For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
      • AstroFully-managed data operations, powered by Apache Airflow.
      • Astro Private CloudRun Airflow-as-a-service in your environment.
      • Professional ServicesExpert Airflow services for your enterprise's success.
    • Tools
      • Cosmos
      • Orbiter
      • CLI
      • AI SDK
      • Agents
      • Blueprint
      • UpdatesThe State of Airflow 2026See the insights from over 5,800 data practitioners in the full report. Download Now ➔
  • Customers
  • Docs
    • Insights
      • Blog
      • Webinars
      • Resource Library
      • Events
    • Education
      • Academy
      • What is Airflow?
  • Pricing
Get Started Free
    • Overview
        • Overview
        • Quickstart
        • Customize Otto
        • Upgrade Airflow with Otto
      • MCP servers
      • Toggle AI features
    • Book Office Hours

Product

  • Platform Overview
  • Astro
  • Astro Observe
  • Astro Private Cloud
  • Security & Trust
  • Pricing

Tools & Services

  • Cosmos
  • Docs
  • Professional Services
  • Product Updates

Use Cases

  • AI Ops
  • Data Observability
  • ETL/ELT
  • ML Ops
  • Operational Analytics
  • All Use Cases

Industries

  • Financial Services
  • Gaming
  • Retail
  • Manufacturing
  • Healthcare
  • All Industries

Resources

  • Academy
  • eBooks & Guides
  • Blog
  • Webinars
  • Events
  • The Data Flowcast Podcast
  • All Resources

Airflow

  • What is Airflow
  • Airflow on Astro
  • Airflow 3.0
  • Airflow Upgrades
  • Airflow Use Cases
  • Airflow 2.x End of Life

Company

  • Our Story
  • Customers
  • Newsroom
  • Careers
  • Contact

Support

  • Knowledge Base
  • Status
  • Contact Support
GitHubYouTubeLinkedInx
  • Legal
  • Privacy
  • Terms of Service
  • Consent Preferences

  • Do Not Sell or Share My Personal information
  • Limit the Use Of My Sensitive Personal Information

Apache Airflow®, Airflow, and the Airflow logo are trademarks of the Apache Software Foundation. Copyright © Astronomer 2026. All rights reserved.

LogoLogo
On this page
  • Prerequisites
  • Step 1: Launch Otto
  • Step 2: Run your first prompt
  • Other prompts to try
  • Step 3: Resume a session
  • What Otto knows about your project
  • Next steps
AI featuresOtto

Otto quickstart

Edit this page
Built with
Labs
This feature is in Labs.

This quickstart walks you through your first Otto session. By the end, Otto is running in your project and ready to help you author, debug, and manage Dags. You can also optionally start local Airflow so Otto can query Dag runs, task logs, connections, and variables.

Otto requires an Astro account. Start a free trial if you don’t have one.

Prerequisites

  • Astro CLI v1.42+ installed.
  • An Astro account. Run astro login.
  • (Optional) An Astro project folder. Otto works without an Astro project, but project context makes it more useful.

Step 1: Launch Otto

From your Astro project folder, run:

$astro otto

Otto opens an interactive terminal interface. The CLI handles authentication automatically.

Have Otto start local Airflow

You can also prompt Otto to start a local Airflow environment:

“Configure this project for standalone mode and start local Airflow.”

With Airflow running, Otto can use the af CLI to query Dag runs, task logs, connections, and variables on the live instance, and automatic Dag validation runs after each edit. See Local Airflow overview for the standalone vs Docker comparison.

Step 2: Run your first prompt

Enter a prompt in the input area. To explore your project, try:

“Look at my Dags and summarize each one.”

Otto reads your Dag files, checks the running Airflow instance for metadata, and provides a summary of each Dag with its schedule, tasks, and dependencies.

Other prompts to try

“Check my Dags for deprecated patterns.”

Otto validates your code against your Airflow version.

“Why did my last Dag run fail?”

Otto checks task logs and run history to diagnose failures.

“Create a new Dag that pulls data from Snowflake and loads it into Postgres.”

Otto authors a Dag using your project’s conventions and connection IDs.

Step 3: Resume a session

Otto persists session history automatically. To continue your most recent session:

$astro otto --continue

To pick from a list of previous sessions in an interactive picker:

$astro otto --resume

To open a specific session file:

$astro otto --session <path-to-session-file>

Session files are stored as JSONL at ~/.astro/otto/sessions/.

What Otto knows about your project

When you launch Otto in an Astro project folder, it automatically detects:

  • Project root: The folder containing .astro/ configuration. If Otto doesn’t find one, it falls back to the current working directory.
  • Airflow URL: The local Airflow instance started by astro dev start.
  • Memory: Existing memory files in .astro/memory/ (shared project memory), ~/.astro/memory/<project-slug>/ (local project memory), or ~/.astro/memory/ (local user memory). See Memory.

Next steps

  • Skills — Browse Otto’s bundled skills and author your own for team-specific workflows.
  • Tools — Explore the full set of tools Otto uses, including the af CLI for Airflow.
  • Memory — Learn how Otto accumulates and uses team-specific knowledge.