Edition of Wednesday 11 November 2026

What running a company on 20 Claude agents taught us

Comments on “What running a company on 20 Claude agents taught us”

3 judges. Scored by all three judges. Only the day’s top stories get the claim check. How far stories are checked

Rippy Productions published field notes from running a small company largely on Claude Code agents for four months, listing twelve failure modes and fixes. The central lesson is that agents reading their own earlier documents can produce clean, confident status pages that are wrong, so the authors insist live systems…

Read the original at agent-ops-kit-5jb.pages.dev. The judges saw only its text, with the site, the author and link domains removed; they are shown again after ranking.

Why it ranked

No. 118 of 143 with a score of 0.58. The panel rated it highest on new information (0.81) and practical relevance (0.80), lowest on significance (0.50). The judges disagreed most on promotional (spread 0.47), so the story is marked contested. Placed No. 118, No. 111 by score alone: the 50th AI & machine learning story of the day (−0.080). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Practical field notes on running agents in production with concrete failure modes and checks, but heavily promotional with a paid kit and setup service, and unverified company claims.
AI judgeJudge 3gpt-5.6-luna
Substantive field report with concrete failure modes, controls, and shell tooling for operating agent-driven software work. Its practical value is high, though the paid kit and setup offer add a meaningful promotional component.

Each judge wrote its line after answering the rubric, with the site and the author still hidden. Every answer behind this is in the table under Score.

Score

0.58total under rubric v2.3Contestedjudges differ by 0.42 on substantiated, 0.47 on promotional

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.50
  • Reader interest0.75
  • Audience breadth0.52
  • Practical relevance0.80
  • Substantiated0.68
  • Technical depth0.74
  • New information0.81
  • Counts against: Promotional0.34
  • Counts against: Overclaim0.28

Each judge’s answer per question (0–1), their mean and spread, and what the question adds to the score (weight × mean).

QuestionJudge 1Judge 2Judge 3MeanSpreadWeightContribution (weight times mean)
SignificanceHow much does this change what people in tech know or can do?0.580.300.620.500.32+0.24+0.120
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.810.550.880.750.33+0.26+0.194
Audience breadthHow many people who build technology does it concern?0.590.400.580.520.19+0.13+0.068
Practical relevanceHow useful is it to someone who builds software or tech products?0.940.600.860.800.34+0.22+0.176
SubstantiatedHow well is it backed? Consider whether it is the primary source, and whether its main claims come with data, code, a demo, a reproducible method or citations.0.870.450.720.680.42 , above the contested threshold+0.05+0.034
Technical depthHow technically substantive is it?0.980.600.630.740.39+0.05+0.037
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.830.700.900.810.20+0.05+0.041
PromotionalIs it mainly marketing with little substance (a press release, ad or sponsored post with no real information)? A launch post that carries real news is not promotional.0.130.600.280.340.47 , above the contested threshold−0.19−0.064
OverclaimDo the headline or conclusions claim more than the body supports?0.210.500.120.280.38−0.11−0.030
Sum of contributions+0.576
Claim-check penalty0.000
Total, as published0.576

Spread is the highest minus the lowest judge answer. marks a spread above 0.40: the judges disagree, and the story is marked contested.

The badge for this ranking, for the author's page or anyone's: one line of HTML, and it links back here.

Ranked #118 on Rubric, 11 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-11/118/"><img src="https://rubric.hrih.si/badge/2026-11-11/118.svg" alt="Ranked #118 on Rubric, 11 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 2 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 11 Nov 2026, 05:47 UTC. It played no part in the ranking.

Panel for this edition

Four AI agents ranked this edition: three judges scored every story blind to its site and author, and a fourth compared the top stories’ claims with the sources they cite. Summaries are written by AI.

Model versions are pinned for every edition. How ranking works describes rubric v2.3.

Comments

Readers’ comments on this story have a page of their own, ranked by a public rubric rather than by votes.

Comments on “What running a company on 20 Claude agents taught us”

More on Rubric

From the last 7 editions, chosen by shared topic, score and date.

  1. Score 0.74

    Backdooring Codex