Episode "Phase 5 · Review" of the SFEIR series on the augmented SDLC, published **the same day** as the Addy Osmani LinkedIn post that it translates into a phase specification. Thesis: **quality has changed address** — it is no longer read in the code (agents produce more of it than anyone can review) but in **the ring of constraints surrounding the agent**. Osmani's ring (seven dimensions — correctness, security, performance, accessibility, maintainability, **economic efficiency**, **comprehensibility** — linked by the **back-pressure** rule: "a loop is only granted the autonomy that can be verified cheaply and reliably, not an inch more") is redrawn, translated, and attached to phase 5 of SFEIR's 11-phase cycle. The structuring corollary: **the bottleneck has never been generation, it is verification** — "generation is a wide mouth, verification a narrow neck; speeding up the mouth thickens the pile at the neck." **The most interesting design decision is a cycle-architecture choice**: Review is deliberately **outside the three human gates** (Define, Plan, Ship), because making Review the gate would put human attention — a finite resource — as the control point of a generation capacity that itself scales: "you would have built a pipeline whose maximum throughput is the number of diffs a senior can read before the end of the day." Hence the split: **Review instruments, Ship decides** — Review delivers an *opposable body of evidence*, Ship decides on the evidence, not on the full diff. A position staked against Monperrus (from whom SFEIR retains the diagnosis — human inspection of every diff cannot withstand agentic speed — but rejects the conclusion: acceptance cannot be delegated). The named trap is **circular validation** (the agent that writes the code writes the tests that validate it: "you built a mirror, not a ring"), with five countermeasures drawn from Anthropic (independent gates in separate context windows, deterministic + agentic never substituting for one another, shadow mode, risk-based tiering, logging to the SIEM) and Compare the Market's warning (**AST graph ~70% vs vector RAG ~58%**, with RAG performing *worse than no context at all*). The firm's own extension is **the ratchet**: "every escape becomes a constraint" — a defect that has crossed the ring is closed *within the ring* (test, lint rule, review rubric, harness guardrail) at Compound-1, "the only asset in the chain that appreciates while the models depreciate" (an unaudited internal measurement: **−30% fix iterations after ten cycles**). It closes by reformulating the question: "is this code good?" has become unanswerable; what remains is **"what does my system refuse to let through?"**
#ring of constraints#constraints around agents#Review phase
SFEIR (voix éditoriale du cabinet, article non signé individuellement) — construit sur Addy Osmani (Google) ; cite Martin Monperrus · Paula Hingel (Augment Code) · DORA/Google Cloud · Jason Clinton (Anthropic) · l'équipe Engineering de Compare the Market
SFEIR analysis (firm's voice) of the general availability, on July 9, 2026, of **GPT-5.6** by OpenAI — not a single model but a **family of three tiers**: **Sol** (long-horizon/cyber/science flagship, the only one to unlock the "max" and "ultra" modes), **Terra** (everyday balanced tier, ~half the price of GPT-5.5), and **Luna** (fast/economical, high volume). All three share ~**1.05M tokens** of context, **128k** output tokens, and a knowledge cutoff of **February 16, 2026**. The most structuring fact is not a score but an **aggressive pricing grid** (Sol $5/$30, Terra $2.50/$15, Luna $1/$6 per million tokens): Sol keeps the previous flagship's price while being more capable, forcing the comparison onto the **capability-to-cost ratio**. Two billing subtleties (cache writes billed at **1.25×**, a surcharge beyond **272k** tokens) make the grid misleading until one has measured how much context the agent re-reads (read/write ratio ~**153:1** in agentic coding). Engineer's verdict, claimed to be neutral (SFEIR is both a **Google Cloud Premier** partner *and* an **Anthropic** partner): **no one sweeps every table** — GPT-5.6 dominates Terminal-Bench 2.1 and the Coding Agent Index (at a third of the cost per task), Claude stays ahead on SWE-Bench Pro (~15 pts); METR flagged a record **reward hacking** rate on Sol. Conclusion: "stop looking for the champion, learn to route" — the model is a commodity, the durable advantage lies in **Context/Harness Engineering**.
