> ## Documentation Index > Fetch the complete documentation index at: https://braintrust.dev/docs/llms.txt > Use this file to discover all available pages before exploring further. # Review and act on patterns > Read a pattern and its evidence, turn it into a scorer or classifier you can monitor, hand it to a coding agent, and close it when it's resolved. Each pattern is a recurring problem or trend that [Loop](/docs/loop) found in your traces, saved with the evidence behind it. Patterns are scoped to a single project. ## Find a pattern Go to [** Patterns**](https://www.braintrust.dev/app/~/patterns) and select a pattern from the list to open it. The list shows open patterns by default. A pattern stays open until someone closes it, so the default view is everything that still needs attention. Click **Filter patterns** to switch between **Open**, **Closed as resolved**, **Closed as not useful**, and **Closed without reason**. Each option shows how many patterns it contains. To search across patterns by name, use the search box above the list. ## Read a pattern Start here to decide whether a pattern is worth acting on, and to check Loop's reasoning against the traces it drew from. A pattern detail has four parts: * **Summary** is what Loop found and the context behind it. * **Suggested fix** is the next investigation or change Loop recommends, when it has one to offer. * **How to monitor** appears when Loop couldn't attach a useful monitor chart but can recommend a way to measure the behavior later. See [Act on a pattern](#act-on-a-pattern). * **Evidence** is what the finding rests on. Evidence comes in two forms: * **Monitors** are charts tracking matching traces over time, when Loop could attach one. * The trace list shows the traces themselves, with Loop's notes quoted inline. Select a trace to open it in the [Debugger](/docs/observe/debug-traces). The trace scrolls to the span field the evidence came from and highlights the quoted terms. ## Act on a pattern Once you've read a pattern, there are four things you can do with it. They're alternatives, not a sequence, and which one fits depends on whether you want to understand the behavior better, track it, fix it, or bring in someone else. ### Keep investigating Select **Continue in Loop** to start a thread with the pattern attached as context. Loop shows a badge with the pattern name, so you can see what it's working from. If the thread the pattern came from is no longer available, Loop opens a fresh thread with the pattern still attached and tells you the original thread is unavailable. ### Make it measurable Under **How to monitor**, click **Create scorer** or **Create classifier**, depending on what Loop recommended. Loop opens with a prefilled prompt, adds the evaluator to the pattern, works out a backfill strategy with you, and creates a monitor chart for it. This is how a one-time finding becomes something tracked continuously, at lower cost than re-investigating it. Loop can also turn a pattern into a [facet](/docs/observe/topics/custom-facets) so that [Topics](/docs/observe/topics) classifies the behavior across all your traces. ### Hand it to a coding agent Click **Copy pattern as prompt** in the pattern header. Braintrust copies a Markdown brief containing the pattern's status and close outcome, summary, suggested fix, evidence trace IDs, and [`bt` CLI](/docs/reference/cli/quickstart) commands for pulling the full traces. Paste it into your coding agent to start work on a fix. ### Share it Click **Copy link** in the pattern header to copy a link to the pattern. This appears when the pattern is open in Loop's workspace. The link only works for people who can already access the project. Objects a scheduled run creates are not linked back to the pattern. If a pattern's monitor chart measures a scorer or facet that a run created, deleting that scorer or facet stops new data from reaching the chart. ## Close or reopen Close a pattern once you've acted on it, or once you've decided it isn't worth acting on. Closed patterns leave the **Open** list, and the outcome you choose becomes feedback Loop uses to judge future findings. Click **Close** in the pattern header. Choosing an outcome is optional: * **Resolved** if the problem is fixed, addressed, or no longer happening. * **Not useful** if the pattern is noise, transient, or unimportant. You can also add free-text feedback. The header then reads **Closed as resolved**, **Closed as not useful**, or **Closed without outcome**, and a banner on the detail attributes the closure to whoever closed it and shows their feedback. Click **Reopen** to set a closed pattern back to active. Loop can also change a pattern's status when it updates an existing pattern. A closed pattern reflects a judgment about the available evidence, not proof that the underlying problem is fixed. Closing a pattern as resolved does not verify the fix. Use a scorer or monitor chart for that. Closing and reopening a pattern requires the [`Update` permission](/docs/admin/access-control#object-permissions) on the project. Without it, the **Close** and **Reopen** buttons don't appear, though you can still read patterns and their evidence. Members of the **Owners** and **Engineers** [permission groups](/docs/admin/access-control#built-in-permission-groups) have it by default. ## Next steps * [Write scorers](/docs/evaluate/write-scorers) to measure a behavior a pattern surfaced. * [Build datasets](/docs/annotate/datasets/create) from the traces behind a pattern, then [run an experiment](/docs/evaluate/run-evaluations) to test a fix. * [Create custom facets](/docs/observe/topics/custom-facets) to track the behavior across every trace. * [Debug a trace](/docs/observe/debug-traces) to dig into a single piece of evidence.