Research

Posts are chapters. These are the programs they belong to.

The through-line is The Reliable AI Agent Stack: memory, tools, deterministic constraints, evaluation, observability, security, and human control.

1 · Memory for AI agents

Memori, architectures, retrieval, decay, identity, evaluation.

• Forging AI’s lasting memory
• Memori architecture
• Memori recursive design
• Artifact: Memori

2 · Reliable agent systems

Luffy, tool design, control planes, observability, failure modes.

• Designing CLI tools for AI agents
• Hard constraints belong in code
• Building Luffy
• Vital Few
• Artifact: Luffy
• Artifact: Vital Few

3 · AI × security

Agent attacks, fraud, identity, social engineering, behavioral security.

No public write-up in this program yet. The line is live: AI-enabled attacks, email/fraud systems, agent security, entity intelligence. New work lands here instead of as a disconnected post.

4 · AI-native software engineering

Coding agents, architecture, productivity, staff+ engineering.

• The AI-augmented developer playbook
• The Staff+ operating model
• Listen to this post