Edition of Saturday 21 November 2026

Written Agent Authorizations: 25 Instruments, Dissected for AI-Agent Design

Comments on “Written Agent Authorizations: 25 Instruments, Dissected for AI-Agent Design”

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

This 2026 paper analyzes 25 government and private authorization instruments, including California's CCPA authorized-agent rules, to derive design patterns for AI-agent delegation. Its central claim is that most hard problems in agent authorization, such as scoping, revocation, counterparty refusal and sub-delegation, already have tested answers in existing forms, usually in…

Read the original at github.com. 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. 38 of 118 with a score of 0.58. The panel rated it highest on new information (0.90) and substantiated (0.76), lowest on significance (0.51). The judges disagreed most on reader interest (spread 0.60), so the story is marked contested. Placed No. 38, No. 90 by score alone: the placement terms moved other stories past it.

AI judgeJudge 2claude-haiku-5-5
Long, document-heavy survey of legal authorization instruments mapped to AI-agent design; relevant to agent builders but broad, low-novelty as a news item, and mostly legal analysis rather than tech substance.
AI judgeJudge 3gpt-5.6-luna
A deeply researched comparative analysis translating real authorization instruments into concrete AI-agent design primitives. It is highly actionable and well sourced, though some broad convergence claims and legal-status assertions remain imperfectly verified.

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 0.52 on significance, 0.60 on reader interest, 0.47 on audience breadth, 0.53 on technical depth, 0.46 on overclaim

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.51
  • Reader interest0.60
  • Audience breadth0.56
  • Practical relevance0.70
  • Substantiated0.76
  • Technical depth0.67
  • New information0.90
  • Counts against: Promotional0.04
  • Counts against: Overclaim0.35

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?0.610.200.720.510.52 , above the contested threshold+0.24+0.122
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.610.300.900.600.60 , above the contested threshold+0.26+0.157
Audience breadthHow many people who build technology does it concern?0.720.250.720.560.47 , above the contested threshold+0.13+0.073
Practical relevanceHow useful is it to someone who builds software or tech products?0.830.450.820.700.38+0.22+0.154
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.0.830.600.840.760.24+0.05+0.038
Technical depthHow technically substantive is it?0.880.350.780.670.53 , above the contested threshold+0.05+0.034
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.930.850.930.900.08+0.05+0.045
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.0.060.050.010.040.05−0.19−0.008
OverclaimDo the headline or conclusions claim more than the body supports?0.610.150.280.350.46 , above the contested threshold−0.11−0.038
Sum of contributions+0.577
Claim-check penalty0.000
Total, as published0.577

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 #38 on Rubric, 21 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-21/38/"><img src="https://rubric.hrih.si/badge/2026-11-21/38.svg" alt="Ranked #38 on Rubric, 21 Nov 2026" width="245" 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 21 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 “Written Agent Authorizations: 25 Instruments, Dissected for AI-Agent Design”

More on Rubric

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