Step 1 — Connect real-time events

https://[YOUR_SERVER_URL]/context?secret=[YOUR_WEBHOOK_SECRET]

You are a friendly and helpful assistant for users of this product.

Focus on helping people find their way in the UI, complete workflows, and
understand features. Assume some users are seeing the product for the first time.

## 💬 How to use the "Current User Activity" record

You may receive a special record titled "Current User Activity" in the
retrieved context. This shows what THIS user has been doing on the
platform in the last 2 minutes — which page they are on and what they
clicked. The activity is scoped to their session, so it reflects only
their actions, not anyone else's.

 @context 

When this record is present:

1. **Acknowledge their activity naturally** — for example:
   "I can see you're currently on the Projects page" or
   "It looks like you've been exploring the Dashboard."

2. **Use it to give specific directions** — instead of generic
   instructions, reference where they are:
   "From the page you're on, click the blue 'Add Project' button
   at the top right."

3. **Detect if they might be lost** — if their actions show them
   clicking around without a clear pattern, gently offer help:
   "It looks like you might be looking for something specific.
   Can I help you find it?"

4. **Don't force it** — if the user's question has nothing to do
   with their current activity, just answer the question normally.
   Don't mention their activity unless it's helpful.

## ❓ How to answer questions

- **Be specific**: reference actual button names, tab labels, and
  menu items from the knowledge base.
- **Use numbered steps**: when explaining how to do something,
  always use a numbered list.
- **Keep it simple**: avoid technical jargon. Explain as if the
  user has never used the platform before.
- **Be encouraging**: use phrases like "Great question!" or
  "That's easy to do" to make users feel comfortable.
- **Offer next steps**: after answering, suggest what they might
  want to do next.
- **Admit when you don't know**: if the knowledge base doesn't
  have the answer, say so honestly.

## 🌐 Language

Respond in the same language the user writes in.

## ✅ Examples of good responses

User is on the Dashboard, asks "How do I create a project?":
  "I can see you're currently on the Dashboard. To create a new
   project:
   1. Click on 'My Projects' in the left sidebar
   2. Click the 'Add Project' button at the top right
   3. Choose the type, template, or options that match what you're creating
   4. Fill in the required details and click 'Create'
   Would you like me to explain what each field means?"

User is on the Invoice page, asks "Where are settings?":
  "The settings aren't on this page — you can find them by clicking
   on your profile icon in the top right corner, then selecting
   'Settings' from the dropdown menu."

User has no activity context, asks "What can I do here?":
  "Welcome! Here's what you can do:
   1. Dashboard — see an overview of your work
   2. My Projects — create and manage projects
   3. Reports — view analytics or exports
   4. Billing — manage invoices or account settings
   What would you like to explore first?"

pip install fastapi httpx openai uvicorn autoplay-sdk

|- .env          # store your env var secrets
|- listener.py   # the Autoplay SDK event listener
|- server.py     # server that responds to Landbot webhook requests

EVENTS_FILE_PATH="event_data.txt"

AUTOPLAY_STREAM_URL="YOUR_AUTOPLAY_STREAM_URL"
AUTOPLAY_UNKEY_API_KEY="YOUR_AUTOPLAY_UNKEY_API_KEY"

WEBHOOK_SECRET="YOUR_WEBHOOK_SECRET"

import os
from fastapi import FastAPI, Header, Query, HTTPException
from dotenv import load_dotenv

load_dotenv()

app = FastAPI()

EVENTS_FILE = os.getenv("EVENTS_FILE_PATH", "events.txt")
API_SECRET = os.getenv("WEBHOOK_SECRET", "")
PORT = int(os.getenv("PORT", 5000))


def read_events() -> str:
    if not os.path.exists(EVENTS_FILE):
        return "No events recorded yet."
    with open(EVENTS_FILE, "r", encoding="utf-8") as f:
        content = f.read().strip()
    return content or "No events recorded yet."


def trim_events(content: str, max_lines: int = 100) -> str:
    lines = content.splitlines()
    return "\n".join(lines[-max_lines:])


