
What happened
A practitioner customizing an agent called Muse had other models review documents and design proposals, found 5 of 6 critiques off-target in one inquiry-draft review, and built a multi-stage setup where models critique separately and a Gemini judge via Vertex AI and OpenRouter rates each point.
Why it matters
Because model critiques can be hit or miss and vary by case, the author treats AI feedback as a bundle of reference opinions — anonymizing points before judging and keeping a human final call — rather than adopting suggestions directly.
Summaries like this, every morning.
The account is a detailed operational log rather than a product announcement. The author started by having a single model review documents, but found critiques could be confidently off-target, so they split review into two rounds: a first round where several models with different roles (logic check, devil's advocate, first-time reader, number audit, structure check) surface issues, and a second round where a judge model rates each point. The results across six review tasks showed wide variation: one inquiry-draft review had almost all critiques rejected, while a spec-compression review had most accepted. The author also describes practical hurdles — rate-limit errors, empty responses from reasoning models, and model availability that shifts by the minute on Vertex AI — and the fallback rules built to keep the workflow running. The overall takeaway is that AI review is treated as a set of opinions to be verified, not answers to be adopted.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
A New Yorker report by Sam Kriss says Maple, a Vermont monastery led by Soryu Forall, targets burned-out AI pr…

An Nvidia research team says feeding models entire novels is often expensive overkill; in many tests, periodic…

Positron's Cameron McCaskill said about two-thirds of AI infrastructure workloads are now inference versus one…
The writer told Muse only their height and that they wanted slim, cropped tops, then let it browse ZOZOTOWN in…

After a reader comment, the Search Console-based service 検索カルテ began attaching explicit start and end dates (f…

OpenAI published copy-ready prompts for GPT-6.2 Astra and Sol covering writing style, initiative, and coding…
