Engine across the lifecycle
For each issue, Engine surfaces the contributing traces, proposes a fix, keeps the issue current by attaching new traces that match the same failure pattern, and creates ground truth dataset examples from the production trace inputs.Build: Open a pull request
Apply the proposed fix by opening a pull request in your connected repository. Engine can propose code changes to agents built with Deep Agents, LangChain, and LangGraph.
Test: Generate datasets
Create ground truth dataset examples from production traces for offline evaluation, so you can verify a fix before it ships.
Monitor: Track recurring issues
Scan your tracing projects on a schedule to surface, prioritize, and diagnose recurring issues, and add new matching traces to each issue as they appear.
How Engine runs
Engine scans each connected tracing project on a dynamic schedule tuned to balance cost and performance. It clusters and prioritizes issues by severity and charges in LangChain Standard Units (LSUs). LangSmith Cloud uses LangChain-managed inference. Self-hosted deployments can use LangSmith Intelligence or their own model providers. See Engine on self-hosted for installation and model-provider options, and Engine security for data handling and access controls. For setup, costs, and the issue workflow, see Find and fix your agent’s issues. On LangSmith Cloud, Red Teaming can also test a deployment with synthetic requests before failures reach production.Get started
Set up Engine
Enable Engine for your organization and configure it for a tracing project or agent environment.
Engine notifications
Send detected issues to Slack or to your incident-management, paging, or chat tools through webhooks.
Connect these docs to your agent of choice via MCP for real-time answers.