Senior Technical Product Manager specializing in AI/ML products and agentic systems. Writing about product strategy, 0-to-1 development, and first-principles thinking & growth.
Let me be direct with you. After years working in enterprise AI, the thing I see kill agentic products in production is not the model. It is not the prompt. It is not even the data. It is the handoff. The moment your agent needs to do something consequential - move money, deploy code, send an email to a customer - and your team has not designed a clear, deliberate boundary between "the agent…
I spent some time trying to figure out why my agent's context window kept filling up before I'd asked it to do anything real. The answer turned out to be embarrassingly simple, and once I saw it I couldn't unsee it. The culprit was MCP. Specifically, the way an MCP server announces itself: the moment it connects, it dumps the full description of every tool it offers into your context. For a GitHub…
A PM’s first-principles field report on learning smart contracts in 2026, with practical guidance on Solidity, toolchains, and the AI × blockchain opportunity.
Data tells you what. Interviews tell you why. Segmentation tells you who. The missing third step that separates senior PMs from mid-level - with a real example.
AI agents are becoming the primary user of your product. A practical AUX guide for PMs - 4 patterns from Notion, Salesforce & Intercom, a supervision framework, and a 7-point action checklist.
A practical decision framework for AI PMs on when to add AI to a product feature - 5 key questions, a visual decision tree, 5 anti-patterns, and real-world examples.
A first-principles guide to competitive advantage when AI has commoditized everything. Hint: It's not your features, your model, or your UI. I'm going to say something that might be hard to hear. For the last decade, we, as product managers, have been worshipping a false god: the feature moat. We told ourselves that a 10x better feature, a slicker UI, or a more integrated workflow would protect…
A comprehensive guide to moving from Product Manager to Venture Builder - skills to build, a venture launch playbook, metrics & governance, AI moats, and how to pitch the role internally.
A first-principles analysis of AI's trajectory to 2030, exploring exponential acceleration, self-improving systems, multi-agent coordination, and why this is the Age of Amplification, not automation.
A comprehensive playbook for building agentic AI systems using first-principles thinking, cognitive science, and real-world implementation with unit economics and code examples.