Skip to main content

Automations

In brief: Automations connect project events to catalog workflows so cloud agents fix issues, implement stories, and repair failing tests without waiting for someone to paste a /testchimp prompt.

Automations turn TestChimp workflows into event-driven runs. When something changes in your project—an issue is created, a story moves to ready, a CI batch fails, a release lifecycle status changes—TestChimp can hand the matching work to a cloud agent as a catalog workflow execution.

Local agents (Claude Code, Cursor, and the TestChimp skill) still run workflows on demand. Automations cover the complementary case: the platform watches for events and invokes the same workflows for you.

Key concepts​

An automation is:

Trigger + Action + Config

PartWhat it answersExamples
TriggerWhen should this run?Entity (issue, story, scenario, test execution, batch, release) + event (created, status updated, failed, …) + optional AND conditions
ActionWhat should the agent do?Execute a catalog workflow (fix-issue, implement, run-qa, …) with a task template, optional policy, and an invocation strategy
ConfigHow should events be batched and gated?Aggregation (Immediate / Buffered / Windowed) and optional human approval before invoke or before plan execute

Policies stay *.policy.md support files in your repo. An automation optionally attaches a policy to the workflow action—the same files local /testchimp runs use.

How it fits with workflows​

Project event  →  matching automation(s)  →  aggregation window
                                              ↓
                                    workflow execution queued
                                              ↓
                         (optional) human approve invoke / plan
                                              ↓
                    cloud agent via ChimpHands, GitHub Issue, or Webhook
                                              ↓
                         /testchimp <workflow> … --workflow-execution-id …
  • Workflows define how the agent should work (playbook + policy).
  • Automations define when that work should start and how the cloud agent is reached.
  • Workflow executions are the auditable runs—status, prompt, ChimpHands session or GitHub issue, approvals—under Executions → Workflow Executions.

Cloud agent invocation strategies​

Each automation action picks one project-level strategy:

  1. ChimpHands — TestChimp dispatches your repo's ChimpHands GitHub Actions workflow with the rendered /testchimp … prompt (and optional branch). Recommended default.
  2. Via GitHub Issue — TestChimp opens a labelled issue (testchimp plus any labels you configure). Your external coding agent watches those labels and runs the prompt in the issue body.
  3. Via Webhook — TestChimp POSTs JSON to a configured endpoint for custom runners.

Configure strategies under Project Settings → Automations and ChimpHands workflow setup under ChimpHands. Details: Cloud agents. For bring-your-own agents (Cursor, Claude Code, Codex, Copilot): Setting up cloud agents.

Where to configure​

SurfacePath
Automations list / create wizardWorkflows → Automations (/workflows/automations)
Project rules (rate limit, ChimpHands, GitHub labels, webhooks)Project Settings → Automations
Runs & approvalsExecutions → Workflow Executions

You can also open the create wizard from contextual Automations CTAs on Issues, Plans, Automation Batches, Releases, and individual workflow detail pages (entity / workflow pre-selected).

Default rate limit: 5 cloud agent invocations per hour per project (shared across all automations). Raise or lower it in project automation settings.

Next steps​

FAQ

What is a TestChimp automation?

An automation is a trigger (entity + event + optional conditions), an action that executes a catalog workflow via a cloud agent, and config for aggregation and optional human approval gates.

How do automations differ from workflows?

Workflows define how the agent works (playbook + policy). Automations define when that work starts and how the cloud agent is reached—ChimpHands, a labelled GitHub issue, or a webhook.

Where do I create and monitor automations?

Create them under Workflows → Automations. Configure rate limits and invocation strategies in Project Settings → Automations. Track runs under Executions → Workflow Executions.

What is the default rate limit?

Five cloud agent invocations per hour per project, shared across all automations. Over-cap runs stay queued until capacity frees.

Related documentation