AI engineering · Available on Amazon
AI Agents in Python That You Can Trust by Kai London
Build AI agents in Python with the controls that make them dependable: bounded tools, logging, evaluation and human oversight.
What the book covers
Agent design
Planning, tools and memory without runaway behaviour.
Guardrails
Limiting what an agent is permitted to do.
Testing agents
Repeatable checks for non-deterministic systems.
Observability
Tracing what the agent did and why.
AI engineeringKai London
Who it is for
Python developers building agentic systems.
About the author
Professor Kai London — CISSP, CISM.
An internationally recognised cybersecurity executive, board advisor and Founder & CEO of Quantum AI Systems Security LLC, writing at the convergence of AI, governance and operational resilience. Honorary Professor and Researcher at UCL.