Stop drifting. Start shipping.
The compass for curious builders. ~100 AI founders and experts distilled into the wedge, the build, and the sell.
About
Angelina Yang
Interviews the technical founders and domain experts building AI, then distills what they actually did into the wedge, the build, and the sell.
AI/ML researcher, published author on RAG, AI patent holder, Anthropic Developer Contest winner. Her questions are basic on purpose. The ones a first-time builder would want to ask but might feel too embarrassed to. That's the point.
Want to ask Angelina a question? Chat with her AI clone →
Latest
What Should You Study If AI Writes the Code?
Ofer Mendelevitch, author of O'Reilly's Hands-On RAG for Production, on what engineers and CS students should learn now that coding agents write the code — and what still can't be automated.
Why Founders Can't Commit to a Position (It's a Leadership Problem)
Rob Kaminski (Co-Founder, Fletch PMM) on why smart founders understand positioning but refuse to choose one — and why he calls that failure to commit bad leadership.
Do You Actually Need a Knowledge Graph for Your RAG System?
Ofer Mendelevitch, author of O'Reilly's Hands-On RAG for Production, gives a concrete ROI test for when a knowledge graph is worth building — and when it's an expensive mistake.
How Often Should a Startup Change Its Positioning?
Rob Kaminski (Co-Founder, Fletch PMM) on how often positioning should change — every 3-6 months when you're early, 12-18 months once you have traction — and why consistency wins.
How to Evaluate a RAG System Without a Golden Answer Set
Ofer Mendelevitch, author of O'Reilly's Hands-On RAG for Production, explains reference-free RAG evaluation — scoring retrieval quality when you can't hand-label a golden dataset.
The 3 Positioning Strategies for Startups (And When to Use Each)
Rob Kaminski (Co-Founder, Fletch PMM) breaks down the three positioning strategies every startup chooses between — category-aware, category-unaware, and category creation — and how to pick.