Testing the Bugs Between Calls
2026-02-15
Part 3 of the Oracles, Traces, Triage series. On combining agent swarms and agent skills with stateful property-based testing to find the consensus bugs that live in sequences, not single calls.
Blog
Agent Teams and claude-swarm
2026-02-08
Part 2 of the Oracles, Traces, Triage series. On running multiple agents in parallel through git—no orchestrator, no message passing—and why the pattern matters more than the tool.
Agent Skills and claude-lint
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.
The Bugs Between Calls
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.
Oracles, Traces, Triage
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.
The Expression Problem in Practice: A Trait-Based Testing Harness
2025-03-25
Part of the Expression Problem in Rust series, concluding with real-world lessons from building a trait-based testing framework that scales from dozens to hundreds of test operations.
Chaos Testing stacks-node with Model-Based Stateful Testing
2025-03-10
Part of the Expression Problem in Rust series, applying madhouse-rs to reproduce a real production bug in the Stacks blockchain that traditional testing couldn't catch.