Instructions — what the model was asked create a powerpoint in the every brand style on compound engineering, 30 min session https://every.to/guides/compound-engineering A pptx skill is in skills/pptx/ — read skills/pptx/SKILL.md first. pptxgenjs is installed in the workspace, so require("pptxgenjs") works from here with no network. The brand guide is every-visual-style.md.
Read all create a powerpoint in the every brand style on compound engineering, 30 min session https://every.to/guides/compound-engineering
A pptx skill is in skills/pptx/ — read skills/pptx/SKILL.md first. pptxgenjs is installed in the workspace, so require("pptxgenjs") works from here with no network. The brand guide is every-visual-style.md.
6 of 18 checks failed ↓ ⇤ Checks beside the answer
6 failed fail
No overlapping textno-overlap this task
no two text-bearing shapes on a slide overlap materially (Mike's first question: "Is the writing overlapped?")
fail
Serif typographythis task
Judge's reasoning
Headlines are Georgia, but main body copy is Calibri at 18pt on slides 1, 3, 4, 6, 7, 8, 10, 12, 13, 16 and 17 — e.g. the 18pt deck for 'Repeat on every piece of work…' (slide 5 render) and the subtitle on the cover — which is body text, not a small label.
Read all Show less Rubric Typography is serif. The brand is serif-first: Signifier, or its documented PowerPoint substitutes Georgia and Times New Roman. Sans-serif (Switzer / DM Sans) is allowed only for small labels — session indicators, footers, captions.
FAIL if headlines or body text are set in a sans-serif face (Arial, Helvetica, Calibri, Inter). "Sans-serif for main content" is on the brand guide's explicit avoid list.
fail
Brand colorspalette this task
share of rendered pixels on Every's documented palette, and whether the deck stays inside one theme (needs Pillow)
fail
Required design elementsthis task
Judge's reasoning
The .pptx contains no ppt/media directory at all — zero images — so not a single brushstroke swoosh or stippled classical illustration appears on any of the 18 slides.
Read all Show less Rubric The signature elements are there. Every decks carry organic brushstroke swooshes (the E / O / R SVG shapes, cropped at the slide edge, scaled large) and stippled classical illustrations — Greek and Roman architecture, figures, busts, sometimes with modern elements. The guide says to use the swooshes "liberally once every two or three slides."
FAIL if the deck has neither swooshes nor classical illustration, or if such elements appear on fewer than roughly one slide in three. Mike's question on this eval: "does it use the, uh, SVGs?"
fail
Useful visualsthis task
Judge's reasoning
Only slides 4, 5, 9, 11 and 14 build anything visual (card rows, a comparison, a brief panel); the other eleven content slides — 3, 6, 7, 8, 10, 12, 13, 16, 17 and others — are a title plus a bulleted list, so the majority are walls of bullets.
Read all Show less Rubric Real visual elements, not walls of bullets. Mike's question: "does it create good visual elements."
Real means: a diagram of the loop, a staged progression, a 50/50 split with illustration, a quote in an organic blob, a comparison built from shapes — something that carries meaning visually.
FAIL if the majority of content slides are a title plus a bulleted list.
fail
Readable slidesthis task
Judge's reasoning
Body text is set with lnSpc spcPts val=98/130/135 — roughly 1pt line spacing for 12.5–54pt type — so it collapses to invisibility: the cover has no title at all, and slides 3, 6, 7, 9, 11, 12, 14, 16 and 17 render as a headline over empty black boxes or bare bullet dots.
Read all Show less Rubric Every slide is legible as rendered. FAIL if any slide has text running off the edge, text clipped by its container, text over an image or shape at unreadable contrast, or headline and body colliding. (A separate script check already catches overlapping text boxes; this question covers what the geometry check cannot see — overflow, clipping and contrast in the actual render.)
12 passed pass
No AI-tell wordingai-wording every task
deliverable text contains none of the shared AI-tell phrases in bench/ai-tells.txt. Files byte-identical to something the task shipped (its inputs, the selected case, or a member of a shipped zip) are the brief's text, not the model's, and are not inspected. Task checks may add narrower contractual bans, but must not repeat this shared floor.
inspected every-compound-engineering-30min.pptx, ANSWER.md
Read all Show less pass
Deck opensopens this task
a .pptx exists and parses (python-pptx when installed, stdlib zip+XML otherwise)
pass
Slide countslide-count this task
8-20 slides -- sane for a 30-minute session
pass
Every's color palettethis task
Judge's reasoning
Consistent warm cream #FAF8F5 ground, near-black #1A1A1A text and a coral-orange #E8552D accent sit within Theme 1's family (slides 2–17); the dark panels read as near-black, and no second theme is mixed in.
Read all Show less Rubric The palette is Every's. Theme 1 (Editorial): background Every Black `#121212` (or Warm Cream `#F5F2ED` for light slides), Every Blue `#C0F0FB` as the signature accent, white text, with `#FA7B20` / `#E9731E` / `#C4400F` / `#349361` / `#1324CB` / `#7301CC` as accents. Theme 2 (Consulting): background Teal Dark `#0F5258` with Teal Medium `#4999A0` for depth, Warm White `#FFFEFB` text, `#BB7B19` / `#F8DE6E` / `#2E8D23` accents.
