Skip to content

All fiches — Page 6

Quality & Security Auto-verified translation

Comparing Context Retrieval Approaches for AI Code Review

Empirical study by the **Compare the Market** engineering team (Meerkat Careers, UK) evaluating four approaches to **context retrieval for AI code review**: Baseline (no additional context), **RAG** (vector search), **GKG** (GitLab Knowledge Graph, AST-based knowledge graph), and **GKG+RAG** (hybrid). Evaluation on **79 real merge requests** with **MLflow on Databricks**. Striking result: **RAG performs worse than the baseline** on almost every metric — vector noise is counterproductive for code review. **GKG outperforms RAG by +21%** in inline comments coverage (0.696 vs 0.577) through structural AST understanding (Tree-sitter + Kuzu graph database). Code requires **structural** understanding (callers, signatures, hierarchies), not mere semantic similarity. GKG costs 4× the baseline but delivers measurable improvements; RAG costs 3× with no improvement. Implemented as a **Docker sidecar** in CI/CD wrapping the GKG binary (still in GitLab beta) with a local MCP server.

#Compare the Market#Meerkat Careers#AI code review

Équipe Engineering Compare the Market (Meerkat Careers, UK — site de comparaison d'assurances et services financiers).

Transformation & Adoption Auto-verified translation

When Using AI Leads to "Brain Fry"

BCG-HBR study (Bedard, Kropp, Hsu, Karaman, Hawes, Kellerman) of 1,488 US employees, January 2026: formal definition of ***AI brain fry*** (acute cognitive fatigue linked to AI oversight), 14% of AI-using workers affected (Marketing 26%, Legal 6%), productivity peaks at 3 simultaneous tools, +33% decision fatigue / +39% major errors / +39% intent to leave among the "brain fried," empirical distinction between **burnout** (emotional, eased by AI on routine tasks -15%) and **brain fry** (acute cognitive, worsened by oversight). 5 recommendations for leaders, "AI orphan tax" (+5% fatigue when the manager expects the employee to figure it out alone), org work-life balance -28%. Pivotal academic source cited by Les Echos and the 2026 debate.

#AI brain fry#cognitive fatigue#BCG study

Julie Bedard (BCG MD & Partner) · Matthew Kropp (BCG MD & Senior Partner, CTO BCG X) · Megan Hsu (BCG Project Leader) · Olivia T. Karaman (UC Riverside / BCG) · Jason Hawes (UC Riverside / BCG) · Gabriella Rosen Kellerman (BCG Expert Partner, psychiatre, co-auteure *Tomorrowmind*)

Economy & Market Auto-verified translation

Local LLMs vs Cloud APIs: 2026 Total Cost of Ownership Analysis

Analysis of the total cost of ownership (TCO) of local LLMs versus cloud APIs in 2026. The article demonstrates that per-token pricing is a trap and that only the full TCO (hardware, electricity, cooling, labor) informs the decision. Key highlight: local/cloud break-even points fell by 40% between 2024 and 2026. Source: SitePoint (developer-focused technical media).

#TCO#total cost of ownership#local LLM

SitePoint Team

Economy & Market Auto-verified translation

Redesigning the Agency Value Model (rapport VoxComm 95 pages, mars 2026) + Billable Hours Are Dead, AI Killed Them, Here's How To Survive (MediaPost / Joe Mandese, 3 mars 2026)

**Consolidated dossier** March 2026 on the **death of the billable hours model in the advertising/communications industry** — combining the **VoxComm report** *"Redesigning the Agency Value Model"* (95 pages, March 2026, **Brian Kessman** of **Lodestar Agency Consulting** + foreword by **Tim Williams** of **Ignition Consulting Group**, intro by **Charley Stoney** President of VoxComm / CEO of **EACA European Association of Communication Agencies**) and the **MediaPost opinion article** *"Billable Hours Are Dead, AI Killed Them, Here's How To Survive"* (March 3, 2026, **Joe Mandese**, Editor-in-Chief of MediaPost). **Shared pivot thesis**: the business model of communication agencies (billable hours / labor-based compensation / service business model) is **structurally disqualified by AI**; agencies must ***"decouple revenue and profit from staffing numbers"*** (Stoney). **MediaPost figures (Mandese)**: agency margins **30% (golden age) → 10% (current average)**; creatives produce **~5× the output** for the same pay or less than 10 years ago. **Mandese's diagnosis**: *"We are defining and monetizing our value through time and effort rather than business impact"* — when agencies sell **hourly services**, they sell **commodities** vulnerable to **AI cost compression**. **Tim Williams quote**: ***"At the heart of our industry's challenges lies a simple economic truth: incentives matter. When agencies embraced the hourly rate model, they unknowingly created a structural misalignment. What agencies are rewarded for — more hours — clients are incentivized to minimize."*** Zero-sum outcome, **race to the bottom**. **Williams' pivot solution**: ***"You are not in the service business. Agencies don't sell services and capabilities, but rather solutions to business problems."*** **Mandese's 4-shift framework**: (1) Define narrow expertise areas; (2) Codify repeatable productized solutions; (3) Build teams around outcomes, not utilization; (4) Replace rate cards with value-based models (fixed fees, subscriptions, performance-based pricing). **Concrete examples**: **FIG** (decoupled pricing from staffing), **72andSunny** (modular product menus), **Monks** (single subscription combining talent + tech + improvement). **Methodological critique**: MediaPost commenters dispute the historical 30% margin figure, suggesting real figures closer to 12-15%. **VoxComm report** structured into 8 chapters: When Your Model Works Against You / Mapping Your Value Model / Case Studies / How to Pivot / How to Price / How to Plan / How to Navigate / Online Tools. **Major relevance** for the dossier: this is the **agency counterpart** of the consulting shifts (McKinsey/Sternfels 60,000 = 40,000 humans + 20,000 agents, January 2026) and SaaS shifts (Bain Rule of 40 → Rule of 30, April 2026). **Cross-cutting convergence for knowledge-intensive services**: consulting + agencies + SaaS are simultaneously shifting from *time-and-materials* to *outcome-based*. To be leveraged for agency/consultancy/marketing/communications executive committees, strategic presentations on AI transformation of services, sourcing on the 30%→10% margin figures.

#VoxComm#Redesigning the Agency Value Model#Brian Kessman

**Rapport VoxComm "Redesigning the Agency Value Model"** :

Economy & Market Auto-verified translation

FinOps for AI Overview

Official FinOps Foundation guide to AI: token economics, KPIs, caching, prompt optimization, model selection, and extension of the FinOps Framework's 14 capabilities to GenAI services - FinOps Foundation

#FinOps Foundation#token economics#cost per token

FinOps Foundation — groupe de travail (Brent Eubanks/Wayfair, James Barney/MetLife, Eric Lam/Google, Adam Richter/AWS, Rahul Kalva/Wells Fargo, JJ Sharma/KPMG, Karl Hayberg/EY, et al.)

Transformation & Adoption Auto-verified translation

Fragments: February 13

Thoughtworks retreat on the future of software development with LLMs — reflections on organizational impact, cognitive debt, and supervised programming

#LLM#software development#AI agents

Martin Fowler

AI Coding Agents & Skills Auto-verified translation

Compound Engineering: The Definitive Guide

Definitive guide to compound engineering: 7-step agentic loop (Ideate→Brainstorm→Plan→Work→Review→Polish→Compound), 40+ agent plugin, 5-stage adoption scale, 50/50 rule — Kieran Klaassen (Cora / Every) - Every Source Code

#compound engineering#AI-native philosophy#7-step loop

Kieran Klaassen (avec Claude & GPT crédités co-auteurs du guide complet)