CodeCrux / Field notes
149 insights / and countingPractical thinking on the systems, controls and trade-offs that make AI useful in production.
AIML
Learn how to detect, constrain, and monitor autonomous AI agents using Wiz, Zenity, and CrowdStrike with a practical, policy-first lab approach.
Read the latest insight
A comprehensive tutorial covering deploy ai agent security infrastructure on kubernetes: policy gateway, mtls sidecars, and audit si...
Read insight
Learn how to replay multi-step tool attack data from Kaggle as a labeled regression suite that catches agent tool abuse before produ...
Read insight
Learn the five key principles of AI agent security and implement each control in a reference MCP server, with policy checks, approva...
Read insight
Learn how to sandbox code-executing AI agents with container isolation, seccomp profiles, and egress allowlists, plus policy, identi...
Read insight
Learn how to contain an AI agent security incident with kill switches, token revocation, and blast-radius limits you can implement t...
Read insight
A comprehensive tutorial covering detecting anomalous agent behavior at runtime: build a baseline, trace, and alerting pipeline. Pra...
Read insight
Learn how to protect persistent agent memory from poisoning attacks using sanitization, cryptographic signing, and audit trails, wit...
Read insight
Map the AI agent security architecture attack surface and defense layers, then implement mutual authentication and scoped capability...
Read insight
Answer the question of which of the following is a key principle for AI agent security, then design deny, allow, and step-up policie...
Read insight
A comprehensive tutorial covering ai agent security reports and news: separate real incidents from marketing claims. Practical examp...
Read insight
Learn how to secure AI agents with a governed gateway: map the attack surface, enforce least privilege, and add approval checkpoints...
Read insight
Learn how to earn and demonstrate AI agent security competence as a security engineer — attack surfaces, practical controls, labs, a...
Read insight
A hands-on guide to AI agent security research papers, GitHub projects, and controls that map the agent attack surface and build a g...
Read insight
Learn how to detect, investigate, and respond to an AI agent security incident, with practical controls, audit evidence, and step-by...
Read insight
Learn how to evaluate AI agent security vendors with a practical framework that maps the agent attack surface, enforces least privil...
Read insight
Learn a practical framework for Microsoft AI agent security: least-privilege access policies, delegated identity, and human approval...
Read insight
A hands-on guide to aws ai agent security covering agent identity, scoped tool access, credential gating, approval checkpoints, and ...
Read insight
Compare identity patterns for AI agents and see what's different about Auth0's approach to AI agent security, from delegated tokens ...
Read insightHave a production AI problem?
Talk to an AI architect about the workflow, the constraints and the path from prototype to production.
