> ## Documentation Index
> Fetch the complete documentation index at: https://qovery-gdubroeucq-qov-2345.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Build & Deployment Optimizer

> Ready-made Agent Task that proposes faster, cheaper build and deployment configurations

<Warning>
  **Early Preview.** Agent Tasks is available in early preview to a limited set of organizations. Capabilities and setup will change before general availability.
</Warning>

## Overview

Identifies build and deployment optimization levers and their expected gain, then opens a PR with the proposed change and/or updates the build configuration in Qovery directly. It never merges a fix on its own.

## How It Works

To find concrete ways to make builds and deployments faster and cheaper, the agent:

1. Inspects the service's build setup: Dockerfile, dependency installation, layer caching, image size, and the build/deploy configuration in Qovery.
2. Identifies optimization levers, for example better layer ordering and caching, multi-stage builds, smaller base images, pruning unused dependencies, or parallelisable steps.
3. For each lever, estimates the expected gain (build time, image size, or cost) and the risk.
4. Opens a PR with the proposed changes to the build configuration, and/or updates the build configuration in Qovery directly.
5. Summarises what it changed, the expected gain, and anything that needs a human decision. It never merges, the human always stays the gate.

## Setting It Up

<Steps>
  <Step title="Create the agent task">
    From the **Agent use cases** section when creating a new service, pick **Build & deployment optimizer** (see [Creating an Agent](/configuration/agent-tasks/overview#creating-an-agent)), or start from scratch and paste in the instructions above.
  </Step>

  <Step title="Connect the repository">
    Add the Qovery service to optimize as its Context, its linked Git repository is included automatically so the agent can inspect the Dockerfile and build setup. Add a repository on its own only if it isn't tied to a Qovery service.
  </Step>

  <Step title="Add the Qovery MCP server">
    Since you added the service as Context, Qovery's own MCP server is created and selected automatically: organization-scoped, read-only, backed by a Viewer API token. That's enough for the agent to **propose** changes (open a PR).

    To let it **apply** changes to Qovery directly instead, add the MCP server manually with an API Policy Token that has write permissions on that service's build/deploy configuration. See [Add MCP Servers](/configuration/agent-tasks/overview#creating-an-agent).
  </Step>

  <Step title="Add a trigger">
    Add a schedule trigger, for example weekly, to periodically review build performance, or a webhook trigger. See [Triggers](/configuration/agent-tasks/overview#triggers) for how they work in general.
  </Step>

  <Step title="Keep In Place as the execution mode">
    This agent is typically run on a schedule rather than triggered concurrently, so **In Place** (the default) works well. Use **Clone Environment** instead if you expect overlapping runs. See [Execution Mode](/configuration/agent-tasks/overview#execution-mode).
  </Step>

  <Step title="Trigger a first run and check the results">
    Click **Trigger** on the agent task's overview page to run it on demand. Check the run under its **Deployments** tab, and review the PR it opened (or the build configuration it updated, if you granted write access).
  </Step>
</Steps>

See [Configuration](/configuration/agent-tasks/overview#configuration) for resources and environment variables, general settings shared by every agent task.