Edition of Sunday 15 November 2026

What makes an agent chat feel good?

Comments on “What makes an agent chat feel good?”

Claim-checked. Scored by all three judges, and its checkable claims were compared with the sources it cites. How far stories are checked

Ouijit's Prentice Bjerkeseth sets out design rules for agent chat interfaces. A single status line should update in place and hold each phrase long enough to read, about 20 characters per second, a limit borrowed from subtitle research and Netflix. Streamed text should be paced smoothly through floor, ceiling and catch-up settings, and the whole transcript should fill top to bottom. His example timings for a 1,000-character message (15.7 s slow, 3.7 s fast) have no cited source, and several psychology citations could not be checked.

Read the original at ouijit.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. 19 of 62 with a score of 0.61. The panel rated it highest on new information (0.87) and practical relevance (0.78), lowest on significance (0.43). Placed No. 19, No. 30 by score alone: the placement terms moved other stories past it.

AI judgeJudge 2claude-haiku-5-5
Practical UX guidance for AI agent chat interfaces with cited studies on reading speed and pacing. Useful to builders of agent UIs; sources are secondary and the design claims are only partly supported by the cited research.
AI judgeJudge 3gpt-5.6-luna
A practical, evidence-cited analysis of agent-chat interaction design, with concrete pacing, status, disclosure, and scrolling recommendations. It is useful to AI product builders, though significance and technical depth are moderate rather than field-changing.

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

0.61total under rubric v2.3

Judges’ mean answer per question, on a scale from 0 to 1. Questions marked minus count against the score.
  • Significance0.43
  • Reader interest0.69
  • Audience breadth0.59
  • Practical relevance0.78
  • Substantiated0.64
  • Technical depth0.65
  • New information0.87
  • Counts against: Promotional0.04
  • Counts against: Overclaim0.17

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?0.500.300.480.430.20+0.24+0.102
Reader interestWould a well-informed senior engineer or tech founder want to read this today, and likely pass it on?0.580.700.780.690.20+0.26+0.179
Audience breadthHow many people who build technology does it concern?0.660.500.620.590.16+0.13+0.077
Practical relevanceHow useful is it to someone who builds software or tech products?0.890.700.760.780.18+0.22+0.172
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.0.580.600.730.640.15+0.05+0.032
Technical depthHow technically substantive is it?0.810.600.550.650.26+0.05+0.033
New informationDoes it contain information absent from the stories covered in the last 7 days (list provided)?0.870.800.930.870.13+0.05+0.043
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.0.050.050.010.040.04−0.19−0.007
OverclaimDo the headline or conclusions claim more than the body supports?0.130.200.180.170.07−0.11−0.019
Sum of contributions+0.612
Claim-check penalty0.000
Total, as published0.612

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 #19 on Rubric, 15 Nov 2026
<a href="https://rubric.hrih.si/editions/2026-11-15/19/"><img src="https://rubric.hrih.si/badge/2026-11-15/19.svg" alt="Ranked #19 on Rubric, 15 Nov 2026" width="245" height="28"></a>

Claim check

Claim check: 3 matches source · 2 no source given · 3 couldn’t check. Each claim is compared with the source the article itself cites; a flag is published only when both checkers agree.

  1. Couldn’t checkCausal conclusion

    Yantis and Jonides (1984) found that anything that abruptly appears pulls the eye, so each new element costs attention.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “Anything that appears pulls the eye,1 so each one costs attention”

    The source says

    No passage could be compared.

    Source cited by the article: doi.org/10.1037/0096-1523.10.5.601

  2. Couldn’t checkCausal conclusion

    Maister's work indicates that knowing what is happening makes a wait feel shorter.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “Knowing what’s happening makes the wait feel shorter”

    The source says

    No passage could be compared.

    Source cited by the article: davidmaister.com/articles/1/52

  3. Matches sourceBenchmark result

    In an eye-tracking study, most viewers kept up with subtitles at 20 characters per second, the fastest speed tested.

    The cited source says the same thing.

    The article says

    “in an eye-tracking study, most viewers kept up with them at 20 characters a second, the fastest speed it tested”

    The source says

    “By analyzing people’s eye gaze, we were able to discover that most viewers could read the subtitles as well as follow the images, coping well even with fast subtitle speeds”

    Source cited by the article: pmc.ncbi.nlm.nih.gov/articles/PMC6007935

  4. Matches sourceNumber

    Netflix uses 20 characters per second as its reading speed limit for adult programs.

    The cited source says the same thing.

    The article says

    “Netflix uses that as its limit for adult programs”

    The source says

    “Adult programs: Up to 20 characters per second”

    Source cited by the article: partnerhelp.netflixstudios.com/hc/en-us/articles/217350977-English-USA-Timed-Text-Style-Guide

  5. Matches sourceGeneralization

    Progressive disclosure is the established pattern of showing what the reader needs now and keeping the rest one click away.

    The cited source says the same thing.

    The article says

    “The reader gets what they need now, and the rest stays one click away, a pattern known as progressive disclosure”

    The source says

    “Initially, show users only a few of the most important options. - Offer a larger set of specialized options upon request”

    Source cited by the article: nngroup.com/articles/progressive-disclosure

  6. Couldn’t checkBenchmark result

    In a study of scrolling text, comprehension dropped when text advanced in the largest steps, and readers preferred smooth movement.

    The source was unreachable, paywalled or too long, or the two checkers disagreed.

    The article says

    “In one study of scrolling text, comprehension dropped when it advanced in the largest steps, and readers preferred it moving smoothly”

    The source says

    No passage could be compared.

    Source cited by the article: doi.org/10.1080/01449298908914536

  7. No source givenNumber

    A 1,000-character message arriving all at once is fully shown after 15.7 s with slow settings (35 cps floor, 120 cps ceiling, 6 s target) and 3.7 s with fast settings (120 cps floor, 400 cps ceiling, 1 s target).

    The article gives no link or citation for it.

    The article says

    “Slow 35 cps 120 cps 6 s 15.7 s”

    The source says

    No source to compare with.

  8. No source givenNumber

    At 20 characters per second, a phrase like "Reading src/auth/session.ts" takes about a second and a half to read.

    The article gives no link or citation for it.

    The article says

    “a phrase like “Reading src/auth/session.ts” takes about a second and a half to read”

    The source says

    No source to compare with.

Also covered by

No other coverage was clustered with this story.

Elsewhere

Elsewhere: HN 1 pts, not on front page

Discussion on Hacker News

Recorded for context only, checked 15 Nov 2026, 20:46 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 makes an agent chat feel good?”

More on Rubric

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