// learn · free, always

The fundamentals.

A practical path from “what is an LLM?” to working safely and effectively with AI agents. Follow the sequence, or open the lesson you need.

12 lessons · first principles · no assumed expertise

// the sequence

Learn what is happening under the surface.

Each lesson adds one layer: the model, the agent loop, its reach, your safeguards, and the habits that make the work reliable.

  1. 01
    What an LLM is — and isn't

    Tokens, context, training, inference, and why fluent answers can still be wrong.

  2. 02
    What makes an LLM an agent

    The working loop: goal, context, action, tool result, revision, verification, and stop.

  3. 03
    Your first supervised task

    Start small, set boundaries, watch the work, inspect the result, and keep control.

  4. 04
    Files, commands, tools & external actions

    Classify what an agent can touch by mutation, scope, destination, privilege, and reversibility.

  5. 05
    Permissions, secrets & prompt injection

    How sandboxes and approval modes work, what read access can expose, and when to stop.

  6. 06
    How to give a good task

    Turn intent into a usable brief: goal, context, constraints, definition of done, and evidence.

  7. 07
    Review, test & verify

    Separate a successful command from a correct result using diffs, tests, and acceptance criteria.

  8. 08
    Git, gently

    Commits, branches, diffs, and recovery as a safety system for agent-assisted work.

  9. 09
    CLAUDE.md & AGENTS.md

    Persistent instruction files, their scope and precedence, and why they guide rather than guarantee behavior.

  10. 10
    Skills, plugins & MCP

    Reusable workflows and outside integrations—including the trust boundary each one adds.

  11. 11
    Cloud vs. local

    Where models and tools run, what data moves, and the tradeoffs among privacy, cost, speed, and capability.

  12. 12
    Limits, model choice & evaluation

    Choose by task and evidence, expect uncertainty, and build repeatable checks for quality.

// after the foundations

Learn with people who are applying it.

Join The Ascent