Skip to main content
Early Preview. Agent Tasks is available in early preview to a limited set of organizations. Capabilities and setup will change before general availability.

​
Overview

Agent Tasks are one-time or scheduled jobs delegated to AI agents, running on your Qovery-managed infrastructure like any other service. Each agent runs with its own resources, environment variables, and a domain allowlist controlling exactly what it can reach.

​
Creating an Agent

1

Create New Service

In your environment, click New Service > Create new service. Under Agent use cases, pick a ready-made template (see Tutorials below) or Start from scratch.
Create new service screen showing the Agent use cases section
2

Add Context (Optional)

Connect a Git repository, a Qovery service, or both, for the agent to load as context.
3

Choose a Provider

Enter your Anthropic API key, the only provider supported today.
4

Add MCP Servers (Optional)

If you added a Qovery service as Context in the previous step, Qovery’s own MCP server is created and selected automatically: organization-scoped, read-only, backed by a Viewer API token. No URL, header, or token to configure. This is also preconfigured for the Incident Analyzer (incident.io and Honeybadger) and Build & deployment optimizer templates.For anything else, connect any remote HTTPS MCP server with its own name, URL, and headers. MCP servers added here are available to every agent task in the organization and can also be managed from Organization Settings > AI settings > Agents.To add Qovery’s own MCP server manually, for example with write access instead of the automatic read-only setup, use an API Policy Token (a regular API token works too):
  • Server URL: https://mcp.qovery.com/mcp
  • HTTP header name: Authorization
  • HTTP header secret value: Token <your API token or Policy API token> (Token with a capital T, then a space, then the token value)
5

Write Instructions

Describe the agent’s role and the steps it should follow in plain text. Reference credentials by the environment variable names you configure below, for example INCIDENT_IO_API_KEY.
6

Choose an Execution Mode

Run the agent in place, or in a clone of the environment. See Execution Mode below.
7

Add a Trigger

Required to run the agent automatically. See Triggers below.
8

Add an Output (Optional)

Send the agent’s result somewhere when it’s done. See Outputs below.
New agent task form with Context, Provider, MCP, Automations, and Instructions on the left, and Resources, Governance, Environment variables, and Advanced settings on the right

​
Execution Mode

Choose where the agent runs when it’s triggered:
  • In Place: runs directly in the current environment.
  • Clone Environment: duplicates the entire environment first, then runs the agent in that isolated clone.
In In Place mode, a new trigger replaces the currently running execution, there’s no run history if the agent is triggered multiple times. Use Clone Environment for agents that can be triggered frequently or concurrently, and In Place for agents on a predictable schedule where overlap isn’t a concern.
Each ready-made template has a sensible default: Incident Analyzer (both the incident.io and Honeybadger variants), Jira Coding Agent, and Linear Coding Agent default to Clone Environment, since an incident or a labeled ticket can trigger them frequently or concurrently. Build & deployment optimizer, typically run on a schedule, defaults to In Place.

​
Limits

  • Execution timeout: each run is capped at 1 hour.
  • Cloned environment TTL: environments created by Clone Environment mode are deleted 3 days after creation.
  • Iterations per run: up to 50 agent iterations per run by default. Override this with the MAX_TURNS environment variable.
  • Clone rate limit: up to 60 clones per hour, per organization, to prevent runaway environment creation.

​
Triggers and Outputs

Add a trigger to run the agent automatically, and optionally an output to send its result somewhere when it’s done. You can also trigger any agent task on demand: click the Trigger (play) button on its overview page, or from the environment’s services list.
Agent task overview page with the Trigger play button highlighted in the top right

​
Triggers

  • On a schedule: a cron expression and timezone, for example 0 8 * * 1-5 for 8:00 AM, Monday through Friday.
  • From a webhook: Qovery generates a unique URL for the agent task, visible later in the environment’s Agent Tasks list (for example https://webhook.qovery.com/api/v1/hook/...). Anything that can send a POST request to that URL starts the agent.

​
Outputs

Send the automation’s result to a webhook: a destination URL, custom headers, and a prompt describing how to shape the result before sending it. For example, to post the result to a Slack channel:
1

Create a Slack Incoming Webhook

In Slack, add the Incoming Webhooks app to the channel and copy the generated URL (https://hooks.slack.com/services/...).
2

Add the output in Qovery

In Add output, paste that URL into Webhook URL. No custom headers are needed, Slack’s incoming webhooks accept a plain JSON POST.
3

Write the prompt

In Prompt, describe the message you want, for example: “Summarize the result as a short Slack message with the root cause and the recommended next step.”
Some agents use a different, more direct pattern instead: storing a chat webhook URL as a secret (for example SLACK_WEBHOOK_URL), adding its hostname to the domain allowlist, and instructing the agent to post to it directly as one of its own steps. Use this pattern when the agent itself, not just the automation’s final output, should decide when and what to post.

​
Configuration

A description of what the agent does.
CPU (mCPU), memory (MB), and storage (GB) allocated to the agent, same as any other Qovery service.
A domain allowlist controls which external hosts the agent task can reach: comma-separated hostnames, or * for all domains.
Plain variables or encrypted secrets the agent’s instructions can reference by name. Secret values can’t be viewed again once set.
A Dockerfile fragment lets you install additional CLIs or binaries in the agent’s runtime before it starts.

​
After You Create It

Agent Tasks appear in your environment overview under Agent Tasks, jobs delegated to AI agents, run once or on a schedule. Each one lists its status, last operation, underlying model, and a dedicated webhook URL you can call to trigger it from outside Qovery. That same webhook URL is also shown on the agent task’s own overview page.

​
Tutorials

Incident Analyzer with incident.io

Ready-made agent that correlates a firing incident.io incident with recent changes, logs, and metrics

Incident Analyzer with Honeybadger

Ready-made agent that correlates a firing Honeybadger incident with recent changes, logs, and metrics

Build & deployment optimizer

Ready-made agent that proposes faster, cheaper build and deployment configurations

Jira Coding Agent

Ready-made agent that picks up a Jira issue and proposes the corresponding code change

Linear Coding Agent

Ready-made agent that picks up a Linear issue and proposes the corresponding code change

Agent Tasks Overview

Use cases and ready-made agent templates