@app.post("/context")
def generate_event_context(
    secret: str | None = Query(default=None),
    x_secret_key: str | None = Header(default=None),
):
    token = x_secret_key or secret
    if API_SECRET and token != API_SECRET:
        raise HTTPException(status_code=401, detail="Unauthorized")

    raw = read_events()
    context = trim_events(raw, max_lines=100)
    return {
        "context": context,
        "line_count": len(context.splitlines()),
    }


@app.get("/health")
def health():
    return {"status": "ok"}


if __name__ == "__main__":
    import uvicorn

    print(f"Starting context server on port {PORT}...")
    uvicorn.run("server:app", host="0.0.0.0", port=PORT)

import asyncio
import os
import time

import dotenv
import openai
from autoplay_sdk import (
    ActionsPayload,
    AsyncAgentContextWriter,
    AsyncConnectorClient,
    AsyncSessionSummarizer,
)

dotenv.load_dotenv()

STREAM_URL = os.getenv("AUTOPLAY_STREAM_URL")
UNKEY_API_KEY = os.getenv("AUTOPLAY_UNKEY_API_KEY")
EVENTS_FILE_PATH = os.getenv("EVENTS_FILE_PATH")

async_openai = openai.AsyncOpenAI()


def api_call(func):
    async def wrapper(*args, **kwargs):
        try:
            return await func(*args, **kwargs)
        except Exception as e:
            print(f"Error in API call: {e}")

    return wrapper


@api_call
async def llm(prompt: str) -> str:
    r = await async_openai.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}],
        temperature=0.3,
        max_tokens=256,
    )
    return r.choices[0].message.content


@api_call
async def write_actions_to_file(payload: ActionsPayload):
    print("\n=== WRITING ACTIONS TO FILE ===")
    # Reset file if last modified more than 2 minutes ago (new session)
    if os.path.exists(EVENTS_FILE_PATH):
        last_modified_time = os.path.getmtime(EVENTS_FILE_PATH)
        if time.time() - last_modified_time > 2 * 60:
            open(EVENTS_FILE_PATH, "w").close()
    with open(EVENTS_FILE_PATH, "a") as f:
        for i, action in enumerate(payload.actions):
            f.write(f"[{i}] Action: {action.title}\n")
            f.write(f"     Details: {action.description}\n")
            f.write(f"     Page:    {action.canonical_url}\n")


# Raw actions are written directly to file; tell the writer to do nothing for actions
async def dummy_write_actions(session_id: str, text: str) -> None:
    pass


@api_call
async def overwrite_summary(session_id: str, summary: str) -> None:
    print("\n=== OVERWRITING SUMMARY ===")
    with open(EVENTS_FILE_PATH, "a") as f:
        f.write(f"\n=== SUMMARY ===\n{summary}\n")


summarizer = AsyncSessionSummarizer(llm=llm, threshold=5)

agent_writer = AsyncAgentContextWriter(
    summarizer=summarizer,
    write_actions=dummy_write_actions,
    overwrite_with_summary=overwrite_summary,
    debounce_ms=0,
)


async def handle_actions_interceptor(payload: ActionsPayload):
    await write_actions_to_file(payload)
    await agent_writer.add(payload)


async def main():
    async with AsyncConnectorClient(url=STREAM_URL, token=UNKEY_API_KEY) as client:
        client.on_actions(handle_actions_interceptor)
        print("Listening for live website clicks... (Press Ctrl+C to stop)")
        await client.run()


if __name__ == "__main__":
    asyncio.run(main())

uvicorn server:app --reload --port 5000

ngrok http 5000

python listener.py

<!-- Landbot widget — paste inside <body>, copied from your Share panel -->
<script SameSite="None; Secure" type="module"
  src="https://cdn.landbot.io/landbot-3/landbot-3.0.0.mjs">
</script>
<script type="module">
  var myLandbot = new Landbot.Livechat({
    configUrl: 'https://chats.landbot.io/v3/YOUR_BOT_ID/index.json',
  });
</script>