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 Design AI Agents for Large-Scale Problem Solving
A practical operating model for decomposing agent work, controlling tools and memory, recovering from failure, and scaling only when outcomes hold up.
-
How to Review Your AI Architecture and Career Story
A practical method to expose production tradeoffs, strengthen AI system design, and turn the same evidence into a credible career story.
-
AI Agent Autonomy: How to Prevent False Success in Production
A practical framework for scoping AI agent authority, proving task completion, blocking unsafe workarounds, and operating autonomy in production.
-
AI Engineering in 2026: An Architecture for Reliability
A practical architecture for dependable AI agents, covering bounded workflows, governed memory, production-path evals, and observability in 2026.
-
How Product Leaders Should Evaluate AI Model and Robotics Releases
A practical framework for deciding which frontier AI and robotics releases deserve evaluation, investment, monitoring, or a deliberate no.
-
A Practical Audit for Removing Unnecessary LLM Calls
A practical framework for tracing LLM calls, testing simpler replacements, and cutting cost and latency without damaging product outcomes.
-
A Product Framework for Evaluating Typed AI Decisions
Learn where typed AI decisions fit, how to keep predictions behind policy controls, and how to test Jev against real workflow economics.
-
How to Turn AI Spending Into Measurable Business Value
A practical model for linking AI costs to completed work, customer outcomes, released capacity, and auditable financial results without overstating savings.
-
Frontier AI Pacing: An Enterprise Safety Assurance Playbook
A practical framework for turning frontier-model evidence into deployment gates, vendor requirements, and coordinated incident controls for AI agents.
-
How to Evaluate and Control Enterprise AI Agents at Runtime
A practical operating model for evaluating agent quality, gating risky actions, preserving identity across queues, and proving your kill switch works.
-
The Real Cost of AI-Assisted Software Product Delivery
A practical way to price AI-assisted delivery across prototyping, production engineering, reliability, launch, operations, and maintenance.
-
How Product Leaders Should Deploy Automated AI Research Agents
A practical model for scoping, supervising, evaluating, and governing AI research agents without confusing polished output with reliable evidence.
-
How to Scale AI Agent Autonomy Without Losing Control
A practical framework for expanding agent permissions, isolating execution, verifying real outcomes, and scaling without multiplying failures.
-
How Product Leaders Should Reassess Core Principles
Use a practical belief audit to preserve, revise, test, or retire product principles as AI and operating conditions change.
-
How Product Leaders Should Govern Emerging AI Capabilities
A practical framework for governing retrieval poisoning, synthetic user forecasts, agent permissions, and the evidence needed before launch.
-
AI, Jobs and Robotics: A Small-Business Readiness Plan
A practical plan for choosing safe AI tasks, protecting high-stakes decisions, preparing employees, and deciding when automation deserves more authority.
-
A Practical System for Personal Multi-Model AI Workflows
Build a portable AI workflow that routes work by job, tests models fairly, and turns repeated corrections into reusable skills without vendor lock-in.
-
How to Design Context for Reliable Enterprise AI Agents
A practical method for giving enterprise AI agents the right evidence, permissions, freshness, and action boundaries before they make decisions.
-
Production AI Reliability: How to Earn User Trust
A practical operating model for setting AI autonomy, testing full workflows, exposing accountability, and recovering before failures erode trust.
-
AI Agent Swarms: An Operating Model for Product Leaders
A practical framework for deciding when agent swarms earn their complexity, building the control plane, and proving value before rollout.
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.