# Autonomous learning from resolved tickets

> When learning is enabled, Atlas extracts Q&A from eligible resolved tickets, auto-approves high-confidence answers, and queues uncertain ones for staff review.

## How learning works

With learning enabled, Atlas watches for **eligible resolved tickets** - conversations that reached a clear answer. From each one it extracts a question-and-answer pair that could help the next member with the same problem.

## Auto-approval and the confidence score

Every extracted pair gets a confidence score. Pairs above your **auto-approve threshold** become searchable knowledge immediately; everything below it lands in a review queue for your staff instead. You control the threshold, so you decide how much autonomy Atlas gets.

- **High confidence** - approved automatically and marked as auto-approved, so you can always tell them apart from hand-approved entries.
- **Uncertain** - held as pending until a staff member approves, edits, or rejects it. Nothing uncertain becomes an answer on its own.

## Where learned answers live

Approved pairs join your knowledge base alongside the sources you added yourself, and Atlas cites them like any other material. See [knowledge-base sources](https://ticketcord.net/help/ai/knowledge-base) for how the rest of the base is managed.

## Plans and quiet mode

Learning that answers members runs on plans with AI access. On the free plan, TicketCord quietly measures what Atlas *could* have learned from your resolved tickets and shows you the opportunity in the dashboard - nothing is answered on your behalf until you upgrade and enable it.

To manage what has been learned, see [reviewing learned Q&A from Discord](https://ticketcord.net/help/workflows/learning-review).

## Machine-readable resources

- [Canonical HTML](https://ticketcord.net/help/ai/autonomous-learning)
- [TicketCord llms.txt](https://ticketcord.net/llms.txt)
- [AI page index](https://ticketcord.net/api/ai/pages)