Operator Agent Skills

Building AI Products

Source-grounded pack with Plan an AI Feature Launch, Review AI Product Risk and Trust, and Qualify an AI Product Use Case, plus 1 more.

Use this pack when

Choose this pack when the work touches Building AI Products and you need a bounded workflow with explicit inputs, a defined output, and human review gates.

Included workflows

Choose the job in front of you.

4 source-grounded skills. Load one workflow at a time.

Plan an AI Feature Launch

Use this workflow when choosing an AI product stack and preparing a limited or full release with model strategy, data and learning rights, economics, metrics, enterprise controls, support operations, rollout gates, rollback, and durable ownership.

Output Return an aifeaturelaunchplan with stackdecision, fallbacks, datarights, learningloop, metrics, economics, enterprisecontrols, supportmodel, rollout, releasegates, stopconditions, rollback, owners, and durability.

Review AI Product Risk and Trust

Use this workflow when designing or auditing an AI product's uncertainty, trust, correction, autonomy, permission, data-rights, admin-control, and recovery surfaces before exposing users to model failures.

Output Return an aiproductriskreview with failureinventory, truststates, evidenceux, correctioncontrols, autonomy, permissions, datacontrols, admincontrols, recovery, supporthandoff, blockingrisks, and owners.

Qualify an AI Product Use Case

Use this workflow when deciding whether a proposed AI product feature solves a valuable user job, needs model behavior, fits a real workflow, can absorb uncertainty, has legitimate data, and supports viable economics.

Output Return an aiusecasequalification with userjob, productpromise, baseline, workflowmap, valuemechanism, aileverage, nonaialternative, uncertaintyfit, datafit, economics, adoption, decision, and proofcriteria.

Plan Model-Behavior Evaluation

Use this workflow when translating an AI product promise into explicit quality requirements, representative gold cases, automatic and human evaluations, regression coverage, release gates, production monitoring, and post-launch ownership.

Output Return a modelbehaviorevaluationplan with productpromise, qualitydimensions, goldset, automaticevals, humanevals, criticalcases, rubric, thresholds, releasegates, productionmetrics, rollback, owners, and cadence.

Human review

Keep consequential decisions explicit.

These workflows structure analysis and artifacts; they do not authorize autonomous external, personnel, financial, legal, security, or other high-impact action.

Source and files

Grounded in the complete Building AI Products series.

10 source essays · 4 usable skills · reviewed Jul 2026

Choose your reading rhythm.

Start with a weekly briefing, add daily notes, or hear only when a durable essay or library update is ready.

You've successfully subscribed to Antoine Buteau
Great! Next, complete checkout to get full access to all premium content.
Welcome back! You've successfully signed in.
Unable to sign you in. Please try again.
Success! Your account is fully activated, you now have access to all content.
Error! Stripe checkout failed.
Success! Your billing info is updated.
Error! Billing info update failed.