Edition of Saturday 14 November 2026

Building Always-On Agents

Comments on “Building Always-On Agents”

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

A post from Anthropic's engineering team explains how always-on agents differ from ordinary agents: they run the same core loop, but are wrapped in architecture that controls when they wake, what persists between runs, and how results reach users.

Read the original at claude.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. 39 of 123 with a score of 0.66. The panel rated it highest on practical relevance (0.86) and technical depth (0.78), lowest on substantiated (0.48). Placed No. 39, No. 21 by score alone: the 13th AI & machine learning story of the day (−0.080), and close to “Designing an Always-On Agent”, No. 24 on Monday 9 November 2026 (−0.012). The placement terms move stories; they are not part of the score.

AI judgeJudge 2claude-haiku-5-5
Practical architecture guide for building always-on AI agents with concrete primitives (inbox, timers, memory, permissions, outbox). Useful for builders, though largely a design-pattern write-up with limited empirical evidence and some vendor promotion.
AI judgeJudge 3gpt-5.6-luna
A detailed, actionable architecture for durable proactive agents, covering eventing, scheduling, memory, permissions, context, and delivery. It is somewhat vendor-referential but offers substantial general engineering guidance and little unsupported hype.

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

0.66total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.58
  • Reader interest0.76
  • Audience breadth0.65
  • Practical relevance0.86
  • Substantiated0.48
  • Technical depth0.78
  • New information0.76
  • Counts against: Promotional0.21
  • Counts against: Overclaim0.15

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?0.670.400.680.580.28+0.24+0.140
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.730.700.860.760.16+0.26+0.198
Audience breadthHow many people who build technology does it concern?0.640.600.720.650.12+0.13+0.085
Practical relevanceHow useful is it to someone who builds software or tech products?0.950.800.830.860.15+0.22+0.190
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.0.380.350.700.480.35+0.05+0.024
Technical depthHow technically substantive is it?0.880.750.720.780.16+0.05+0.039
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.760.700.820.760.12+0.05+0.038
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.0.100.250.280.210.18−0.19−0.040
OverclaimDo the headline or conclusions claim more than the body supports?0.160.200.080.150.12−0.11−0.016
Sum of contributions+0.658
Claim-check penalty0.000
Total, as published0.658

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 #39 on Rubric, 14 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-14/39/"><img src="https://rubric.hrih.si/badge/2026-11-14/39.svg" alt="Ranked #39 on Rubric, 14 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 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 “Building Always-On Agents”

More on Rubric

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

  1. Score 0.75

    llama.cpp v1.0