eval-driven development
- AI Strategy (429)
- Generative AI (113)
- IT Leadership (38)
- Leadership (81)
- Product Management (394)
- Product Management Leadership (373)
- Uncategorized (32)
-
How to Prepare for a Senior Product Manager Technical Interview
A practical framework for proving technical judgment, handling AI-first interview formats, and preparing stories that survive senior-level follow-up.
-
From AI Demo to Production: Proving Value Before You Scale
A practical framework for choosing a valuable AI job, defining proof of success, and scaling autonomy only when the system can fail safely.
-
Consolidating MCP Tools Without Sacrificing Capability
A practical framework for reshaping an MCP tool catalog around user intent, reducing context waste, and validating changes with task-level evals.
-
How to Run AI Support Quality as a Continuous Operation
A practical operating model for measuring AI support quality, gating releases, shaping conversations, and turning live failures into controlled improvements.
-
A Product Leader’s Playbook for Every New AI Model Release
A practical system for deciding when a new AI model deserves testing, how to evaluate it, and when to adopt, watch, or walk away.
-
Frontier AI Scaling: A Product Leader’s Agent Economy Playbook
A practical framework for turning abundant frontier-model capacity into trusted, measurable agent work without mistaking supply for demand.
-
Trustworthy Agentic Product Engineering: A Release Playbook
Use this release playbook to bound agent authority, stop inherited errors, evaluate failures, explain changes, and make AI actions reversible.
-
Claude 5.5 Task Economics: Price Outcomes, Not Tokens
A practical framework for testing Claude 5.5 on real work and measuring model spend, correction time, retention, and cost per accepted outcome.
-
AI Citation Integrity Checks: A Workflow Editors Can Trust
A practical design and rollout guide for citation checks that catch integrity risks before peer review without overwhelming editors with weak alerts.
-
Planning Product Strategy Around Rapidly Falling AI Costs
A practical framework for modeling AI unit economics, sequencing cost-sensitive bets, pricing usage, and building defensible products as inference gets cheaper.
-
Jev Decision Model Performance: Accuracy, Cost, and Fit
A practical guide to interpreting Jev benchmarks, designing a safe cascade, and measuring whether its fast decisions improve real outcomes.
-
Product Context: The Missing Layer in Enterprise AI Agents
A practical framework for giving enterprise AI agents the user, workflow, policy, and outcome context needed to act safely and prove measurable value.
-
How to Build an AI Strategy as Costs Fall and Tools Multiply
A practical framework for selecting, integrating, governing, and retiring AI tools as capability prices fall faster than planning cycles.
-
September 2026 AI Evaluation: From Scores to Systems
A practical system for deciding whether AI features and agents are ready to ship, what to measure, and how to turn failures into regression tests.
-
Fei-Fei Li and the Product Foundations of Computer Vision
Use ImageNet’s history to decide where a vision product really needs investment: data, taxonomy, evaluation, compute, or model design.
-
How to Design AI Assistants for Wearables and Enterprise
A practical framework for choosing the right jobs, permissions, handoffs, and success metrics for AI assistants on wearables and at work.
-
How to Make Frontier AI Evaluations Independent and Credible
A practical framework for frontier AI evaluations that preserves access, limits provider influence, controls observer effects, and earns trust.
-
How to Build Reliable AI Evals for Product Decisions
A practical method for separating real AI gains from evaluator drift, auditing failures, and making defensible product release decisions.
-
When AI Agents Need World Models: A Product Leader’s Guide
A practical framework for deciding when an AI agent needs a world model, designing its control loop, and testing consequences before granting autonomy.
-
How to Design AI Agents for Large-Scale Problem Solving
A practical operating model for decomposing complex work, constraining agent authority, evaluating outcomes, and scaling only when the system earns it.
Weekly digest
One email a week on AI products, enablement and hiring. No fluff.
Browse topics
- AI Strategy (429)
- Generative AI (113)
- IT Leadership (38)
- Leadership (81)
- Product Management (394)
- Product Management Leadership (373)
- Uncategorized (32)
Work with me
45-minute consultation on AI product strategy, GTM and PM hiring — no charge.