Skip to content

root / tags / prosecution

#prosecution

2 fiches

AI Coding Agents & Skills Auto-verified translation

Two Human Gates and Everything Between Is Machine-Checked

Second installment of Chris Williams's ADLC series: it unrolls the cycle that follows from the "first law" — eight phases (P0 Triage → P7 Distill), a deterministic gate between each pair, and exactly two mandatory human moments (spec approval at P1, behavioral acceptance at P6). Key principle: an LLM→LLM handoff without a deterministic checkpoint multiplies error rates; and a "barbell" cost distribution (heavy at both ends, light in the middle) that inverts agile economics.

#ADLC#eight-phase agentic cycle#deterministic gates

Chris Williams (@voodootikigod)

AI Coding Agents & Skills Auto-verified translation

Prosecution, Not Code Review

Fourth installment in the ADLC series: Williams reframes code review as adversarial "prosecution" rather than collaborative evaluation. Charter agents to refute ("find what's wrong"), deploy single-lens reviewers with fresh contexts (correctness, security, contract compliance, spec alignment, test quality), act only on verified findings (reproduced by a failing test), and loop until two consecutive passes yield zero findings. Measure calibration by planting known bugs, mutation-testing style. Exit gate: zero open findings, two dry passes, green tests, empty test diff.

#ADLC#prosecution#adversarial review

Chris Williams (@voodootikigod)