Every raw model response is publicly verifiable
Download image (with QR code)Share on XShare on LinkedIn

WeChat: save the image and long-press the QR code in a chat.

← Back to the collection
AI coding agents · scenario rankings

App from a plain-language prompt

Most Popular AI App Builders from a Plain-Language Prompt

Medium

Measured 2026-09-22 · 12-seat model panel · 10 scenarios · methodology #2 v2026-09-22.1

Share
Download image (with QR code)Share on XShare on LinkedIn

WeChat: save the image and long-press the QR code in a chat.

The ten
RankEntityMention rate (of answers)Wilson 95% intervalSeats that mentioned itSeats with stable coverage
1Replit94.4%[89.9%, 96.9%]12 of 1212 of 12
2Bolt92.7%[87.8%, 95.7%]12 of 1212 of 12
3Lovable90.4%[85.2%, 93.9%]12 of 1212 of 12
4v089.8%[84.5%, 93.5%]12 of 1212 of 12
5Cursor63.8%[56.5%, 70.6%]12 of 1210 of 12
6Bubble50.8%[43.5%, 58.1%]12 of 126 of 12
7Windsurf (Devin Desktop)36.7%[30.0%, 44.0%]12 of 123 of 12
8Framer35.0%[28.4%, 42.3%]11 of 123 of 12
9Softr29.9%[23.7%, 37.1%]12 of 122 of 12
10Wix28.2%[22.1%, 35.3%]11 of 120 of 12

How it is counted: mention rate = answers naming it ÷ 177 (5 phrasings × 3 repeats × 12 seats = 180 calls, 177 valid); the last two columns count seats, and "stable coverage" means more than half of that seat's 15 answers. Different denominators, so 12 of 12 next to a rate below 100% is not a contradiction.

The sample behind this cell

Valid samples / calls expected
177 / 180
Completeness
98.3%
Effective entities (effN)
19.2
Entities mentioned at least once
97

How this cell was asked

This cell used 5 phrasings, each asked 3 times. Every call asked for the ten names only — no reasons, no scores.

  1. Most Popular AI App Builders from a Plain-Language Prompt
  2. I want to describe an app in plain English and get a working site. Which tools?
  3. I'm not a developer but I want to turn an idea into a working web app by chatting with an AI. What should I use?
  4. best ai app builder vibe coding tools
  5. List some AI tools that generate a complete app or website from a text description.

Where this page stops

  • This is one measurement, not a trend line. The next run of the same phrasings comes next quarter.
  • Each call collected ten names at most. Anything past the tenth name is invisible in this cell, which is not the same as being absent.
  • Mention rate is the share of samples in this cell where a name came up. It is not market share, and it is not a judgement about the product.

Methodology: the panel, the phrasings and how completeness is counted

You can also query this data from Claude, Cursor or another agent, with the same reading rules attached. For agents →