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

# Findings

> Problems agents hit in the factory while they work, recorded so someone can fix the cause.

A **finding** is a problem an agent hit in the factory while working on an item, such as a flaky test or a wrong instruction. Agents record problems they hit in the factory so you can fix the cause before the next agent hits it. A problem in the agent's own change is fixed, not recorded.

## Read them on the item page

The work item page lists its findings on the **Findings** tab. Each finding has exactly one category, and the tab groups them under these headings:

<Frame caption="The Findings tab groups each finding under its category.">
  <img src="https://mintcdn.com/outer-layer/WamG4UDZsfczxWBI/images/item-findings-tab.png?fit=max&auto=format&n=WamG4UDZsfczxWBI&q=85&s=f9e59320177d1d48fabf45d926e25269" alt="A work item page on its Findings tab, with one flaky-test finding and one tooling finding" width="2880" height="1800" data-path="images/item-findings-tab.png" />
</Frame>

| Category | Shown as | What it reports |
| - | - | - |
| `context` | Context | An instruction, skill or rule that is wrong, broken, or silent on something the agent had to discover. It names the file and, for a wrong or broken rule, the sentence. |
| `flaky-test` | Flaky tests | A test that failed and then passed with no change. |
| `tooling` | Tooling | A command, script or gate that misbehaved. |
| `environment` | Environment | A local setup problem, such as a port in use, a shared database or a missing dependency. |
| `defect` | Defects | A bug in code outside the agent's own change. |
| `other` | Other | Anything else that cost the agent time. |

Each row has three columns:

* **Finding**: the one-sentence title, and the file and line it is about.
* **Rule it relates to**: for a `context` finding, whether the instruction is `wrong`, `broken` or `missing`, and the quoted sentence.
* **Where**: where the agent recorded it, such as "build session".

The **Context** heading also names the repository the instructions came from, and its commit when the agent recorded one. An item with no findings shows *No findings*.

Findings do not affect whether the work passes. No check, policy or merge gate reads them.

## Record one

An agent records one finding with [`outerlayer emit finding`](/reference/cli-emit#outerlayer-emit-finding), or a batch from a JSON file with [`outerlayer emit findings`](/reference/cli-emit#outerlayer-emit-findings). Each finding needs an id, a category, a title, a file and where it was recorded.

The maintained `reporting-findings` skill tells agents when a problem is worth recording. `outerlayer init` installs it when you run init in a git repository.


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