Writing
Research and field notes
Deep dives, threat analysis, and notes from the work - mostly on AI and agent security, sometimes on whatever is breaking this week.
All4+1 ArchitectureAccess ControlAI AgentsAI Safety ResearchArchitecture DiagramsAssuranceC4 ModelCybersecurityDetection EngineeringDocumentationEnterprise ArchitectureEvaluationHardware SecurityHome LabIdentityIndustrial SecurityIntegrityKruchtenLoggingMemoryMicrosoft EntraMSPPerformancePythonReproducibilitySecurity ArchitectureSQLSystem ArchitectureTenancyThreat HuntingTOGAFToolsUpdatesZachman FrameworkZero Trust
Latest
Choosing an AI Agent Memory Service: Security and Performance Tradeoffs
A memory-service decision method with a small local SQLite experiment, tenant checks, deletion limits, and latency measurements.
September 9, 20265 min readAI Systems
Read note
September 9, 20265 min read
How to Evaluate Tools for Securing Production AI Agents
An evaluation method that follows identity, authority, approval, and failure behavior through a real agent workflow.
AI AgentsSecurity ArchitectureEvaluation
September 9, 20265 min read
Tamper-Evident AI Agent Logs: Integrity, Gaps, and Limits
A runnable local log-chain experiment covering edits, deletion, replay, truncation, drops, restarts, and signer compromise.
AI AgentsLoggingIntegrity
September 9, 20264 min read
What AI Agent Assurance Claims Actually Cover
How to read an agent assurance claim through its scope, assessor, test version, and renewal conditions.
AI AgentsAssuranceAccess Control