eval-driven development
- AI Strategy (315)
- Generative AI (106)
- IT Leadership (33)
- Leadership (76)
- Product Management (344)
- Product Management Leadership (306)
- Uncategorized (32)
-
AI-Ready Customer Support: An Operating Model That Works
A practical operating model for preparing support knowledge, workflows, guardrails, human handoffs, and launch controls for reliable AI automation.
-
How to Design a Dependable CLI Agent Users Can Trust
A practical framework for building CLI agents with narrow contracts, safe permissions, predictable execution, and measurable reliability.
-
Beyond Accuracy: How I Evaluate AI Customer Service Agents That Delight and Scale
Most teams judge AI agents by accuracy and resolution rates—but that’s only half the story. In my POCs, I mirror real-world messiness, stress-test multi-turn and multilingual…
-
How to Build an AI-Native Product Discovery Workflow
A practical workflow for turning customer evidence and product analytics into traceable decisions with retrieval, bounded AI tasks, and evals.
-
How to Prove the ROI of an AI Product Before You Scale It
A practical system for tying AI product behavior to incremental revenue, real cost savings, and risk-adjusted launch, scale, or rollback decisions.
-
AI-Enabled Enzymatic Recycling: A Product Leader’s Playbook
A practical framework for turning AI-designed recycling enzymes into an industrial product, with stage gates for data, lab proof, scale, and cost.
-
No More Accidental Agents: How We Engineered Global Agent’s Helpful, Curious Personality
Most AI agents inherit accidental personalities from prompts and defaults. We took a different path, treating personality as a measurable product surface and optimizing it with…
-
I Pointed a “Ralph Wiggum” AI Loop at My Product for a Week—The Data That Stopped Chaos
I pointed a “Ralph Wiggum loop” at my product for a week to see how an agentic AI would perform under tight guardrails. The loop moved…
-
From Vision to Execution: Building Agentic, Data‑Driven Products with Real‑World Rigor
Agentic AI demands more than dashboards—it requires a system that observes, reasons, and acts with measurable impact. I connect behavioral analytics to action by pairing Amplitude-style…
-
From Prototype to Production: How I Built Reliable AI-Generated Opportunity Solution Trees
I set out to make AI-generated opportunity solution trees reliable at scale and discovered why updating a tree is far harder than creating one from scratch.…
-
AI-Assisted Product Strategy: A Practical Operating System
A practical operating system for using AI to sharpen product strategy, trace decisions to evidence, and turn discovery into measurable learning.
-
How to Link AI Evals to Retention Without Chasing Proxies
A practical playbook for finding early AI quality signals that predict retention, validating causality, and turning them into product decisions.
-
Amplitude MCP: Evidence-Grounded AI Workflows for Product Teams
A practical playbook for grounding product decisions, bug investigations, and AI-generated changes in Amplitude behavioral evidence, with clear decision gates.
-
5 Proven Agent Skills I Use to Automate Weekly Product Reviews with Claude, Cursor, and Codex
Weekly product reviews can be fast, focused, and high-signal when agentic AI does the prep work. I use five repeatable agent skills—backlog triage, PRD synthesis, experiment…
-
How to Build a Reliable WhatsApp AI Ordering Agent
A practical guide to scope, architect, evaluate, and roll out WhatsApp AI ordering without sacrificing response time or order accuracy.
-
CPO Leadership in the AI Era: A Practical System for Focus
A practical operating system for turning AI pressure into measurable bets, clear decision rights, protected discovery, and durable customer value.
-
AI Product Growth: A Strategy and Execution Operating System
Learn how to turn an AI capability into adoption and revenue with a focused growth thesis, closed-loop instrumentation, evals, and disciplined experiments.
-
How to Run Customer-Facing AI Agents Across Sales and Support
A practical operating model for assigning, measuring, governing, and improving AI agents that serve buyers and support customers without losing trust.
-
Amplitude AI Product Analytics: A Practical Agent Playbook
Use this practical framework to instrument, evaluate, experiment with, and scale Amplitude Agents around product outcomes rather than AI activity.
-
Master Build-to-Learn: The Essential FAQ to Supercharge Product Discovery in the AI Era
In the age of AI, the fastest teams separate build to learn from build to earn. I use discovery to validate problems and value before committing…
Weekly digest
One email a week on AI products, enablement and hiring. No fluff.
Browse topics
- AI Strategy (315)
- Generative AI (106)
- IT Leadership (33)
- Leadership (76)
- Product Management (344)
- Product Management Leadership (306)
- Uncategorized (32)
Work with me
45-minute consultation on AI product strategy, GTM and PM hiring — no charge.