> ## Documentation Index
> Fetch the complete documentation index at: https://docs.clarifeye.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Signals

> Collect corrections, gaps, and drift so the store stays accurate.

A store is only useful while it stays accurate, and accuracy decays. **Signals** are how it keeps up: a signal is anything that should prompt an update, a correction, a gap, drift, or new context worth capturing.

A signal can come from anyone, anywhere, the moment they notice the knowledge is out of date or incomplete: from an AI client using the [Clarifeye skill](/guides/mcp), from a [chat or a task](/guides/use), from inside Clarifeye, from [Slack or Teams](/guides/signals-slack), or from an expert who simply knows a policy changed. They all land in one place so nothing is lost.

What a signal points at depends on the use case. When the store is context for an implementer, on an ERP migration for instance, signals mostly flag missing information the implementer needs to move forward. When the store is used directly through Chat, Task or an AI client, they more often surface something that needs the project owner's attention: a rule that changed, an answer that was wrong, a decision nobody has taken yet.

Signals are an input, not the change itself. Take them into [Work with Clara](/guides/work-with-clara) to turn each one into a concrete update to your [artifacts](/guides/artifacts) or [sources](/guides/sources); when closing a gap needs fresh expertise, a signal can trigger a new [interview](/guides/interviews). Keeping the store current is the most important ongoing job, so encourage everyone to leave a signal whenever something looks off.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.