Agent Teams and claude-swarm
2026-02-08
Part 2 of the Oracles, Traces, Triage series. On running multiple agents in parallel through git, with no orchestrator and no message passing, and why the pattern matters more than the tool.
2026-02-08
Part 2 of the Oracles, Traces, Triage series. On running multiple agents in parallel through git, with no orchestrator and no message passing, and why the pattern matters more than the tool.2026-02-01
Part 1 of the Oracles, Traces, Triage series. On structuring .claude/ directories so the model adapts from norms instead of following stale scripts, and a Rust tool to enforce it.2026-01-31
Anthropic's recent work shows how far property-based testing can go when you can express properties at a function boundary. This follow-up argues that consensus clients need model-based, stateful testing to catch failures that only appear across sequences of events.2026-01-25
A series on agentic testing in 2026: how to build bug-finding systems that work because the oracles are real, traces are exercised, and findings are triaged.2025-03-25
Part of the Model-Based Stateful Testing with madhouse-rs series, concluding with real-world lessons from building a trait-based testing framework that scales from dozens to hundreds of test operations.2025-03-10
Part of the Model-Based Stateful Testing with madhouse-rs series, applying madhouse-rs to reproduce a real production bug in the Stacks blockchain that traditional testing couldn't catch.2025-02-10
Part of the Model-Based Stateful Testing with madhouse-rs series, showing how madhouse-rs uses a trait-based design to escape the enum bottleneck.