Lessons
1LLMs for PMs46 min read
What an LLM actually is — a probabilistic next-token predictor with finite working memory you rent by the token — with no math. Tokens, context, why output varies, what it can and cannot reliably do, and the interview questions that probe whether you treat it as a magic box.
- →LLM Product Fundamentals
2Prompting & context47 min read
Why prompting is context engineering, not magic words. The anatomy of a strong prompt, the failure modes of a weak one, few-shot vs instructions, structured output as a contract, and how a PM critiques and improves a prompt in a review — with the interview drills that test it.
- →Prompt and Context Architecture
3RAG vs fine-tuning vs API49 min read
The single most-tested AI-PM decision: prompt → RAG → fine-tune → custom, and the build-vs-buy call underneath it. What each approach actually changes, what it costs, when each wins, the named-company cases (Notion, Harvey, Bloomberg), and the decision tree interviewers want to hear.
- →Model and Build Strategy
4Agents & MCP for product48 min read
What an agent actually is versus a workflow, why Anthropic says use agents only when steps are unpredictable, how errors compound across multi-step tasks, where to put the human, and what MCP is — the integration standard you should ask vendors about. With the agency/reversibility/value-density decision tree interviewers test.
- →Agents and MCP
- →Capability-to-Feature Scoping
5Cost, latency & routing economics49 min read
The economics an AI PM owns, not engineering: cost-per-task as the North Star, the output/input price asymmetry, real 2026 per-million-token numbers, why a routing cascade hits ~97% of frontier quality at ~24% of cost, the latency levers, and the debugging playbook when quality or cost regresses.
- →AI Unit Economics
- →Model and Build Strategy
6Capstone: capability-to-feature map50 min read
Put it together: take a concrete product and map model capabilities to a feature set — choosing prompting/RAG/fine-tuning/agents per feature, scoping each by inputs/outputs/tasks/subjects, pricing it, designing for failure, and specifying the eval. The end-to-end artifact a senior AI PM produces.
- →Capability-to-Feature Scoping
- →Prompt and Context Architecture
- →AI Unit Economics
Skills in this course
- 01LLM Product FundamentalsExplain tokens, context, variability, and core model limits in product terms.
- 02Prompt and Context ArchitectureSpecify prompts, context, structured outputs, and failure handling as product behavior.
- 03Model and Build StrategyChoose prompt, RAG, fine-tune, API, or owned model based on the product gap.
- 04Agents and MCPChoose bounded workflows or agents and assess MCP integration value and risk.
- 05AI Unit EconomicsModel cost per completed task and use routing, caching, and output control.
- 06Capability-to-Feature ScopingMap model capabilities to bounded features, failure modes, and eval criteria.