AI-powered support draft bot for Pylon. Receives Pylon webhooks, generates draft replies using Claude (via Kilo Gateway), and posts them as internal notes on the Pylon issue for human review.

Rendering mermaid diagram...

Add these environment variables in the Val Town project settings:

1. Go to Pylon → Settings → API → Webhooks.
2. Create a new webhook destination with URL: https://YOUR-VAL-ENDPOINT.web.val.run/
3. Select the event types you want to trigger on (e.g., issue.message.created).
4. Save the secret — add it as PYLON_WEBHOOK_SECRET in Val Town.

Create a Pylon Trigger that fires on new customer messages and sends a webhook with the issue ID:

{
  "id": "{{issue.id}}"
}

The bot will fetch the full issue context (metadata and conversation history) from the Pylon API.

1. Webhook received at POST / — the handler verifies the Pylon HMAC-SHA256 signature.
2. Early return — responds 200 OK immediately, then fires a background request to POST /process.
3. Fetch context — retrieves full issue metadata and conversation history from Pylon API.
4. AI inference — loads prompt.md as the system prompt, sends the issue context to Claude Opus 4.6 via Kilo Gateway.
5. Internal note — posts the AI-generated draft as an internal-only note on the Pylon issue.
6. Error handling — on failure, sends an error notification email to steve@val.town.

Edit pipeline.ts to use a different model:

// Current: Claude Opus 4.6 via Kilo Gateway
const kilo = createOpenAI({
  baseURL: "https://api.kilo.ai/api/gateway",
  apiKey: Deno.env.get("KILO_GATEWAY_KEY"),
});

const { text: draftReply } = await generateText({
  model: kilo("anthropic/claude-opus-4-6"),
  system: systemPrompt,
  prompt: userPrompt,
});

// Example: Use a different model through Kilo Gateway
const { text: draftReply } = await generateText({
  model: kilo("openai/gpt-4-turbo"),
  system: systemPrompt,
  prompt: userPrompt,
});

Edit prompt.md to add:

• Product-specific knowledge
• FAQ pairs from your support history
• Links to your documentation
• Custom tone and style guidelines
• Troubleshooting trees for common issues

Run the test script to verify the pipeline end-to-end:

// Edit scripts/test-pipeline.ts with a real issue ID
const TEST_ISSUE_ID = "your-pylon-issue-id";

// Run the script from Val Town

The bot verifies Pylon webhook signatures using HMAC-SHA256:

1. Pylon sends X-Pylon-Signature header with hex-encoded digest
2. Bot computes HMAC-SHA256 of raw request body using PYLON_WEBHOOK_SECRET
3. Constant-time comparison prevents timing attacks
4. Invalid signatures return 401 Unauthorized

See Pylon webhook signature docs for more details.

• GET /issues/{id} — Fetch issue metadata
• GET /issues/{id}/messages — Fetch conversation messages (with pagination)
• POST /issues/{id}/threads — Create a new thread
• POST /issues/{id}/note — Post an internal note to a thread

See Pylon API Reference for more details.

This bot is deployed on Val Town, a serverless platform for TypeScript/JavaScript functions.

To deploy your own:

1. Fork this val or create a new val in your Val Town account
2. Add the required environment variables (see Setup section)
3. Configure the Pylon webhook destination to point to your val's endpoint
4. Test with a real issue using scripts/test-pipeline.ts