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 Systems · Level 3
2. Computer use: the model acts, you return a screenshot · Level 3
3. Sandboxing and Execution Environments · Level 3
4. Agent channels: one agent, many places to talk · Level 3
5. Agentic Payments: how an AI agent pays its own way · Level 3
6. Formal verification: proving software correct · Level 4
7. Automated Theorem Proving with LLM Agents: COPRA · Level 5

## Sources

These lessons draw on 13 sources. The most used:

- [Cloudflare Workers AI, Agents, AI Gateway and Vectorize](https://developers.cloudflare.com/workers-ai/)
- [Advanced LLM Agents MOOC, Spring 2025](https://www.youtube.com/playlist?list=PLS01nW3RtgorL3AW8REU9nGkzhvtn6Egn)
- [OpenAI Agents SDK (Python)](https://github.com/openai/openai-agents-python)
- [Claude Docs — Tool Use and Agent Tools](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview)
- [Claude Quickstarts](https://github.com/anthropics/claude-quickstarts)
- [GPU MODE lectures](https://www.youtube.com/@GPUMODE/videos)
- [Lovable documentation](https://docs.lovable.dev/)
- [A practical guide to building agents](https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf)

[All units in Learn to use AI](https://rabbithole.pro/courses/learn-ai)

Source page: https://rabbithole.pro/courses/learn-ai/going-deeper-agents-at-work