Learn · Developer

The Builder's Path

From your first API call to shipping agents: prompting for programs, your own data, tools, evals, and costs.

Developer

From Chatbot to API: Your First Programmatic Call

What an AI API actually is, how keys, tokens, and billing work, the universal shape of a model request, and when building on the API beats using a subscription.

Updated Aug 19, 2026
Developer

Prompting for Programs: When the Reader Is Code

How prompting changes when software consumes the output: system prompts as specification, structured output, handling the model's creativity when you wanted none, and designing for the failure case.

Updated Aug 19, 2026
Developer

Grounding AI in Your Own Data

The three ways to give a model your own knowledge — stuffing the context, retrieval (RAG), and fine-tuning — when each wins, and the unglamorous details that decide whether retrieval actually works.

Updated Aug 19, 2026
Developer

Building Your First Agent

The agent loop from a builder's perspective: defining tools the model can call, MCP as the integration standard, prompt injection as the threat model, and the permission design that makes autonomy safe.

Updated Aug 19, 2026
Developer

Evals: Testing Software That Rolls Dice

How to test AI features when outputs vary: building a golden set from real failures, grading with code, humans, and model judges, and wiring evals into development so prompt changes stop being vibes.

Updated Aug 19, 2026
Developer

Choosing Models and Controlling Costs

A durable framework for model selection — capability tiers, latency, context, and price — plus the cost levers that matter in production: right-sizing, caching, cascades, and knowing your unit economics.

Updated Aug 19, 2026

← All learning tracks