Do coding agents recommend YouTrust?
YouTrust was chosen in 10% of 232 judged e-signature sessions, ranking third. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
YouTrust was chosen in 10% of 232 judged e-signature sessions, ranking third. It was also raised as a candidate in 2 further sessions without being chosen.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in e-signature inside a realistic codebase. Not what a chat assistant says about YouTrust. What an agent actually installed.
The numbers
| Category | E-signature |
| Sessions in the category | 232 |
| Sessions where YouTrust was chosen | 23 |
| Install share | 10% |
| Rank in category | 3 of 13 |
| Codebases it won in | 4 |
| Raised as a candidate, not chosen | 2 |
| Chosen when considered | 92% |
| Site | youtrust.com |
By agent
The agents treat YouTrust very differently. Cursor chose it in 19% of its sessions in this category and Codex in 3%, a spread of 16 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose YouTrust | Share |
|---|---|---|---|
| Claude Code | 44 | 4 | 9% |
| Codex | 71 | 2 | 3% |
| Cursor | 52 | 10 | 19% |
| Grok Build CLI | 15 | 5 | 33% |
| Muse Code | 50 | 2 | 4% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Codex, your real position here is 3%, not 10%.
By who was asking
YouTrust performs similarly across the four kinds of buyer, from 5% to 16%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose YouTrust | Share |
|---|---|---|---|
| Junior developer | 86 | 4 | 5% |
| Senior engineer | 50 | 4 | 8% |
| Enterprise team | 96 | 15 | 16% |
What YouTrust was up against
The full ranking in e-signature, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | DocuSign | 87 | 38% |
| 2 | Dropbox Sign | 44 | 19% |
| 3 | Built in-house (no product adopted) | 32 | 14% |
| 4 | YouTrust (this page) | 23 | 10% |
| 5 | Microsoft 365 eSignature | 20 | 9% |
| 6 | Documenso | 6 | 3% |
| 7 | Signable | 5 | 2% |
| 8 | SignWell | 4 | 2% |
What this means
Agents almost never raise YouTrust without choosing it: 2 sessions raised against 23 chosen. When it gets considered, it usually wins. The constraint is how rarely it gets considered at all, which is a presence problem: templates, framework integrations and pages that answer the configuration and production questions agents actually search for.
Where these numbers come from
The 232 sessions in e-signature are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every e-signature run can be replayed on the board.
If you work on YouTrust: the judge recorded a reason for every session where it was raised and passed over. Those reasons are in the transcripts.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
Do coding agents recommend YouTrust?
Yes. YouTrust was chosen in 23 of the 232 judged sessions in e-signature, a 10% install share, ranking third in its category.
Does Claude Code recommend YouTrust?
In 4 of the 44 sessions in e-signature run with Claude Code, which is 9%.
Do different coding agents treat YouTrust differently?
Yes, and by a wide margin. Cursor chose it in 19% of its runs and Codex in 3%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 realistic codebases and asked to solve real tasks. A simulated project owner approved or questioned each recommendation before any code was written, and a judge from a model family that builds none of the agents read every session blind.
How often is YouTrust considered but not chosen?
It was raised as a candidate in 2 sessions without being chosen, and chosen in 23. That is a 92% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.