Edition of Saturday 21 November 2026

Apple is building an AI agent

Comments on “Apple is building an AI agent”

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

Apple is reportedly building its own AI agent capable of browsing the web, working across apps, writing code, and calling services, according to a job listing first spotted by Bloomberg and later removed.

Read the original at theverge.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. 100 of 118 with a score of 0.57. The panel rated it highest on new information (0.80) and reader interest (0.70), lowest on technical depth (0.30). Placed No. 100, No. 98 by score alone: the 37th 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
Reports Apple building an agentic AI assistant via a job listing and Bloomberg reporting. Relevant to AI product builders, but mostly a news report on plans with thin technical detail and limited substantiation.
AI judgeJudge 3gpt-5.6-luna
A timely report of Apple pursuing cross-app agent capabilities, supported by a job listing and related Siri plans. It matters broadly to AI and product builders, but offers little technical detail and relies mainly on secondary reporting.

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

0.57total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.61
  • Reader interest0.70
  • Audience breadth0.70
  • Practical relevance0.50
  • Substantiated0.42
  • Technical depth0.30
  • New information0.80
  • Counts against: Promotional0.09
  • Counts against: Overclaim0.18

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?0.640.500.680.610.18+0.24+0.146
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.540.750.820.700.28+0.26+0.183
Audience breadthHow many people who build technology does it concern?0.610.670.820.700.21+0.13+0.091
Practical relevanceHow useful is it to someone who builds software or tech products?0.530.400.570.500.17+0.22+0.110
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.0.390.300.580.420.28+0.05+0.021
Technical depthHow technically substantive is it?0.460.150.280.300.31+0.05+0.015
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.790.700.910.800.21+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.0.140.050.080.090.09−0.19−0.017
OverclaimDo the headline or conclusions claim more than the body supports?0.230.200.120.180.11−0.11−0.020
Sum of contributions+0.568
Claim-check penalty0.000
Total, as published0.568

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 #100 on Rubric, 21 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-21/100/"><img src="https://rubric.hrih.si/badge/2026-11-21/100.svg" alt="Ranked #100 on Rubric, 21 Nov 2026" width="252" height="28"></a>

Also covered by

Elsewhere

Elsewhere: HN 19 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 “Apple is building an AI agent”

More on Rubric

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