A playbook
Put AI inside your product
Ship AI features users actually feel, not a bolted-on chatbot.
3 steps, 34 questions, laid out in the order you'll hit them
Each step is a topic with the real questions founders ask; open whichever one you're stuck on for the answer and the resources on it.
-
1
AI in Your ProductShould my startup add AI features, and which ones actually matter to users? 21 → How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)? 21 → How much does it cost to run AI features, and how do I keep costs sane? 22 → Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in? 20 → How do I test whether my AI feature actually works before launch (evals, in plain terms)? 18 → All 15 questions in AI in Your Product →
-
2
AI AgentsWhat actually is an AI agent, in plain language? 7 → Why would a founder use agents instead of a chatbot or automation? 17 → What real tasks are founders delegating to agents today? 21 → How do I build my first agent without being technical? 10 → Which platform or framework should I build my agents on? 20 → All 15 questions in AI Agents →
-
3
PromptingWhy do some people get 10x better results from the same AI tools? 4 → What are the 5 prompting techniques worth learning (and the ones that are outdated)? 7 → How do I give AI the right context about my business (projects, custom instructions, memory)? 6 → Which tool helps me write better AI prompts? 7 →