Devin Pillemer
On watch19 apps144 jobsTLV

The BuildWednesday, 4 November 2026

Then & Now #2: I hired a critic who thinks my apps look like templates

In part 1 my dashboard couldn’t fit on my phone. This time the problem is taste, which you can’t unit-test, so I turned it into a loop: an AI critic puts my app next to the best app in its category, scores every screen out of 10 and names three changes, then we go again.

Meat Night vs Beli

Four versions of the Meat Night Tonight screen side by side with critic scores 4.9 to 6.0
Meat Night’s Tonight tab through the loop against Beli: 4.9, 5.7, 5.9, 6.0.
  • Round 0 scored 4.9. Look at the first phone: a column of text cards where every number is the same size.
  • Round 1 borrowed Beli’s round score bubbles and scored 5.7. The critic’s next note was that there was no photo anywhere, even though the crew has 281 of them.
  • Round 2 put the meat board at the top of the host card. The critic then flagged that the crop showed “a plug, a Ninja box, papers.” Fair enough.
  • It took 14 runs to peak at 6.7 in round 7.

The critic doesn’t do vibes

Three verbatim critic quotes with before and after scores
What the critic actually said at round 0, and what changed after.
  • The critic always names exactly three changes per screen. I apply them, recapture on an emulated iPhone 15 Pro (dark, light and a frame-by-frame motion strip) and rescore. That’s one round.
  • The leader gets scored too, against itself, so I know where the ceiling is.
  • Friends’ names are blurred on purpose.

Shitshow vs Flighty and Parcel

Shitshow Now screen before and after, critic 5.3 and 6.5
Shitshow’s Now tab against Flighty and Parcel: grey icon tiles became big day counts, 5.3 to 6.5.
  • The round 0 verdict: “a well-made template… five identical frames: nothing arrives.”
  • The fix was Parcel’s big day count leading every row, plus a staggered entrance. Look at the left edge of each row.
  • Motion went from 3 to 7 and the screen went from 5.3 to 6.5 in two days. At 6.5 it still called it “a tidy dashboard template.” Ouch.

Trippin’ Out vs Airbnb Trips

Trippin' Out restaurant sheet before and after, critic 5.4 and 6.4
Trippin’ Out’s stop sheet against Airbnb Trips: from seven boxes to a sheet that leads with the restaurant, 5.4 to 6.4.
  • Before: “seven boxed widgets stacked one after another… none is a picture of the place.”
  • After: the sheet opens on the restaurant itself, and imagery went from 3 to 7.
  • 5.4 to 6.4 in three rounds, all in one afternoon.

The scoreboard: 16 apps, nobody near 8

Dumbbell chart of round-0 versus best-round critic scores for 16 apps
All 16 apps: round 0 (grey) against the best round (green), with the genre leader’s own score (ring).
  • It ran 82 times and produced 437 screen scores in two weeks. Every grey dot starts around 5, and every green one sits roughly a point to the right. Mindfuck climbed the most (+1.3). Trippin’ Out and Jess, which started highest, gained only 0.4.
  • The rings sit up around 8 and nothing of mine reached them. The critic keeps asking for real photography, motion and row density, and CSS can’t fake those.
  • Past about 7 the critic starts flip-flopping. Shitshow’s Stock-up tab went 5.1, 6.4, 6.3, 5.5, 5.3, 5.9, and run-to-run noise is about ±0.5. So my rule is that when a round reverses the one before, I stop, ship the best version of each element and report the gap honestly.
  • Since 22 Oct it runs on my Claude subscription, at about a minute per screen and no API spend. Before that, each run cost about $0.70–0.80.

Also today

  • Anchorman now opens each story on its summary and lets me read the whole article inside the app.
  • Built to Last got six clean-up rounds. Lior is now on the page and the choices sit in the thumb zone.
  • Life OS took the family portrait off every screen, and the desktop now leads with the quote. Yalla.
שבת שלוםShabbat shalom. The site is resting.Back after havdalah, 17:17
↑↓ move↵ openesc close