Overview

Lemma turns each agent execution into a trace, finds the executions that went wrong, and groups repeated evidence into issues you can triage. This page is the path after traces arrive: how a trace becomes an issue, how projects and agents relate, and which dashboard surface to open at each step. For software development kit (SDK) vocabulary, see SDK concepts. For dashboard vocabulary, see Platform concepts. To send your first trace, see Quickstart. See Product boundaries for what Lemma evaluates and which surfaces are not shipped.

​

How a trace moves through Lemma

1. An instrumented agent emits a trace for one execution, or one conversation turn when you set a thread ID.
2. Lemma stores the spans and marks the trace ready when you can open it in the dashboard. An API key, an SDK dependency, or an ingest attempt alone does not prove observability.
3. Lemma analyzes completed traces for behavior that materially hurt the agent’s task. Detection is probabilistic: review the supporting traces before you treat a finding as ground truth.
4. Repeated evidence is grouped into an issue. Say the issue was observed in a trace.
5. You investigate in the dashboard or through Inspect, then resolve, dismiss, or send the work into Slack, Linear, the Model Context Protocol (MCP), or webhooks.

​

Projects, agents, and scope

You create projects. A project holds traces, issues, artifacts, and project settings. Each project has its own dashboard. Use separate projects to isolate environments (dev, staging, prod) or distinct products. Agents appear when named traces arrive. Lemma does not ask you to register an application entity. The agent name on a trace is how Lemma groups Artifacts, Analytics scorecards, and issue scope. Traces without a usable agent name still ingest, but agent-scoped features have nothing to attach to.

​

Recommended workspace sequence

1. Select or create an organization and project.
2. Generate an API key and instrument the production agent. Keep LEMMA_API_KEY server-side: never commit it, and never put it in the browser. See Quickstart.
3. Verify at least one real production trace becomes ready. Open Traces and confirm the execution tree and conversation look complete. If the conversation is still active, wait: extraction runs after a thread goes quiet, or immediately when there’s no thread ID.
4. Add agent-specific Artifacts context.
5. Connect the customer Slack workspace, bind a project alert channel, and optionally enable Issue Briefs. See Slack.
6. Configure Linear if the team turns issues into tickets. Each member verifies their own Linear identity.
7. Connect external MCP servers only when Lemma needs their tools. See Lemma MCP server.
8. Connect the coding agent to Lemma MCP when it should investigate or act on Lemma evidence.
9. Add signed webhooks when another system needs issue lifecycle events.
10. Set up the Lemma support Slack Connect channel independently if the plan includes it. It is not a product alert path.

​

The dashboard surfaces

Each surface answers a different question about the same traces: A typical investigation starts on Analytics or Issues, where you spot a trend. From there you open the supporting traces, ask Inspect what’s going on, add Artifacts context if detection missed the mark, and alert or ticket the finding through Connections.

​

Related pages