Latest
Build Your First AI Evaluation Dataset and Scoring Rubric
Create a quality baseline before changing an AI prompt or model. Work through eight cases, hand-scored answers, a copyable rubric, and explicit decision gates.
Ideas for better product decisions
Featured
How to Actually Deploy Claude in Your Product Development Workflow
Every product team is using Claude. Very few are deploying it in a way that closes the real gap. This is the guide that shows you what the complete deployment …
Popular
MCP Skills in Claude and Codex: A Practical Comparison
MCP skills combine reusable AI workflows with live tool access. See how Claude and Codex handle skills, connectors, packaging, and product backlog work.
Latest thinking
Build Your First AI Evaluation Dataset and Scoring Rubric
Create a quality baseline before changing an AI prompt or model. Work through eight cases, hand-scored answers, a copyable rubric, and explicit decision gates.
Turn a Shipped Feature into an AI-Drafted Help Article
Turn verified product behavior into task-based documentation. Follow an invitation demo through an evidence packet, a drafting prompt, and a complete help-article sample.
Human Review, LLM Judges, or Automated Tests: Choosing the Right AI Evaluation
Match the evaluation method to the failure you need to catch. Compare exact checks, claim support, expert judgment, and calibrated model grading through four worked cases.
From Product Requirements to a Clickable AI Prototype: A Reviewable Workflow
Follow a fictional workspace invitation from a bounded brief to a working browser prototype. Use a requirement matrix, generation prompt, and click-through tests to review the result.
How to Build a Reusable Visual Component Library for Product Workshops
Give product workshops a shared vocabulary for screens, actions, decisions, and states. Build a small library, test it across two workshops, and connect the result to a story map.
Schedule AI Feedback Reviews Without Automatically Changing Your Backlog
Design a weekly feedback review that produces evidence-linked proposals. Keep scheduling, human approval, and backlog writes explicit, with checks for missing sources, stale records, and retries.
How to Update a Story Map After a Release
Reconcile the map with what users can actually do, keep new evidence distinct from delivery status, and assign ownership when research or a release changes the plan.
A Two-Hour Remote Story Mapping Workshop: Agenda and Facilitation Script
Take one user journey from a shared starting point to a proposed release slice. This 120-minute agenda includes quiet writing, facilitator prompts, a break, and follow-up decisions.
User Activities vs User Tasks: How to Structure a Story Map
Place activities, steps, and stories at a useful level of detail. A worked class-booking example shows where ambiguous cards belong and how to repair a mixed-level map.
I Only Wanted a Delete Button. It Became Four Different Decisions
Getting a request out of Waiting could mean delivery, taking it back, cancellation, or deletion. The gap-finder question forced four different decisions about the person’s history.
The Chart Looked Convincing. What Exactly Was It Claiming?
SpendVsInvest’s chart raised questions an animation could not answer: which returns count, how far the data goes, and what “gain” means. Those questions became requirements.
The Penalty Role Sounded Fun—Until Someone Had to Get It
A role that removes someone’s points made the game more varied on paper. Asking who would receive it exposed the fairness decisions that belonged before an MVP commitment.