Skip to main content
Ona Agent extends your engineering team’s capacity. It completes tasks in isolated environments - writing code, running tests, opening pull requests - while respecting your organization’s security policies and guardrails. Ona Agent works out of the box with zero configuration. Start a conversation, give it a task, and it gets to work. As you use it more, you can teach it your codebase conventions, create custom commands, and configure guardrails.

​
What Ona Agent can do

  • Write and modify code - features, bug fixes, refactors, tests, documentation
  • Run your toolchain - commands, formatters, linters, test suites in isolated environments
  • Manage pull requests - open branches, create PRs, respond to review feedback
  • Execute long-running work - migrations, large refactors, multi-repo changes (see Automations)
  • Follow your policies - command allow/deny lists, SSO, audit logging

​
How it works

  1. You give Ona Agent a task (via chat, Linear issue, or automation trigger)
  2. Agent starts an isolated environment with your Dev Container configuration
  3. Agent works autonomously - reading code, making changes, running tests
  4. Agent opens a pull request for your review
The environment is isolated from your machine and other environments. If something goes wrong, discard it and start fresh - mistakes are free.

​
Prerequisites

None required to get started. Ona Agent works immediately with Ona Cloud. For advanced setups:
  • Your own infrastructure: Deploy runners in AWS or GCP
  • Faster startup: Configure a Dev Container for your repository

​
Get productive

  1. Teach agents your codebase - create an AGENTS.md with your conventions, or add Skills for repo-specific workflows
  2. Create custom commands - codify your team’s workflows with slash commands
  3. Connect integrations - enable Linear or other integrations for richer context
  4. Set guardrails - configure command deny lists and policies for safe execution

​
Best practices

  • Start with smaller tasks and expand scope as you build confidence
  • Keep environments reproducible with Dev Containers and Tasks
  • Use guardrails for safe, auditable execution
  • Test workflows in non-production repositories before broad rollout

​
Next steps