> ## Documentation Index
> Fetch the complete documentation index at: https://docs.uselemma.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Introduction

> Lemma is an observability platform for AI agents

Lemma is an observability platform for AI agents. You send one trace per agent execution, and Lemma lets you search, debug, and monitor what your agents actually did in production - and automatically surfaces silent failures.

You instrument with the Lemma SDK; Lemma reads the result and owns the analysis. Follow Lemma's required trace structure so every run is complete and easy to debug.

<Note>
  **The one rule:** one agent execution = one trace. LLM calls and tool calls are child spans of that trace, not separate traces.
</Note>

## Get started

<CardGroup cols={2}>
  <Card title="Quickstart" icon="rocket" href="/getting-started/quickstart">
    Install the SDK, point it at Lemma, and send your first trace in a few minutes.
  </Card>

  <Card title="Lemma tracing skill" icon="bot" href="/getting-started/agent-skill">
    Let a coding agent install the SDK and add tracing from the public Lemma repo.
  </Card>

  <Card title="Trace contract" icon="file-check" href="/reference/trace-contract">
    The exact shape Lemma reads - the mental model everything builds on.
  </Card>
</CardGroup>

## How it works

1. **Instrument with the SDK.** Wrap one agent execution in `lemma.trace()`, and record generation, tool, and app work inside it.
2. **The SDK sends to Lemma** over HTTPS, using your Lemma credentials.
3. **Lemma reads the trace shape** to show inputs and outputs, model calls, tool calls, threads, and to run automated issue detection.

## Instrument in levels

You do not need perfect instrumentation to get value. Start at level 1 and go deeper where debugging hurts.

| Level | Add this                                                        | You can now see                                    |
| ----- | --------------------------------------------------------------- | -------------------------------------------------- |
| 1     | [Trace](/tracing/instrumentation/traces) root with input/output | Which executions ran and whether they succeeded    |
| 2     | [Generations](/tracing/instrumentation/generations)             | Prompts, completions, model, and latency           |
| 3     | [Tool calls](/tracing/instrumentation/tool-calls)               | Tool arguments, results, errors, and latency       |
| 4     | [Spans](/tracing/instrumentation/spans)                         | Retrieval, ranking, and app-logic steps            |
| 5     | [Threads & context](/tracing/instrumentation/context)           | Conversations, users, environments, custom filters |

## What you can do with Lemma

**Trace agents** - see the full execution tree for every trace: LLM calls, tools, retrieval, latency, and errors.

**Debug failures** - inspect inputs, outputs, and errors across nested spans; filter by user, session, environment, and custom attributes.

**Connect your IDE** - use the [Lemma MCP server](/connections/mcp) to query traces from Cursor, Claude Desktop, or Claude Code.

## Choose your path

<CardGroup cols={2}>
  <Card title="Instrument with the SDK" icon="wrench" href="/tracing/instrumentation/setup">
    Install the SDK, then add traces, generations, tool calls, and spans.
  </Card>

  <Card title="Trace contract" icon="file-check" href="/reference/trace-contract">
    Understand the exact shape Lemma reads.
  </Card>
</CardGroup>