Patterns

Patterns uses Loop to investigate your logs and raw trace data for recurring problems and trends, including behavior your scorers don’t measure. A pattern is a saved finding with supporting evidence, an explanation, and a suggested next step. Use Patterns to:

• Find failures affecting a group of users or regressions, whether or not a scorer covers them.
• Track cost and latency drift in recurring LLM calls.
• Discover recurring successes and emerging use cases.
• Give a coding agent a pattern and its evidence as a prompt to implement a fix.

​

How discovery works

Patterns are produced by a scheduled Loop automation. Each run:

1. Queries recent data according to the automation’s instruction and default query range.
2. Investigates findings through queries and individual traces using the Debugger.
3. Records findings with supporting evidence, or updates an existing pattern when new evidence matches it.

Loop uses Frequency to measure how often a behavior occurs when trace data can reliably identify it. Findings can also include monitor charts and representative traces. When Frequency cannot be measured, Loop provides trace evidence and recommends how to measure it. Scheduled runs review active patterns and refresh Frequency measurements. Loop can close a pattern when recent, relevant data shows the behavior has stopped. Missing data or a failed query is not enough. Your closure outcomes and feedback guide later findings. See Close or reopen. You can also ask Loop to find patterns in an interactive thread. They appear in the same list.

​

Requirements

Patterns needs model access and project permissions:

• Braintrust’s built-in models use your monthly model credits and need no setup if you meet the requirements. To use your own key or continue after credits run out, configure an OpenAI-compatible AI provider.
• Anyone who can read the project’s logs can read patterns. Closing and reopening a pattern also requires the project’s Update permission.

​

Patterns and Topics

Topics classifies and clusters traces so you can filter and chart them by user intent, sentiment, or issue. Patterns investigates findings in depth. Neither requires the other. Topics runs as a separate, low-cost pipeline on Braintrust-served models, regardless of your Loop model selection. Loop can use topic classifications, scores, and human feedback in its investigations. It can also turn a pattern into a facet, scorer, classifier, or monitor to measure the behavior continuously at lower cost. See Act on a pattern.

​

Next steps

• Enable Patterns and configure how often Loop looks for them.
• Review and act on patterns once the first run finishes.
• Discover insights with Topics to classify your traces at a broader scale.
• Run Loop on a schedule for recurring analysis beyond pattern discovery.