Skip to content
Agentic AI for serious engineers

Build agents that survive contact with reality.

Earn the complexity

Start → Read the book See the evidence
0pp
Workflow > Agent
0×
Cost ratio
0×
Latency
Part I

Build

Tools, loops, multi-agent without theater.

4 chapters →
Part II

Judge

Eval, oversight, when not to use agents.

3 chapters →
Part III

Operate

Deploy, govern, secure, remember.

6 chapters →
What's new
See all →
Anthropic just told you the harness is the product banner
FN-003 · Field Note

Anthropic just told you the harness is the product

 Multi-agent vs router on 100 customer-support queries banner
LAB-001 · Lab

Multi-agent vs router on 100 customer-support queries

 Your eval rubric needs failure buckets, not just scores banner
FN-002 · Field Note

Your eval rubric needs failure buckets, not just scores
"Most agents are workflows in costume. Earn the complexity."
Read the manifesto →
Try the agent · pre-recorded sessions
Loading sample sessions…