How to record and verify AI coding-agent activity
Featured guide
A concrete, local-first workflow for capturing agent actions, binding them to repository state, signing the result, and verifying the final patch independently.
Read the guideField notes on building systems that can be inspected, tested, and trusted.
Practical guides to systems engineering, verification, and developer infrastructure. Clear enough to implement, detailed enough to stand up to scrutiny.
Designing replayable evidence for coding agents
AI agent systems
How to turn an agent session into a deterministic evidence graph that another reviewer or agent can navigate without replaying every token or trusting a transcript.
How Starknet contract source verification works
Blockchain systems
A practical explanation of how a verifier reconstructs a Cairo build, compares the resulting Starknet class, and publishes source without confusing source verification with proof verification.
Auditing agent skills and instruction files
AI agent systems
A repeatable way to inspect SKILL.md, AGENTS.md, referenced scripts, and local overrides for structural drift, unsafe capability combinations, and instructions an agent cannot actually execute.
Local-first architecture for developer tools
Local-first systems
A systems design for CLIs that keep source, prompts, credentials, and evidence on the developer's machine while still supporting reproducible automation and optional remote coordination.
How to test cross-chain bridge workflows locally
Developer infrastructure
A repeatable method for testing deposits, message propagation, proof readiness, claims, restarts, and duplicate operations across a pinned local bridge topology.
Designing evidence-bounded recommendations for an AI travel agent
AI agent systems
How to let an AI travel agent choose tools and make useful judgments while deterministic code owns evidence sufficiency, source labels, privacy, and degraded states.