Skip to main content
Agent Canvas ships with a set of pre-built automations for the most common agent workflows. Each one is a ready-to-use starting point — pick the one that fits your use case, connect it to the right backend, and you can have an automation running in minutes.

Available Pre-built Automations

Issue to Pull Request

Implements issues from your issue tracker and creates pull requests.

GitHub PR Review Assistant

Reviews pull requests and posts feedback as a comment.

GitHub Repository Monitor

Watches a repository for events and triggers agent actions in response.

Slack Channel Monitor

Listens to a Slack channel and triggers an agent when a message matches a pattern.
Backends created by the agent-canvas launcher include Automation Server, so they can run agents on a schedule or in response to external events.

What You Can Do

In the Automate view, you can:
  • Browse existing automations
  • Inspect automation configuration and activity
  • Enable or disable automations
  • Edit an automation’s LLM profile for future runs
  • Work with recommended automation flows

Templates

The Templates page groups pre-built automations into Suggested (up to eight cards) and More templates. The Beta label appears on individual cards rather than as a section heading. With nothing connected, Suggested starts with proven default templates. Templates that use a connected Git provider, an installed MCP server, or an integration reported by the instance move ahead of the defaults. A template moves to the end of More templates only when the instance reports a different provider or integration type and you have not connected the one the template needs. The catalog includes Bitbucket Data Center code review and Jira Data Center issue to Bitbucket Data Center PR templates on all backends. On a compatible self-hosted deployment, set up Bitbucket Data Center and, for the issue-to-PR template, Jira Data Center. Confirm the automation service supports the required event source before creating one. A Data Center template may be listed even if your backend cannot run it. For the Bitbucket repository picker and cloning behavior, see Repository picker providers. On a self-hosted instance with no detected setup for a Git provider used by a template, selecting the template first shows guidance for connecting that provider through MCP or a token. Continue to the provider’s MCP install, or cancel; when a native integration, matching MCP server, or matching token secret is already available, the template setup opens without this notice. Cloud and local backends do not show this self-hosted notice.

How Creation Flows Usually Start

In practice, new automation setup starts in one of two ways:
  • From a conversation, where you ask OpenHands to create an automation for you
  • From a recommended automation flow in the Automations view
For recommended automations that support a direct form setup, Agent Canvas checks the active backend’s capabilities and any prerequisites, then guides you through the required input fields, a review step, and creation. The setup form shows the template’s description and, if the published catalog entry includes one, a diagram below it. Not every template has a diagram. If direct form setup is unavailable, it offers a conversation-assisted setup instead. Review the proposed configuration before creating an automation. A template that finishes its setup in a conversation opens the two-panel automation setup view: the template’s seed arrives as the first message, and the automation draft sits beside the chat for the agent to fill in. This is the same setup view used when you ask an agent to create an automation. Some catalog entries ship a script bundle — a packaged set of files that install as a deterministic automation — rather than a prompt-based preset. Script-bundle entries run their own logic for tasks like polling, deduplication, and fixed API calls, using the agent only for the parts that genuinely require judgment. When a catalog entry supports a bundle install, the setup form handles packaging and upload automatically; you just fill in the required fields. Catalog entries that accept repositories can also collect multiple repositories in a single field, so one automation can monitor several repos at once. Automation templates appear on cloud backends as well as local backends. Where the built-in Git integration is offered, Agent Canvas presents it before the issue-to-PR templates. For a detailed walkthrough, see Creating Automations. Automations run against the active backend. Use Manage Backends to see and switch which backend your automations run on.

Edit an Automation’s LLM Profile

Open an automation, select Edit, and use the LLM profile dropdown to change which saved profile future runs use. If an automation already has a profile, the edit dialog pre-selects it. Changing the LLM profile affects future automation runs. It does not rewrite previous run history.

Select an Agent Profile for an Automation

When the active backend advertises agent-profile support, the automation setup and edit dialogs include an optional agent profile selector. Choose a saved agent profile to use for automation runs instead of the default agent. When a saved agent profile is selected:
  • The stable agent_profile_id identifies the profile sent to the backend.
  • The automation uses the selected agent profile instead of an LLM profile. Editing an automation clears any existing legacy model selection.
If a previously selected agent profile has been deleted, it remains visible in the selector rather than silently switching to another profile. This lets you review the configuration before choosing a replacement. The agent profile selector appears only on backends that support agent profiles. On backends without agent-profile support, only the LLM profile dropdown is available.