (chat vs tour vs silence) using your delivery channel.
5. **[Enrich with user memory](./step-5-enrich-with-user-memory)** — Define workflows so Atlas and memory expose **completion rates** and mastery; then filter with cross-session **user memory**.

### Implementation references

Use these SDK references as you wire the recipe into production:

* **[UserSessionIndex](../user-session-index)** — required for production user-keyed chat so `user_id` resolves to the correct recent sessions before Step 2 context assembly.
* **[compose\_chat\_pipeline(...)](../compose-chat-pipeline)** — compose safe default chat-ingestion wiring in Step 2.
* **[build\_copilot\_app(...)](../build-support-agent-app)** — stand up a minimal FastAPI bridge when you want an out-of-the-box serving layer.

You can build and ship real-time event ingestion today. Visual guidance wiring is covered in [Step 4](./step-4-enhance-with-user-memory). **Workflow ontology + user memory enrichment** (Chrome extension; docs with Autoplay via Slack) is part of [Step 5](./step-5-enrich-with-user-memory); expect an iterative loop on **Autoplay Atlas** labelling quality. The in-SDK [knowledge base query](../knowledge-base) and full user memory rollout are still rolling out.

***