Skip to main content
Here’s how a typical interaction with Astro works.
1

Ask Astro to help

You describe what you want to accomplish, whether that’s building a new agent, improving an existing one, or fixing an issue.
2

Astro analyzes and makes changes

Astro reads your agent’s current state and can:
  • Read, edit, delete, and rename nodes
  • Modify node instructions and configurations
  • Tweak workflow settings
  • Add or remove transitions between nodes
  • Start a live environment — a real browser or Linux desktop — and let Astro drive it to understand your use case before it builds the workflow
  • Write Playwright scripts to put reliable nodes on the fast path
  • Run executions and inspect what happened
  • Manage schedules and agent profiles
  • Search the Asteroid documentation and validate your agent
3

Review the changes

Astro’s edits save automatically as it makes them. They land in a draft, so your published agent keeps running untouched until you publish.
This workflow ensures you maintain full control over your agent while benefiting from Astro’s expertise and suggestions.

Conversation Management

You can have multiple conversations with Astro for the same agent. Each conversation maintains its own history, making it easy to:
  • Work on different aspects of your agent in separate conversations
  • Keep track of different topics or improvements
  • Share specific conversations with team members
All your conversations with Astro are saved. You can:
  • View history: Access past conversations from the conversation selector
  • Resume conversations: Pick up where you left off
  • Delete conversations: Remove conversations you no longer need

Operating Context

Each conversation with Astro is tied to a specific agent. Publishing and Running
  • An agent must be Published before it can be run
  • When you run an agent, it uses the last published version, not the draft
  • This means you can continue editing and improving your agent without disrupting running executions
This ensures:

Safe experimentation

Make changes in drafts without affecting production agents

Version control

Keep a stable published version while iterating on improvements

No disruption

Running agents continue using the published version even as you edit

Confidence

Test and review changes thoroughly before publishing