Skip to content
AFTERTHE LASTCLICK

Track

AI products

How to build AI products that make money. Agents, answer engines and copilots, from picking the first use case to pricing the launch.

  • Agents
  • Evals
  • RAG
  • Pricing
  • Trust
EP 06How to build pricing for an AI productSeats, usage or outcomes, and how to pick before your costs pick for youAI productsPlanned
EP 04How to build an eval system for an AI productThe test suite that tells you if the model got better or just differentAI productsNext up
EP 02How to build an AI agent that takes actions for usersScope, evals and guardrails for an agent people let touch real moneyAI productsLive

Glossary

Key terms

Agent
A system that plans and takes actions for a user, not only answers.
Evals
A test set that scores model output, so you know if a change made it better.
RAG
Retrieval-augmented generation. The model reads your documents before it answers.
Grounding
Tying an answer to sources the user can check.
Guardrail
A rule that blocks or reviews an output before it reaches the user.
Token cost
What each model call costs you. It sets your floor price.

SUBSCRIBE

One playbook every two weeks. Nothing else.