Overview
Agent Tasks let you delegate a job, investigating an incident, optimizing a build, or anything else you describe, to an AI agent running on your own Qovery-managed infrastructure. For how an agent is configured and what settings are available, see the Configuration Reference.Why Run Agent Tasks in Qovery?
Runs on Your Own Infrastructure
The agent runs as a service on your Qovery-managed cluster, on your own cloud account, not on a third-party SaaS runner you don’t control.
Same Guardrails as Everything Else
Scoped access via Policy API tokens, network boundaries from a domain allowlist controlling exactly what it can reach, resource limits, and execution timeouts, the same governance model as any other Qovery service.
Full Audit Trail
Every run shows up under the agent task’s Deployments tab, with logs, like any other deployment.
Isolated by Design
Clone Environment mode gives a run its own throwaway copy of the environment, so an agent investigating an incident or proposing a code change can’t interfere with what’s actually running in production.
Your Qovery Context, in One Click
Add Qovery services from your environment as context directly, alongside or instead of a Git repository, so the agent has the same view of your infrastructure you do.
Ready-Made Templates
Start from a template built for your use case, incident response, build optimization, or picking up tickets, and adjust it instead of starting from a blank prompt.
Use Cases
Today there are a few ready-made agent configurations, or you can start from scratch and configure every part yourself. Don’t hesitate to reach out to us directly in the product if you have a specific need so we can add it.
Incident Analyzer with incident.io
Correlates a firing incident.io incident with recent changes, logs, and metrics, then reports back to the on-call human and opens a PR if the fix is small and well-understood.
Incident Analyzer with Honeybadger
Same behavior, for teams using Honeybadger instead of incident.io.
Build & Deployment Optimizer
Identifies build and deployment optimization levers and expected gain, opens a PR with the proposed change and/or modifies the build configuration in Qovery.
Jira Coding Agent
Picks up a Jira issue and proposes the corresponding code change as a pull request.
Linear Coding Agent
Picks up a Linear issue and proposes the corresponding code change as a pull request.
Start from Scratch
Configure every part of the agent yourself. Also the full configuration reference: creating an agent, execution mode, triggers and outputs, resources, governance, and environment variables.