Post by **Rachel Laycock**, CTO of **Thoughtworks**, published on **September 2, 2026** on *Rachel's Ramblings*, the martinfowler.com section she runs, roughly **8,000 characters**. The text is a **deliberate response** to [[houck-dx-what-are-code-reviews-for-2026-08-05]], following a public disagreement between the two authors on a **Code Remix** panel hosted by **Moderne**. Laycock accepts Houck's quantified diagnosis (+**106%** lines per diff at **Meta**, +**64%** median PR size on the DX side) and the list of non-defect-finding functions of review, then shifts the question: *« why are we waiting until code review to do all of those things? »* (A) The guiding principle is the shortening of feedback loops learned at Thoughtworks — if feedback has value, don't remove it, move it closer to the decision it informs. Each function attributed to review is reassigned upstream: exploring alternatives before implementation, knowledge transfer through **pair programming**, collective ownership through **mob programming** and team design sessions, architectural alignment through shared design followed by **fitness functions**, and automation of everything deterministic — *« We really shouldn't still be arguing about whitespace in 2026. »* (B) Exception-based review replaces systematic review: a fundamental architectural change, a sensitive security boundary, a large blast radius, an unfamiliar area of a critical system, or simply a team's declared lack of confidence. (1) Automating review with an agent that mimics the human reviewer is dismissed as *« automating the ceremony rather than questioning why the ceremony exists »*. (2) Houck's cognitive debt is acknowledged as real, but the mandatory PR is judged a weak defense: *« We need engineers to understand systems, not diffs. »*
#code review#exception-based review#pull request
Rachel Laycock · CTO de Thoughtworks · sur *Rachel's Ramblings* (martinfowler.com).
**Boris Cherny** (Creator & Head of Claude Code @Anthropic) publishes a framework table on LinkedIn, **« Steps of AI Adoption »**, mapping an engineering team's adoption of agentic AI across **5 stages (0→4)**, each characterized by an **order of magnitude of agents driven** and a **transformation of the engineer's role**: **0 Gated** (0 agents, locked-down access), **1 Assisted** (~1 agent — "you + one agent", supervised pair programming), **2 Parallel** (~10 agents — **orchestrator**), **3 Supervised autonomy** (~100 agents — **manager of managers**, an org tree), **4 AI-native** (~1,000+ agents — **VP steering by intent**). The table crosses five columns: number of agents, *what it looks like*, *the bottleneck*, *the products that help*, *the guardrails*. **Central thesis**: consuming more tokens does not move you up a level — advancing to the next stage requires **identifying and breaking the next bottleneck** AND **building the next set of guardrails**. Concretely: giving Claude a trustworthy **self-verification loop** (tests + build + lint + e2e on a real environment), enabling **Auto mode** (avoiding blocking permission prompts), making **code review and security review the default**, adopting multi-agent interfaces (Agent view CLI, Desktop, iOS/Android apps, Tag), then `/loop`, `/batch`, `/goal`, **dynamic workflows** and **worktree isolation** for subagents. On steering: usage (dashboard) measures **activity, not return**; the right question is *"would we have spent engineering effort on this anyway? if so, how many manual engineer-hours would it have cost?"* — that's the ROI. The real payoff arrives when **fixing and maintaining happens in the background** and teams focus on *building*. Anthropic sits at **stage 3, heading toward 4**; Boris Cherny states he has personally reached **level 4**.
#Boris Cherny#Claude Code#Anthropic
Boris Cherny (Creator & Head of Claude Code @Anthropic)
Thoughtworks retreat on the future of software development with LLMs — reflections on organizational impact, cognitive debt, and supervised programming