Hire an AI Drupal performance engineer

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A baseline of what is slow and what is already fine
• Findings ranked by gain, each with evidence, the fix, the risk and a check
• Cache settings fixes, so no cache has to be turned off
• Slow Views, queries, image and script fixes
• Hosting and PHP settings for your developer to check

How it does the job well

• Every finding must cite evidence the user gave. If a cause is only likely, write "likely, confirm with <check>". Never invent scores, query times or module behaviour.
• Never advise turning off the Internal Page Cache, the Dynamic Page Cache or setting max-age to 0 on a whole page to fix stale content. Fix the cache tags or contexts. If something is truly uncacheable, isolate it behind a lazy builder.
• Never advise changing a live site first. Every fix goes to a copy of the site, then is tested, then is released.
• Never advise caching pages for logged-in users in a shared cache without the right contexts. A cache that leaks one user's page to another is a breach.
• Do not log in, run a command, change settings or deploy. Prepare drafts and ask first.
• Profile before you change anything — never optimize on a hunch. Capture a baseline with Lighthouse, the database query log, and a profiler (Webprofiler/XHProf) before touching code. An "optimization" with no before-and-after measurement is a guess, and guesses make sites slower as often as faster.
• Never disable a cache to fix a stale-content bug — fix the cacheability metadata. A block showing old data is a cache *tags* problem, not a reason to set max-age: 0 or turn off the Dynamic Page Cache. Disabling caches to fix invalidation trades one wrong render for a site-wide performance collapse.

Mistakes it avoids

• Optimizing by hunch with no measurements.
• Giving a speed gain as a number you cannot support. Say "expected to help" until the after test.
• Copying the profile's sample audit as the user's facts.
• Judging by desktop scores alone. Mobile on a slower connection is the test.
• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.

What a good result looks like

An example, not your task: Your Drupal 10 or 11 site feels slow and a speed test shows a poor mobile score.

• Scope. The site, versions, host and the pages being fixed.
• Baseline. Speed scores and cache headers per page, recorded before any change.
• Findings, ranked by gain. Each problem with the evidence, the fix, the risk and the check that proves it.
• Caching fixes. What is uncached, why, and the cache tags, contexts or lifetime to set.
• Query and Views fixes. Slow Views and queries, with rows loaded against rows shown and the fix.
• Front-end fixes. Script, style and image problems with a fix for each.

How the work is checked

• The changed files build, and the relevant tests and linters pass. The commands and results are shown.
• Each change is explained in one line with its reason, and risky areas are named.
• Any check that could not run is reported as NOT_RUN with what it needs.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

Capabilities

• Fix the scope. It confirms the Drupal version, host and pages to fix. Anything missing is asked once, then marked MISSING.
• Read the baseline. It records your speed scores and cache headers before any change, so each fix can be proved.
• Fix caching first. It finds anything that stops pages from being cached and fixes the cache tags, contexts and lifetime instead of turning a cache off.
• Fix queries and Views. It finds the slowest queries and Views, and bounds each one so it loads only what it shows.
• Fix the front end. It checks script and style loading, image sizes, formats and lazy loading, and the main image on each page.
• Check hosting and prove it. It reviews PHP and cache storage settings, then lists the before and after checks for each fix.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id engineering-drupal-performance only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/engineering-drupal-performance/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• Your Drupal version (10 or 11), PHP version and where it is hosted
• The addresses of the slowest pages
• A PageSpeed or Lighthouse mobile result for each, with the main scores (LCP, INP and CLS)
• The response headers for one slow page, from your browser's network tab (optional)
• Any slow query list or profiler output, and the list of added modules (optional)

Helpful context (optional)

• A PageSpeed report saved as a file for each slow page.
• The View settings of the slowest listing page.
• Your host's PHP and cache settings page.

Tools and access

• Claude, ChatGPT or Gemini with file upload: It can read a saved PageSpeed report, a header export or a module list next to your description.

Functions and deliverables

• Drupal performance engineer agent: Find why your Drupal site is slow. Get ranked fixes for caching, slow pages, images and hosting, each with the evidence and a before and after check.
  • A baseline of what is slow and what is already fine
  • Findings ranked by gain, each with evidence, the fix, the risk and a check
  • Cache settings fixes, so no cache has to be turned off
  • Slow Views, queries, image and script fixes
  • Hosting and PHP settings for your developer to check
  Source: Michael Sitarzewski and Agency Agents contributors.
• Website performance fix ranker: Rank your store speed fixes by orders gained per hour of work. Give it your audit problems and sales numbers. You get a plan for this week and next month.
  • A ranked fix list with expected gain as a range, effort, risk and who does it
  • The money at stake written as orders and revenue per month
  • A plan: top three this week, next five next month, the rest parked with a reason
  • What to measure before and after each fix
• Django database performance reviewer: Trace Django queries to find supported performance issues. Get evidence, proposed fixes and limits where size, usage or timing could not be checked.
  • Confirmed performance issues ranked by impact
  • The code location of each
  • A concrete fix such as select_related or an index
  • A clear statement if nothing serious was found
  Source: sickn33.
• Slack agent response builder: Turn your AI agent's output into a safe Slack message with leak checks, size limits and a plan for each failure, before it posts to a client channel.
  • The response shape and the Slack blocks it becomes, with the size limits applied
  • A 12-check validator plan in a fixed order, with the result of each failure
  • A list of changes to make to the starter formatter for your project
  • A failure checklist saying who is alerted and what is logged
  • Synthetic test cases to run before you turn it on
• AI project context organiser: Share your project and next task. Get a short rules file, a focused file list and a clear handoff for later sessions.
  • A ready rules file for your project
  • A list of which files to load for each task
  • Rules for when to reset or trim the session
  • A checklist for spotting drifting answers
  Source: Addy Osmani.

Tasks you can use it for

• Your Drupal 10 or 11 site feels slow and a speed test shows a poor mobile score.
• A developer said "turn off the cache" to fix stale content, and you want a safer way.
• A page with a big View or a listing takes seconds to load.
• You want a fix list to hand to your developer or your host, in order of gain.

Limits to check before starting

• Your site runs on WordPress. Use the WordPress performance reviewer.
• You run a store on another platform and have a PageSpeed report. Use the Store speed report analyst.
• The site is down right now, or a traffic spike is crashing it. Use the Incident response coordinator, and call your host.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack from this page and add it to your AI as a skill. If you cannot, paste SKILL.md into a new chat, then paste references/source-agent.md.
• Run a free speed test on your slowest pages, such as PageSpeed Insights, on the mobile setting. Copy the main scores and the list of problems it names.
• In your browser, open your slowest page, open the Network tab in developer tools and copy the response headers, including X-Drupal-Cache and X-Drupal-Dynamic-Cache. Your developer can help. No code running by the AI is needed.
• Paste the scores, headers, version details and module list into the AI. Type "Find the real causes. Rank them by gain. Mark anything I did not give you as MISSING."
• Check the first three findings against your own pages. Ask for the evidence line if any looks wrong.
• Give the fix list to your developer. Test each fix on a copy of the site first, and run the speed test again after each one.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/engineering-drupal-performance for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.