pref0

# pref0 — Preference Learning for AI Agents

You have access to the pref0 API. It learns user preferences from conversations and serves them back at inference time. The more conversations you track, the better it gets.

## When to use this skill

### After a conversation ends → Track it

After finishing a conversation (or at natural breakpoints), send the messages to pref0 so it can extract preferences. This is especially valuable when the user **corrects** you (e.g., "use pnpm, not npm") or states explicit preferences (e.g., "always use metric units").

### Before responding to a user → Fetch their preferences

Before generating a response, fetch the user's learned preferences and follow them. This prevents the user from having to repeat themselves across sessions.

## API Reference

**Base URL:** `https://api.pref0.com`
**Auth:** `Authorization: Bearer $PREF0_API_KEY`

### Track a conversation (POST /v1/track)

Send a conversation so pref0 can learn from it. It extracts corrections, explicit preferences, and behavioral patterns automatically.

```bash
curl -X POST https://api.pref0.com/v1/track \
  -H "Authorization: Bearer $PREF0_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "userId": "<user-id>",
    "messages": [
      { "role": "user", "content": "Help me set up a new project" },
      { "role": "assistant", "content": "Here is a project using npm and JavaScript..." },
      { "role": "user", "content": "Use pnpm, not npm. And TypeScript." },
      { "role": "assistant", "content": "Updated to pnpm and TypeScript..." }
    ]
  }'
```

**Response:**
```json
{
  "messagesAnalyzed": 4,
  "preferences": { "created": 2, "reinforced": 0, "decreased": 0, "removed": 0 },
  "patterns": { "created": 1, "reinforced": 0 }
}
```

The response tells you how many messages were processed (`messagesAnalyzed`) and exactly what changed: `created` (new preference learned), `reinforced` (existing preference seen again, confidence increased), `decreased` (user retr...