An agent is a model plus tools (reading files, running commands, searching the web) plus a loop.

In depth: 00 · ABC: six words before you start → “6. Agent”

Related: agent · MCP

Appears in

• 00 · Kickstart: Map of tools · The Source or the Packaging
• 01 · Introduction: Your experience with AI · Your first prompt
• 02 · Setup: Environment check · Installing the tools
• 03 · Stack selection: What are your constraints? · Matrix of 4 stacks · Behind a censorship firewall: no VPN · Migration plan for your workflow
• 05 · Context & Memory: Tune your memory
• 06 · Automation Pipeline: The info you process by hand · Trigger → Action model · Build your pipeline · What to automate next?
• 07 · Tools & Extensions: What's Claude Code missing? · MCP: superpowers through a protocol · Hooks: event automation · Pendel: your agent audits your project
• 08 · Agent Engineering: When Prompts Stop Working · Jagged Intelligence: What to Delegate · Orchestration: Gmail Agent as a Case · Prototype → Production · Design Your Clone · Agent SDK: the Agent as a Library
• 09 · AI Notebook: A notebook in 15 minutes · How it works · Where it lies · Output formats · Practice
• 10 · Model Training: What's inside a model · Fine-tuning: when and how · Practice: fine-tune a small model
• 11 · Second Brain: A channel: your agent within reach

The course is free — start on the site →

Write to the author: Telegram · LinkedIn

checked against the course: 2026-11-02 · 664b147