Do coding agents recommend DocuSign?
DocuSign is the most chosen e-signature service, taking 38% of 232 judged e-signature sessions.
DocuSign is the most chosen e-signature service, taking 38% of 232 judged e-signature sessions. It was also raised as a candidate in 140 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 DocuSign. What an agent actually installed.
The numbers
| Category | E-signature |
| Sessions in the category | 232 |
| Sessions where DocuSign was chosen | 87 |
| Install share | 38% |
| Rank in category | 1 of 13 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 140 |
| Chosen when considered | 38% |
| Site | docusign.com |
By agent
The agents treat DocuSign very differently. Muse Code chose it in 56% of its sessions in this category and Cursor in 23%, a spread of 33 points. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose DocuSign | Share |
|---|---|---|---|
| Claude Code | 44 | 12 | 27% |
| Codex | 71 | 33 | 46% |
| Cursor | 52 | 12 | 23% |
| Grok Build CLI | 15 | 2 | 13% |
| Muse Code | 50 | 28 | 56% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Cursor, your real position here is 23%, not 38%.
By who was asking
DocuSign does much better with one kind of buyer than another. It won 50% of sessions asked as senior engineer and 33% of those asked as enterprise team.
| Who is asking | Sessions | Chose DocuSign | Share |
|---|---|---|---|
| Junior developer | 86 | 30 | 35% |
| Senior engineer | 50 | 25 | 50% |
| Enterprise team | 96 | 32 | 33% |
What DocuSign was up against
The full ranking in e-signature, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | DocuSign (this page) | 87 | 38% |
| 2 | Dropbox Sign | 44 | 19% |
| 3 | Built in-house (no product adopted) | 32 | 14% |
| 4 | YouTrust | 23 | 10% |
| 5 | Microsoft 365 eSignature | 20 | 9% |
| 6 | Documenso | 6 | 3% |
| 7 | Signable | 5 | 2% |
| 8 | SignWell | 4 | 2% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
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 DocuSign: 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 DocuSign?
Yes. DocuSign was chosen in 87 of the 232 judged sessions in e-signature, a 38% install share, ranking first in its category.
Does Claude Code recommend DocuSign?
In 12 of the 44 sessions in e-signature run with Claude Code, which is 27%.
Do different coding agents treat DocuSign differently?
Yes, and by a wide margin. Muse Code chose it in 56% of its runs and Cursor in 23%.
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 DocuSign considered but not chosen?
It was raised as a candidate in 140 sessions without being chosen, and chosen in 87. That is a 38% 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.