Documentation

Datool brings traces, datasets, scorers, and evaluation runs into one project. Start with a trace from your application, inspect its inputs and outputs, then turn useful examples into repeatable tests.

Start here

Send your first trace — Choose AI SDK, TypeScript, Python, or LangGraph. The Python function and graph examples need no model API key.

Run your first evaluation — Connect an app, catch a failing case, fix it, and compare saved runs. No model key is required.

Use your first managed prompt — Publish a template and fetch the latest published version from your application.

Understand the concepts — Learn how traces, spans, sessions, datasets, and scores fit together.

Connect your existing instrumentation — Export OpenTelemetry spans and instrument AI SDK calls.

Build an evaluation workflow

1. Inspect a request in Traces and identify an example worth testing.
2. Add cases and expected outputs to a dataset.
3. Define a scorer that expresses what a good result means.
4. Run an evaluation against a connected app and inspect each result.

Use the Playground to try individual inputs, Prompts to version message templates, and Dashboards to follow changes over time.

Work from your tools

• SDK: record application behavior from Node.js.
• API: call project operations with typed request and response schemas.
• CLI: inspect traces, sync resources, connect local handlers, and run evaluation gates.
• MCP: let an authorized AI assistant investigate and work with your project.
• Self-hosting: run the web application, database, Redis, and ingestion worker.

These docs are public. Your project's data and API operations require authentication.

Read docs as Markdown

Every documentation page supports Accept: text/markdown or a .md suffix. For example, with DATOOL_BASE_URL set to your instance's origin:

curl -H 'Accept: text/markdown' "$DATOOL_BASE_URL/docs/evaluation/datasets"
curl "$DATOOL_BASE_URL/docs/evaluation/datasets.md"

Both return the same Markdown with Content-Type: text/markdown. Use /docs.md for this documentation index. The View as Markdown link on each page also works, and agents can discover all pages through /llms.txt. Normal browser requests to URLs without .md keep the documentation layout.

For installation requirements, see versions and compatibility. If a workflow fails, start with troubleshooting.