Hire an AI feature planner

Everything it can hand back

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

• A one-line measure of success and the numbers that will show it.
• A data check that lists what you have, what is missing and any privacy concerns.
• A comparison of two or three ways to build it, with one recommended and why.
• A test plan that covers quality, fairness across groups and a live comparison.
• A launch plan for how the feature answers users, with versioning and a way to roll back.
• A watch plan with drift, speed and cost alerts, and what should trigger retraining.

How it does the job well

• Give no accuracy, speed or cost figure you did not get from the user or from a source you name. Mark any estimate ASSUMED:.
• Do not choose a vendor or tool as a fact. Offer the profile's examples as options and say to check current prices and features.
• Do not give legal advice on privacy or fairness law. Refer that to a qualified person.
• Read the existing code, its conventions and its tests before changing anything. Match the project's patterns.
• Make the smallest change that fully solves the request. Keep unrelated refactors out.
• Reproduce a bug before fixing it, and add a test that fails without the fix.
• Treat input from users, files and networks as untrusted. Validate it at the boundary.

Mistakes it avoids

• Claiming code works without running it or its tests.
• Inventing APIs, package versions or settings instead of checking the installed ones.
• Changing behaviour outside the request, such as reformatting whole files or renaming public interfaces.

What a good result looks like

An example, not your task: You want to add a recommendation, classifier, search or text feature to your product and don't know where to start.

• Goal and success measure. The feature in one line and the numbers that will show it works, with any assumed number marked.
• Data check. Each data source, what it holds, what is missing and any privacy concern.
• Options. A hosted model, your own model and a rules-only version compared, with one recommended.
• Test plan. Quality measures, a test set, bias checks across groups and a live comparison.
• Launch plan. How the feature serves answers, with sign-in, rate limits, versions and a rollback.
• Watch plan. Alerts for drift, speed, data quality and cost, and the trigger for retraining.

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.

A second opinion

Before it hands back, your AI reviews the draft the way Donald Knuth would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Pin down the goal and the data. It restates the feature and the user, asks what good looks like, and checks what data exists, how clean it is and what is private.
• Compare ways to build it. It sets a hosted model, a model you train and a rules-only version side by side on effort, cost, speed and risk.
• Plan how to measure it. It picks the quality measures, a test set, bias checks across groups and a live comparison against what you do today.
• Plan the launch. It chooses real-time, batch, streaming or on-device serving. It adds sign-in, rate limits, model versions and scaling.
• Plan the watching. It lists alerts for drift, slow answers, bad data and cost, and a trigger for retraining.
• Review safety and privacy. It checks bias, privacy, harmful output and human review, and says what a qualified person must sign off.

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-ai-engineer 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-ai-engineer/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

• The feature you want, in one or two sentences, and who will use it.
• What data you have, where it lives and roughly how much (a short description is enough).
• Your limits, such as response time, monthly budget and where the data may be stored.
• What goes wrong if the AI is wrong, such as a wrong tag or a wrong decision about a person.
• Your current setup, such as your cloud and the languages your team uses (optional).

Helpful context (optional)

• A sample of your data with private details removed.
• What you do today for this task, so the plan can compare against it.
• Your monthly budget for the feature.

Tools and access

• Claude, ChatGPT or Gemini: Any of them can compare options and write the plan. Attach notes or a data sample if you can.

Functions and deliverables

• AI feature planner: Get a plan to add an AI feature to your product, from data check to launch, with bias tests, monitoring and a retraining trigger.
  • A one-line measure of success and the numbers that will show it.
  • A data check that lists what you have, what is missing and any privacy concerns.
  • A comparison of two or three ways to build it, with one recommended and why.
  • A test plan that covers quality, fairness across groups and a live comparison.
  • A launch plan for how the feature answers users, with versioning and a way to roll back.
  • A watch plan with drift, speed and cost alerts, and what should trigger retraining.
  Source: Michael Sitarzewski and Agency Agents contributors.
• Cloud monitoring planner: Share your app and cloud setup. Get a plan, dashboards and alert settings to track service health.
  • Service health targets
  • Metric, log and trace setup
  • Dashboards by service
  • Alert rules with fewer false alarms
  Source: Burhan Sebin.
• Qdrant health monitoring planner: Get a Qdrant monitoring plan: what to watch, which alerts to set, and how to find why search is slow or memory keeps growing.
  • A list of the metrics to collect and where to find them
  • Health checks for your setup
  • A short list of alerts to set, with the reason for each
  • A log plan, if you need central or audit logs
  • For a live problem, the likely cause, the number that proves it and what not to touch
  Source: GitHub Copilot community.
• Agent anomaly monitor builder: Plan checks that spot unusual changes in your numbers. Set baselines, quiet periods and alert rules so you get few, useful alerts. Draft only.
  • A check table: baseline window, detector, warning and critical levels, confirmation count and quiet period for each number
  • Rules for missing or late data
  • The fields of an alert record, with a next check
  • Tuning rules for too many or too few alerts
  • A list of gaps in the starter files, and test cases
• 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.
• Donald Knuth: Review code or a careful explanation using Donald Knuth’s recorded approach. Work a small example, make the reasoning readable and separate tests from proof.
  • Your problem worked on the way Donald Knuth would: their questions, their method, their push-back
  • The answer or the work, in Donald Knuth's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• You want to add a recommendation, classifier, search or text feature to your product and don't know where to start.
• A prototype works on a few examples and you need a plan to run it for real users.
• You must choose between calling a hosted AI model and training your own.
• Someone asks how you will test an AI feature for bias, privacy and drift.

Limits to check before starting

• You want a chatbot or app built today. Use the AI app and chatbot builder.
• Your feature answers questions from your own documents. Use the RAG pipeline implementation planner or the RAG pipeline designer.
• You are training or tuning a large language model. Use the LLM post-training planner.
• Your problem is moving and cleaning data, not the AI itself. Use the Data pipeline designer.

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. Or paste SKILL.md into a new chat, then paste references/source-agent.md after it.
• Describe the feature, your data, your limits and the cost of a wrong answer. Attach any notes on your current setup.
• Say "Plan this AI feature." Your AI asks once for anything missing.
• Read the data check and the option comparison first. Make sure the recommended option fits your budget and skills.
• Share the plan with the engineer who will build it. It does not train a model, run code or deploy anything.
• Replace every number marked ASSUMED with your own before you commit to a launch date.
• Next, take the watch plan to the AI agent monitoring planner to set up alerts. If the feature answers from your own documents, use the RAG Pipeline Engineer agent.

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-ai-engineer 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.