First-rate technical account by **Jarred Sumner**, creator of **Bun** (JS/TS runtime, >22M downloads/month), on the **complete rewrite of Bun from Zig to Rust in 11 days** (May 3→14, 2026) driven by **Claude** — an exceptional case study in AI-assisted software engineering **at industrial scale**. Motivation: a recurring class of bugs (use-after-free, double-free, leaks) arising from the mix of GC-managed memory (JavaScriptCore) and manual memory (Zig); in **safe Rust**, these bugs become **compile errors** with automatic cleanup (`Drop`/RAII) — "a better feedback loop than a style guide." Rejecting the dogma that "a rewrite is always a bad idea" (a year of bugfix freeze for 3 engineers), Sumner chooses a **mechanical port** (preserve the architecture, minimal behavior change) validated by the **existing test suite, written in TypeScript and therefore language-independent** (60,624 tests, 1.39M `expect()` assertions, 0 tests removed, 6 platforms). The harness: **~50 dynamic workflows** in **Claude Code**, *write → 2+ adversarial reviewers → apply* loops, up to **64 Claude instances in parallel** (4 worktrees × 16), with **PORTING.md** + **LIFETIMES.tsv** generated in preparation. Numbers: **6,502 commits** (peak 695/h, 58/min, ~1,300 lines/min), final diff **+1,009,272 lines**, ~16,000 compile errors treated as a queue, **5.9B uncached input tokens + 690M output ≈ $165,000**. Key methodological levers: **adversarial review** (a second Claude, separate context, sees only the diff, tasked with finding why it's wrong — catches subtle bugs that are *semantically* different but *syntactically* identical) and the principle **"fix the process that generates the code, not the code by hand."** Model used: a pre-release of **Claude Fable 5** (Mythos class). Since the merge: **11 rounds of Claude Code security review**, 24/7 coverage-guided fuzzing (100B executions → ~15 PRs), **4% `unsafe` code** (78% on a single line), **19** known regressions fixed. In production: Claude Code v2.1.181, the first release on Bun-in-Rust, **+10% faster startup on Linux**. Disclosed upfront: **Bun was acquired by Anthropic in December 2025**.
#Bun#Jarred Sumner#Zig-to-Rust rewrite
Jarred Sumner (créateur de Bun ; travaille chez Anthropic depuis le rachat de Bun en décembre 2025)
In-depth technical guide (Lushbinary agency blog) on **Loop Engineering**: designing the systems that drive coding agents in a loop, rather than prompting them manually. Covers the lineage prompt → context → loop engineering, the Ralph technique (Geoffrey Huntley), the **five building blocks + memory** of a loop, their implementation in Claude Code and OpenAI Codex, writing verifiable stop conditions, an adoption maturity scale, and the risks that worsen as loops grow more sophisticated. Domain: agentic software engineering, coding agents, harness/orchestration.
Televised debate on BFM Business (*Tech & Co Business* program, "The Debate" segment, 17 minutes) with **Rémi Jacquet** (CEO of Cast Software France, founder in 2023 of a think tank of about a hundred CIOs on the impact of generative AI on development, partnership with Cigref / Epita) and **Didier Girard** (CTO and CEO of **SFEIR**, a French IT services company (ESN) of about 1,000 people). Strong theses: *"writing code has become an anti-pattern"* (Girard), AI produces code of higher quality than most engineers and is *"2 to 10× more efficient"* — this is a reality, but the profession is not disappearing. The developer becomes a **conductor / agent manager / arbiter**, 14-day sprints are replaced by one-hour to half-day ***bolts***, the **Pizza Team** (8-10 people) no longer works in the agentic era, a new role is emerging — the ***product engineer*** —, the lifespan of a skill drops from **10 years to 1 year**, and **token** consumption becomes the *fuel* of value creation (NVIDIA anecdote allegedly paying bonuses in tokens, taxi driver metaphor for a driver who doesn't consume gas). SFEIR claims *"1,000 people, production capacity of 10,000"*. On the Cast side: positioning on ***harness engineering*** (deterministic vs probabilistic AI, control and guardrails), aligned with Sylvain Duranton's (BCG X) op-ed in *Les Échos* stating that *"an agent = an LLM + harnesses"*. Historical pivot: 2024 *prompt engineering* → 2025 *context engineering* → 2026 *harness engineering*. Key warning: *"the stronger AI becomes, the more we let our guard down — the more risks there are"* (Jacquet). Pivotal role of HR in the transformation, complete overhaul of the SDLC, recommendation to juniors to solidify software architecture fundamentals (*"code is the score, you need to master the symphony"*).
Google whitepaper (the "Day 1" installment of a series, by Addy Osmani, Shubham Saboo and Sokratis Kartakis) mapping the transformation of the software development lifecycle (SDLC) in the age of coding agents. Thesis: the fundamental shift is not a new language but the move from writing code to **expressing intent**. The document sets out a spectrum ranging from *vibe coding* (prompting and accepting) to *agentic engineering* (AI implements under constraints, tests, and feedback loops designed by humans), with **context engineering** as the central skill, the **software factory** model (the developer's deliverable = the system that produces the code), **harness engineering** (Agent = Model + Harness), and a CapEx/OpEx economic analysis of total cost of ownership.
Synthesis by Addy Osmani (Google, Chrome/Cloud) of the emerging field of *harness engineering*: the equation `agent = model + harness`, the *ratchet* principle ("every mistake becomes a rule"), the HumanLayer "skill issue" reframe, Terminal Bench evidence (Top 30 → Top 5 from a harness change alone), the layered Claude Code architecture, Anthropic's "harnesses don't shrink, they move" vision, and Harness-as-a-Service (Claude Agent SDK, Codex SDK, OpenAI Agents SDK). Pivot article that consolidates Trivedy, HumanLayer, Anthropic, and Böckeler into a doctrine.
#harness engineering#agent harness#Addy Osmani
Addy Osmani (Software Engineer at Google, Cloud + Gemini)