retrieval-first pipeline
- AI Strategy (429)
- Generative AI (113)
- IT Leadership (38)
- Leadership (81)
- Product Management (394)
- Product Management Leadership (373)
- Uncategorized (32)
-
Google AI Engineering Interview Prep: A Practical Plan
A practical plan to prioritize coding, ML depth, system design, RAG, agents, and resume stories without memorizing a speculative question bank.
-
AI Memory Freshness: How to Handle Contradictory Facts
Design AI memory as a governed decision ledger so your product retrieves the latest approved truth, exposes conflicts, and preserves history.
-
AI Music Search Starts With Metadata, Not a Chatbot
A product playbook for building AI music search on structured metadata, rights-aware retrieval, rigorous evaluation, and durable strategy.
-
How to Build a Trustworthy AI-Assisted Research Workflow
A practical workflow for using AI to collect, compare, draft, and edit academic work while keeping evidence, citations, and judgment under your control.
-
Persistent Memory for AI Assistants: A Product Playbook
A practical guide to deciding what an AI assistant should remember, operating its memory lifecycle, and measuring whether users can trust it.
-
Persistent Memory for AI Agents: A Product Leader’s Guide
A practical framework for deciding what an AI agent should remember, how it should retrieve and forget memories, and how to test the value safely.
-
Context Engineering: How to Build Reliable AI Applications
A practical framework for designing context, diagnosing agent failures, budgeting each turn, and evaluating AI applications before production.
-
Visual Search for Messy B2B Catalogs: An Intent-First Playbook
A practical framework for turning ambiguous product images into intent-aware retrieval, trustworthy ranking, and measurable B2B sourcing outcomes.
-
Engineering MCP Agents as a Reliable Product Platform
A practical framework for building MCP agent platforms around controlled context, safe actions, measurable reliability, and governed scale.
-
Prompt Engineering for Amplitude Global Agent That Holds Up
A practical framework for prompting Amplitude Global Agent to produce grounded, reviewable analysis that supports real product decisions.
-
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…
-
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.
-
AI Product Data Security: A Practical Playbook for PMs
A practical playbook for mapping AI data flows, assigning risk, selecting vendors, and embedding security controls without blocking delivery.
-
Cracking the Hardest Percentages: Turn Complex Support into Scalable, Trust-Building Automation
Complex queries are the smallest slice of most queues, yet they dominate handle time and define customer trust. In my experience, the fastest path to higher…
-
How We Taught Agentic AI to Speak Product Analytics—and Unlocked Actionable Insights
I describe how we taught agentic AI to understand the nuanced language of product analytics and deliver trustworthy answers grounded in our metric catalog and event…
-
Never Stop Disrupting: Why the Fin API Platform Signals a New Era for Agentic AI
Disruption favors teams that move from features to agents—and the Fin API platform accelerates that shift. With a customer agent platform resolving over 2M issues weekly…
-
How to Build Scalable, AI-Ready Product Documentation
A practical operating model for creating reliable, versioned product knowledge that serves customers, support teams, and AI assistants.
-
Agentic Architecture Demystified: How Modern AI Systems Plan, Learn, and Execute at Scale
Modern AI isn’t just a model; it’s an agentic system that plans, retrieves, acts, and evaluates in a tight loop. In this piece, I break down…
-
Prevent Strategy Drift: AI that flags ‘merge conflicts’ in product plans before a quarter derails
What if you could spot strategy misalignment the moment it starts—before it torpedoes a quarter? I break down how “GitHub for product management” can surface merge…
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.