# Validating & improving knowledge

Confirm your agent answers correctly from its sources, close real gaps surfaced in conversations, and keep content fresh as your product changes.

**Path:** Agent Studio → Knowledge

Adding a source isn't the finish line. You still need to confirm the agent actually answers correctly from it, and keep that content accurate as your product changes. Run this as a continuous loop.

## 1. Validate in the Playground before users do

Open the [Playground](/user-guides/playground/) and ask the questions your users actually ask. Check each answer against what the source contains:

- **Right answer, right source.** The content is covered and retrievable. Done.
- **Wrong or "I don't know".** The content is missing or stale. [Add or re-sync a source](/user-guides/knowledge-sources/).
- **Right answer exists but the agent didn't find it.** A retrieval miss, not a coverage gap. Fix it with [Pointers](/user-guides/pointers/).

This is the fastest way to catch a problem before it reaches a real user.

## 2. Close real gaps from Conversations

The Playground tells you what you thought to test. [Conversations](/user-guides/conversations/) tells you what users actually hit. Two methods surface the gaps:

- **Filter by signal.** In the filter bar, open **Conversation Signals** and select **Agent Knowledge Gap** to see exactly the chats where the agent lacked the content to answer.
- **Ask the Foldspace agent.** On the same page, ask the built-in agent for an analysis, for example *"What are the knowledge gaps in the last 30 days?"*. It reads the same signals and summarizes them, so you can get oriented fast, then apply the filter to read the underlying conversations yourself.

Each gap is a concrete to-do:

1. Read the conversation to understand what the user wanted.
2. Add or update the source that should have answered it, usually a new [internal article](/user-guides/knowledge-sources/) or a re-synced one.
3. Re-test the question in the Playground to confirm it is fixed.

This conversation-driven loop is how your Knowledge Base gets better over time instead of drifting out of date.

:::tip[Action gaps work the same way]
The same two methods surface **action gaps**: filter Conversations by **Agent Action Gap**, or ask the Foldspace agent *"What are the action gaps in the last 30 days?"* to discover which actions users want that the agent can't yet run. Reading that signal in aggregate and turning it into new capabilities is covered in [Analyzing conversations](/user-guides/analytics/analyzing-conversations/).
:::

## 3. Keep sources fresh

A wrong or incomplete answer is most often an out-of-date source. Review sync status regularly:

- **Crawlers and connectors** re-sync on their own. Confirm the last sync date is recent and the article count looks right.
- **Files, single pages, and internal articles** only change when you change them. Refresh them when the underlying product or policy changes.

## 4. When the right content isn't retrieved

If the article exists but the agent reaches for the wrong one, or doesn't surface it because the user's wording differs from your terminology, that is a retrieval problem, not a coverage problem. Those rare cases are exactly what [Pointers](/user-guides/pointers/) are for.