Skip to content

root / tags / linkedin-pulse

#LinkedIn Pulse

2 fiches

Quality & Security Auto-verified translation

I built a marketing AI operating system for a 60-person team. The most valuable thing in it is the part that refuses to write.

Experience report published on **LinkedIn Pulse** on **August 12, 2026** by **Guillaume Dumortier**, in his newsletter *Growth Marketing Fit*, subtitled *« Four layers, a lot of rebuilding, and the failure modes nobody warns you about »*, ~2,500 words. The subject: an internal AI system built **in Claude** for a marketing team of about sixty people — roughly thirty content and sales **skills**, a dozen **source-of-truth modules**, **seven agents, six of which exist only to check work rather than produce it**, a **plugin** for those who live in a terminal, a **browser application** carrying the same knowledge for everyone else, and an orchestration that chains three or four assets into a *campaign bundle*. The thesis is set out early: the quality of an AI output is not determined at the moment of generation, but by what the system knows before it starts and by what happens to the draft afterward — *« The generation step in the middle is the easy part. It's also the only part most teams have built. »* Hence four layers: **Truth** (almost nobody builds it), **Production** (everybody), **Verification** (almost nobody), **Internal distribution** (*« where good systems die of neglect »*). Two failure mechanisms carry the article. **(A) The verifier's bare closed-world « pass »**: a fact-checker backed by product documentation receives a draft containing a claim about another product, one its sources did not cover — it returns a *« pass »*, not because the claim was true but because nothing contradicted it. *« It didn't just miss the error, it certified it. »* Fix: forbid a bare verdict and require every report to declare its **own coverage** — how many claims were checked, how many matched to sources, which fell outside its jurisdiction, which were owned by no source. *« "I can't verify this" became a first-class result. »* **(B) The cross-asset contradiction**: two assets can each be individually correct, each traceable to a real source, and still contradict each other — the press release states one date, the blog post another, both pass, the bundle can't ship. *« Per-asset verification can't catch that, by construction. »* Article's closing clause: *« The generation is free. The trust is the product. »*

#Guillaume Dumortier#Growth Marketing Fit#LinkedIn Pulse

**Guillaume Dumortier** — auteur de la newsletter LinkedIn **Growth Marketing Fit** (~1 300 abonnés à la publication). Il écrit en **praticien-constructeur** : il a passé *« une longue partie de cette année »* à bâtir et exploiter le système décrit. La légende de l'illustration précise le socle technique — *« A custom-built Marketing AI OS within Claude »*. Publié le **12 août 2026**.

Transformation & Adoption Auto-verified translation

A Year With Claude Code: My Output Doubled. My Attention Span Didn't.

LinkedIn Pulse op-ed by Alexandre Frizzo after a year of daily use of Claude Code, offering a **nuanced assessment** rare in the 2026 corpus — productivity **multiplied by 3-5×** in his case (consistent with Wescale, and in line with the median of committed practitioners; the elite tail goes much higher, cf. Cherny *few dozen PRs/day + 150 PRs record* and Karpathy *"peaks much higher than 10×"*), but **hidden cognitive costs** acknowledged. Pivot thesis: ***"the new bottleneck is supervision"*** — the job has changed shape, one no longer *writes* code, one *decides* about code generated by agents. Gains: 3-5× output, previously infeasible projects now achievable (yak-shaving, boilerplate), near-zero cost of experimentation. Acknowledged losses: ***"writing muscle"*** atrophied (manual code now feels *effortful*), **rare deep flow state** (constant context-switching between supervisions), **diminished ownership satisfaction** (*"code is good, but isn't quite mine"*). Unresolved tensions: **FOMO** (*"every hour I'm not at the keyboard is an hour an agent could be earning for me"*), **review quality** at 3-5× volume, **skill atrophy**. Statistics cited: median 3-4h effective coding out of an 8h day, **23 min** context recovery per interruption (Gloria Mark study), 15-25 min flow entry, 500% productivity in flow (McKinsey). Exemplary epistemic position: simultaneously rejects the *"AI is bad"* narrative and uncritical enthusiasm. A welcome counterweight to Cherny's *"coding is solved"* (2026-05).

#Alexandre Frizzo#LinkedIn Pulse#year with Claude Code

Alexandre Frizzo (auteur LinkedIn Pulse, identité tech non précisée par le post au-delà du nom — auteur d'une tribune one-year retrospective Claude Code).