---
title: Introduction
sidebar:
  order: 0
---

**Roboto** analyzes your robotics data, so you know how your robots behave, why they fail, and what to improve.

<div style="position: relative; padding-bottom: 62.5%; height: 0;"><iframe src="https://www.loom.com/embed/15be947f0931480a831a57031f4a47cb?sid=9e118f2a-79f1-4097-9e00-c17c7aa87795" frameborder="0" webkitallowfullscreen mozallowfullscreen allowfullscreen style="position: absolute; top: 0; left: 0; width: 100%; height: 100%;"></iframe></div>

Robot logs are **complex**: they're large, multimodal, and often use binary formats. This makes it hard to extract the data and insights needed to build safe, reliable systems.

Most teams start with manual review: visualizing logs and replaying data. But that approach alone doesn't scale. It slows you down and makes it harder to catch issues or measure performance as your fleet grows.

Roboto helps you move beyond that. It gives you the tools to **automate analysis** and handle growing data volumes:

- **Datasets** to organize, curate and tag your robot logs
- **Agents** to search, analyze, triage, and annotate your data
- **Actions** to ingest data and automate custom post-processing
- A powerful **query engine** to search data and find edge cases
- An interactive **visualizer** to annotate events and dive deep on issues
- An extensible **SDK** to extract slices of data and integrate with other tools

Roboto has support for formats like `ros`, `px4`, `mcap`, and `parquet` — and can be extended to custom ones as well.

## Next steps

**[Get started](/docs/getting-started)**

Create a free account and an access token for the SDK and CLI.

**[Concepts](/docs/learn/concepts)**

Understand how Roboto works.