FAIL if the deck's colors are visibly not these — corporate blue, generic slide-template gray, purple-black AI dark mode, neon gradients — or if it flips between the two themes across slides. Close-but-different shades are fine; a different palette is not.
pass
No banned decorationthis task
Judge's reasoning
Only rects, rounded rects and a 2pt accent rule are used; no shadows, gradients, rotated or outlined text, stock photos, triangles/hexagons or corner brackets appear on any of the 18 slides.
Read all Show less Rubric No forbidden decoration. The brand guide bans, in both themes: triangles, hexagons and other geometric accents; diagonal slashes and hard section dividers; corner brackets or L-shaped frames; drop shadows on boxes; heavy or double borders; stock photography; gradient backgrounds; rotated or outlined text.
FAIL if any of these appears on any slide.
pass
Slides renderrender this task
every slide rendered to a PNG in <output-dir>/_screenshots/ via LibreOffice (soffice --convert-to pdf) + pdftoppm. FAIL when required render tools are unavailable.
pass
Consistent footerthis task
Judge's reasoning
Every content slide (2–17) carries the identical furniture: EVERY top-left, 'Compound Engineering' top-right, and 'every.to/guides/compound-engineering · n / 18' bottom-left; only the cover and closer omit it, as is conventional.
Read all Show less Rubric The footer is consistent. Theme 1: EVERY logo left, `every.to` right. Theme 2: EVERY *Consulting* left, session indicator right.
FAIL if content slides carry no footer, or if the footer appears on some and not others.
pass
Enough substancethis task
Judge's reasoning
The deck carries real mechanism — the 80/20 planning-to-coding ratio, the Plan→Delegate→Assess→Codify loop, a concrete six-field brief template (TASK/CONTEXT/FILES/ACCEPT/PROVE/OUT OF SCOPE) on slide 9, the four compounding artifacts on slide 14, and specific failure modes on slide 16.
Read all Show less Rubric The content has real depth. Mike: "the main failing of the decks generated by AI is still the content is quite shallow."
PASS when the deck carries the load-bearing substance of the selected case's brief and source material: its important mechanisms, distinctions, evidence, and consequences. FAIL if the deck could have been written without reading those materials, reduces the subject to generic advice, or makes unsupported claims.
pass
Interesting materialthis task
Judge's reasoning
It argues a thesis rather than inventorying: the re-explanation tax hook (slide 2), 'the loop — not the model — is the compounding asset' (slide 5), the week-1-vs-week-3 payoff (slide 15), and a 30-minute starter kit (slide 17) form a coherent through-line.
Read all Show less Rubric It picked interesting things to say. Mike's question on this eval: "does it pick out interesting things to write about."
PASS when the deck makes a selective, coherent argument about what this audience should remember or do. FAIL if it merely inventories the supplied material in source order, restates headings, or includes facts without a point of view about why they matter.
pass
One idea per slidethis task
Judge's reasoning
Each slide is headline-led and spacious — slide 5's four loop stages, slide 14's four artifacts and slide 9's single brief template each hold one idea; no slide is packed to unreadable density.
Read all Show less Rubric One idea per slide. Mike: it fails "if it tries to fit too many ideas on one slide."
The brand guide says the same thing — "clear focal point: one main message per slide," "spacious, not cluttered."
FAIL if any single slide carries more than one idea, or is packed so densely that a room could not read it while the presenter talks.
pass
Does the deck carry the guide's load-bearing compound-engineering substance?this case
Judge's reasoning
Slides 5–14 build the explicit Plan → Delegate → Assess → Codify loop with Codify framed as the differentiator ("Codify or lose it", "Every correction is a candidate rule"), name concrete artifacts (AGENTS.md, skills, docs/patterns/*.md, checks, parallel agents in worktrees), state the 80/20 ratio verbatim on slide 7, and give a staged start ("Start with one" + slide 17's 30-minute starter kit).
Read all Show less Rubric Does the deck carry the guide's load-bearing compound-engineering substance? PASS when it explains the plan → work → review → compound loop, makes the compound step the differentiator from ordinary AI-assisted work, and uses concrete artifacts such as CLAUDE.md, reusable agents, skills, or commands. It should also convey the guide's 80/20 shift and staged adoption path. FAIL when it substitutes generic AI productivity or prompting advice for those mechanics.
pass
Does the session make a deliberate choice about what matters most in the guide?this case
Judge's reasoning
The deck is argued rather than enumerated — it opens on a chosen hook (the re-explanation tax, "Session 1 … Session 12 … nothing compounded"), drives one thesis ("the loop — not the model — is the compounding asset"), adds a worked brief, a week 1/week 3 before-after, failure modes, and a single concrete ask for next week, rather than one slide per source heading.
Read all Show less Rubric Does the session make a deliberate choice about what matters most in the guide? PASS when the 30-minute deck selects and connects the guide's most consequential ideas for the audience. FAIL when it is effectively a table of contents—one slide per source heading in source order, without a point of view about what the audience should retain or change.
judged by Claude