# Content library

**Summary:** Structured knowledge automatically organized from your Sources, ready for the Customer Agent to use.

**In short:** Where structured knowledge lives after Living Knowledge processes your Sources. Continuously restructured and rewritten into one non-ambiguous library.

**Last updated:** 2026-05-27

## Key concepts

### Structured content units
Discrete pieces of content the Engine derives from your Sources. Each unit covers one idea, written in a consistent voice and stripped of duplicates.

### Continuous restructuring
The library rebuilds itself whenever Sources change. Add a new Source, the library updates. Update an existing Source, the library updates. You do not maintain this manually.

### Source traceability
Every unit in the library traces back to the Source it came from. When the agent answers a question, you can follow the chain to the original content.

### Conflicts and gaps
The Engine flags conflicting content across Sources and topics where Living Knowledge is thin. These appear in the Inbox as Messages waiting for human judgment.

## What you can do here

- Review structured content units the Engine has derived from your Sources
- Trace a content unit back to its original Source
- See which units are referenced most often by the agent
- Inspect flagged conflicts and gaps
- Approve, edit, or discard suggestions from Team Feedback

## When to use it

- You want to understand what the agent actually knows, not just what is in your Sources
- The agent gave a wrong answer and you want to find the offending content unit
- You are auditing Living Knowledge for an internal review

## When not to use it

- You want to add new content. Add it as a [Source](/en/help/train/knowledge-base/sources/) and the Content library will pick it up.
- You want to publish customer-facing articles. That is what the [Help Center](/en/help/train/knowledge-base/help-center/) is for.

## How it works

The Engine reads every Source, breaks it into ideas, dedupes across Sources, and rewrites into one voice. This is the difference between a vector index over raw documents and a maintained library: ambiguity gets removed at processing time, not at retrieval time.

## Frequently asked questions

**How do I see what is in the Content library?**
Open **Train > Knowledge base > Content library**. The view lists structured units, with filters for topic, Source, and usage frequency.

**Why is a content unit wrong?**
Open the unit to see its source chain. Usually one of the upstream Sources is wrong, outdated, or contradicts another Source. Fix the Source and the library updates.

**How do I resolve a conflict between Sources?**
Open the conflict in the Inbox. Decide which Source is correct, archive or update the other, and the library reprocesses.

**Can I edit content directly in the library?**
No. Edits happen at the Source level. The library is derived, not authored.

**How often does the library refresh?**
On every Source change. There is no schedule to manage.