Notes from the build
Writing
Notes on building products with a fleet of AI agents.
Latest
Latest · Personal
RAG is a tool. Sometimes it's the wrong one.
RAG solves specific problems—stale knowledge bases, regulatory citations, costly errors—but it's often added prematurely. Here's when to use it, and when to shi
Personal ·
More notes
Feasibility First: The Four Pillars of Real Assessment
Confidence is a mood. A feasibility assessment is evidence. Here's how to structure one that actually changes decisions.
Personal ·
RAG Is Not a Badge of Honor
RAG solves specific problems, not all of them. Here's how to know if your product actually needs it.
Personal ·
Prove It First, Then Build It: The Feasibility Gate
Skip the feasibility check and pay for proof later with runway. Run an honest assessment against four pillars: technical constraints, data availability, integra
Personal ·
RAG is a tool, not a requirement
RAG earns its keep for domain-specific knowledge and regulated industries, but premature implementation before product-market fit wastes resources and obscures
Personal ·
The Four Pillars of Feasibility: Before You Build
Most studios fail not because they built wrong, but because they never tested if their idea could exist. A feasibility gate with four pillars—technical constrai
Personal ·
Five Questions to Ask Before Hiring an AI Studio
Most studios added AI to their pitch decks after the last board meeting. Here's how to tell if they actually know what they're doing.
Personal ·
RAG is a Tool, Not a Badge: When to Build It and When to Skip
RAG solves specific problems—domain knowledge, auditability, expensive errors—but it's often added prematurely. Decide based on real constraints, not vendor pre
Personal ·
Discovery Is the Real Work, Not the Delay Before It
Most SaaS fails because founders assume too much and test too little. Real discovery means actively trying to prove your idea wrong before spending money to bui
Personal ·
The archive
October 2026
- When a Custom Build Is the Wrong Answer · Personal ·
September 2026
- Discovery Is the Only Cheap Insurance You'll Ever Buy · Personal ·
- What Investors Actually Want to See From an AI-Native Startup in 2025 · Personal ·
- The Discovery Ritual Nobody Actually Does · Personal ·
- The Infrastructure Gap: Why Demos Fail in Enterprise · Personal ·
- Why Enterprise Deals Stall (And How to Prevent It) · Personal ·
August 2026
- Structural vs. Discretionary: The Question That Actually Matters · Personal ·
- An AI Glossary for Builders: The Terms Nobody Puts on the Slide · Personal ·
- An AI Glossary for Builders, Not Fundraisers · Personal ·
- Hard Tech Is Hard, But the Studio Model Might Be the Right Vehicle · Personal ·
- How Long an MVP Actually Takes When AI Agents Do the Volume · Personal ·
- What AI Agents Can Actually Do for a Business, From People Who Run Twenty · AI ·
- How to Vet an "AI-Powered" Agency in Fifteen Minutes · Growth ·
July 2026
- AI-Assisted Agency vs AI-Operated Studio: The Difference Nobody Explains · AI ·
- The Bootstrapper's Guide to Mental Models for Better Decisions · Growth ·
- The Bootstrapper's Dilemma: Why Growth Frameworks Fail Early-Stage Businesses · Growth ·
- Claude API Integration: The Sharp Edges We Hit So You Don’t Have To · AI ·
- The Mental Model Quietly Wrecking Your Content Strategy · Growth ·
- What Running AI Agents Actually Costs: Our Real Numbers · AI ·
- Why Nobody Trusts You Yet: The Real Meaning of Topical Authority · Growth ·