14 courses in 11 categories, each with runnable lessons and a quiz after every section.
Tokens, temperature, prompts, evals, context, cost and speed, on a real model you run.
Python from your first line to classes, Pydantic, async and pytest, on one AI program.
Anthropic's terminal agent. Reads your repo, edits it, runs your commands.
Agents that reason over your documents. Strong on retrieval and indexing.
The layer under most agents. Models, tools, prompts and messages in one interface.
Agents that plan with to-do lists, keep notes in files and hand work to subagents.
Build agents as graphs. Loops, memory, human approval and full control of the flow.
OpenAI's own agent loop, with handoffs, guardrails and tracing built in.
Give each agent a role, a goal and a backstory, then let the crew work the task.
Scores a RAG bot's answer and its retrieval separately, so you know which half to fix.
Rails written as files between your app and its model, in a language of their own.
Long-term memory for LangGraph agents: extraction, consolidation and retrieval.
Not a framework. The standard that lets any agent plug into any tool or data source.
Type safe agents. If you already trust Pydantic for validation, this feels like home.
