Step 01
AI for SREs
Running LLMs in production with observability, cost control and security
Your LLM returned HTTP 200. And it was wrong. Learn to run AI with SRE discipline.
View bookLearning paths · ᚱ
AI in production
Ship LLMs and agents to production — safely.
For developers, SREs and platform teams: observability, cost, security and agents with clear guardrails.
Step 02
AI Agents in Practice
Build agents with tools, memory and guardrails
Build agents that get work done and know when to stop.
View bookFree resource
LLM incident runbook template
Read up to 10 pages of the book right now, here on the site, and decide at your own pace. No spam — just book content and new releases.