notebook / reading paths
Start with a question, not a date.
These collections put related notes in a useful order. Each one begins with the foundation and moves toward implementation or evidence.
Agent Evaluation Incidents
What two rounds of testing Aria's language and image models taught me about speed, benchmarks, and knowing when a score is wrong.
Read in order →6 notesAgent Security Foundations
Anthropic's framework connects agent identity, least agency, tool boundaries, memory integrity, and recovery into one practical security model.
Read in order →5 notesAISecOps Frameworks
NIST AI RMF gives an AI security program its operating model: govern the work, map the context, measure the risk, and manage what happens next.
Read in order →7 notesDetection Contracts
A hidden pull-request comment turned legitimate MCP calls into a cross-project data path. Detecting it requires source, identity, scope, sequence, and sink.
Read in order →