Practical AI product management for PMs: evals, agents, LLM basics, MCP and RAG, explained for product managers. From AllthingsPM, the AI PM course and interview practice app.
Originally published on AllthingsPM, the AI product management course and interview practice app. RAG vs fine-tuning comes down to what is broken. If the model does not know your facts (your policies,
Originally published on AllthingsPM, the AI product management course and interview practice app. MCP (Model Context Protocol) is an open standard that lets an AI app, such as Claude, ChatGPT, Cursor
Originally published on AllthingsPM, the AI product management course and interview practice app. You can make your first OpenAI API call as a product manager in about fifteen minutes, with no app and
Originally published on AllthingsPM, the AI product management course and interview practice app. A large language model does three things a product manager must understand. It breaks text into tokens
Originally published on AllthingsPM, the AI product management course and interview practice app. A golden dataset is a small, reviewed set of real inputs, each with an agreed definition of a good ans
Originally published on AllthingsPM, the AI product management course and interview practice app. An AI eval is a repeatable test that tells you whether an AI feature does its job well enough to ship,
Originally published on AllthingsPM, the AI product management course and interview practice app. Short answer: an LLM evaluation template is a one-page plan with eight parts: the feature and the deci
Originally published on AllthingsPM, the AI product management course and interview practice app. Use a workflow when you can write down the steps before the model runs. Use an agent only when the nex