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

# Introduction

> Infrastructure for catching AI agent mistakes in production and turning them into evals.

Infrastructure for catching AI agent mistakes in production and turning them into evals. A trace is the full record of one agent run — every message, tool call, thinking block, and step — whether or not a human is in the loop. You send traces through the Python or Node.js SDK, OpenTelemetry, or the HTTP Ingestion API. Moda analyzes every trace automatically — grouping it into use-case clusters and detecting user emotion, tool failure, laziness, and hallucination signals, which are rolled up into problems — and you explore the results in the dashboard or query them with the Data API and CLI.

## The three surfaces

### Ingestion

The Ingestion API accepts trace data from the Moda SDKs for Python and Node.js, which auto-instrument the OpenAI and Anthropic client libraries, and from any OpenTelemetry setup that exports OTLP over HTTP, or a direct HTTP call. Integrations also cover the [Vercel AI SDK](https://docs.moda.dev/ingestion/vercel-ai-sdk.md), the [Claude Agent SDK](https://docs.moda.dev/ingestion/claude-agent-sdk.md), and providers such as OpenRouter, Azure OpenAI, Bedrock, Vapi, and OpenClaw. Start with the [ingestion overview](https://docs.moda.dev/ingestion/overview.md) or the [quickstart](https://docs.moda.dev/quickstart.md).

### Dashboard

The dashboard at [moda.dev/dashboard](https://moda.dev/dashboard) is where you read the analysis: browse [traces](https://docs.moda.dev/dashboard/traces.md) with a full timeline and world state, review [signals](https://docs.moda.dev/dashboard/signals.md) and [problems](https://docs.moda.dev/dashboard/problems.md), and explore [use cases](https://docs.moda.dev/dashboard/use-cases.md), users, and tools. The [dashboard overview](https://docs.moda.dev/dashboard/overview.md) describes each section.

### Data API & CLI

Everything the dashboard shows is also queryable. The [Data API](https://docs.moda.dev/data-api/overview.md) is an HTTP API at `https://moda.dev/api/v1/data`, authenticated with your API key. The [CLI](https://docs.moda.dev/cli/overview.md) (`@moda-ai/cli`, binary `moda`) brings search, analytics, signal and Problem investigation (emotions, hallucinations, Problem dossiers, world state), live tailing, and fix workflows to your terminal and CI. The hosted [MCP server](https://docs.moda.dev/mcp/overview.md) exposes the same commands as MCP tools, so Claude Code, Cursor, or any MCP client can query your production data directly.

## How data flows

1. Your application sends traces to the Ingestion API — through an SDK, an OpenTelemetry exporter, or a direct HTTP request.
2. Moda processes new data within minutes; traces appear on the Traces page shortly after ingest.
3. Emotion, tool-failure, laziness, and hallucination signals appear within minutes, and problems and use-case clusters build automatically as evidence accumulates.

## Getting access

Moda is invite-only. Sign up at [moda.dev/signup](https://moda.dev/signup) and request access. Once the Moda team approves your request, it creates your workspace with you as its owner, emails you, and onboarding starts at your next sign-in. Teammates join an existing workspace by invitation (**Settings → Members & roles**). To send data you need an API key (called an ingestion key in the dashboard): create one at **Settings → Ingestion keys**. The full key is shown once, at creation.

## Next steps

* [Quickstart](https://docs.moda.dev/quickstart.md) — send your first trace and see it in the dashboard.
* [Ingestion overview](https://docs.moda.dev/ingestion/overview.md) — choose the right way to send data for your stack.
* [Data model](https://docs.moda.dev/concepts/data-model.md) — how traces, signals, problems, and use cases relate.
* [Data API overview](https://docs.moda.dev/data-api/overview.md) — query your data programmatically.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.