Edition of Saturday 14 November 2026

How I run my agent fleet to build my product

Comments on “How I run my agent fleet to build my product”

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

The post describes how a solo developer runs an "agent fleet" to build Stet.sh, a 1M+ line product that automates coding-agent evals. It separates fleets (single-engineer, experimental, org-chart style) from software factories (team-owned, repeatable pipelines), and covers the management layer, token waste from inter-agent messaging, and context rot that causes…

Read the original at stet.sh. 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. 113 of 123 with a score of 0.56. The panel rated it highest on new information (0.80) and practical relevance (0.73), lowest on significance (0.47). The judges disagreed most on significance (spread 0.42), so the story is marked contested. Placed No. 113, No. 111 by score alone: the 52nd 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 first-person account of running a multi-agent coding fleet with concrete metrics, but claims are anecdotal, unverifiable, and partly self-promotional; topic is highly relevant to AI tooling builders.
AI judgeJudge 3gpt-5.6-luna
A detailed firsthand account of operating large coding-agent fleets, with concrete coordination metrics, failure modes, reward-design examples, and practical techniques. It is somewhat self-promotional and extrapolates from one operator’s experience, but offers genuinely new, actionable information.

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

0.56total under rubric v2.3Contestedjudges differ by 0.42 on significance

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.47
  • Reader interest0.71
  • Audience breadth0.56
  • Practical relevance0.73
  • Substantiated0.57
  • Technical depth0.70
  • New information0.80
  • Counts against: Promotional0.18
  • Counts against: Overclaim0.39

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?0.590.200.620.470.42 , above the contested threshold+0.24+0.113
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.740.550.840.710.29+0.26+0.185
Audience breadthHow many people who build technology does it concern?0.660.450.580.560.21+0.13+0.073
Practical relevanceHow useful is it to someone who builds software or tech products?0.820.600.780.730.23+0.22+0.162
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.0.690.350.670.570.34+0.05+0.029
Technical depthHow technically substantive is it?0.880.500.720.700.38+0.05+0.035
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.820.700.880.800.18+0.05+0.040
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.0.100.200.240.180.14−0.19−0.034
OverclaimDo the headline or conclusions claim more than the body supports?0.300.450.420.390.15−0.11−0.043
Sum of contributions+0.559
Claim-check penalty0.000
Total, as published0.559

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 #113 on Rubric, 14 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-14/113/"><img src="https://rubric.hrih.si/badge/2026-11-14/113.svg" alt="Ranked #113 on Rubric, 14 Nov 2026" width="252" height="28"></a>

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 3 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 15 Nov 2026, 20:44 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 “How I run my agent fleet to build my product”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0