Arjun Virk
arjunvirk.com · 9,531 words · saved by 2 readers
Personal website of Arjun Virk
ML Bible · Chapter 7 Agentic Engineering The four levels of AI usage, then a deep tour of a real Level-4 agent (OpenClaw): the Markdown-file workspace, the anatomy of a tool call, the N×M problem and MCP, multi-agent patterns, context management, and the lethal trifecta. Good news: this chapter should be an easier read than the last few. We're stepping back from the heavy architectural machinery, attention matrices, convolutions, loss functions, and looking at how all of that gets put to work . The models we've been building are about to stop being things you talk to and start being things tha
saved by
related reading
- Building Effective AI Agents \ Anthropicanthropic.com
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- Building Effective AI Agents \ Anthropicanthropic.com
- Demystifying evals for AI agents \ Anthropicanthropic.com
- Designing agentic loopssimonwillison.net
- What is an Agent Harness?rubriclabs.com
- The Unreasonable Effectiveness of Agentic Loopsweb.navan.dev
- Agent Evaluation: A Detailed Guidecameronrwolfe.substack.com
- How we built our multi-agent research system \ Anthropicanthropic.com
- Building reliable AI agents · parth sareenparthsareen.com
- Ampampcode.com
- What is an Agent? | Devinwindsurf.com