Wrap AI providers

Integrate frameworks

Add custom tracing

Advanced tracing patterns

Capture user feedback

Log attachments

View your logs

Filter and search logs

Use deep search

Score production traces

Monitor with dashboards

Use Loop

Build evaluation datasets

Configure human review

Capture user feedback

Add labels and corrections

Export annotated data

Use playgrounds

Run evaluations

Write effective prompts

Write effective scorers

Run remote evaluations

Interpret evaluation results

Compare experiments

Evaluate reasoning models

Use the AI Proxy

Deploy prompts

Deploy functions

Monitor deployments

Manage environments

Use the Data API

Model Context Protocol

Stream responses

Manage organizations

Manage projects

Access control

Configure the AI Proxy

Evaluating agents

Writing scorers

PM workflows