Going deeper

Going deeper: agents at work

Going deeper: agents at work is a unit of 7 lessons in Rabbithole's Learn to use AI course, at levels 3 to 5.

Lessons

1. Multi-Agent SystemsLevel 3
2. Computer use: the model acts, you return a screenshotLevel 3
3. Sandboxing and Execution EnvironmentsLevel 3
4. Agent channels: one agent, many places to talkLevel 3
5. Agentic Payments: how an AI agent pays its own wayLevel 3
6. Formal verification: proving software correctLevel 4
7. Automated Theorem Proving with LLM Agents: COPRALevel 5

Sources

These lessons draw on 13 sources. The most used:

• Cloudflare Workers AI, Agents, AI Gateway and Vectorize
• Advanced LLM Agents MOOC, Spring 2025
• OpenAI Agents SDK (Python)
• Claude Docs — Tool Use and Agent Tools
• Claude Quickstarts
• GPU MODE lectures
• Lovable documentation
• A practical guide to building agents

All units in Learn to use AI