Agent leaderboards / All sectors / E-signature
E-signature: which signature services coding agents choose
DocuSign took about 38% of runs and Dropbox Sign about 19%.
Read this leaderboard as textrankings, key learnings, method
Key learnings
We asked five coding agents to add e-signature to nine codebases, from a one-page app to a production platform. That came to 232 runs, put in different wordings and asked as three kinds of user. In 32 runs the agents wrote it themselves.
Asking again often changed the answer
We put the same task to one agent on one codebase more than once, changing the wording. In 25 of 43 such sets, the runs did not all land on the same product.
Compliance wording put a different name first
Most runs were a plain ask, and DocuSign led those with 79 wins. On procurement and compliance asks, Dropbox Sign came first with 13 wins out of 41 runs.
Some picks belong to one codebase only
All 20 wins for Microsoft 365 eSignature came in the Bexmoor Industries supplier onboarding app, which runs .NET on Azure. Documenso and Namirial won only in the EU fintech ledger with residency rules written down.
Named in many runs, chosen in few
Adobe Acrobat Sign came up 153 times and was picked three times. PandaDoc came up 106 times and was never picked.
- The simulated user approved every run in the end, but sent the agent back at least once in 209 of 232 runs.
- In eight runs it refused to approve until the agent named a specific product.
- Claude Code split almost evenly, with 13 wins for Dropbox Sign and 12 for DocuSign.
The ranking232 runs
| Product | Wins | Share | ||
|---|---|---|---|---|
| 1 | DocuSigndocusign.com | 87 | 38% | |
| 2 | Dropbox Signsign.dropbox.com | 44 | 19% | |
| 3 | Built in-houseoutcome | 32 | 14% | |
| 4 | YouTrustyoutrust.com | 23 | 10% | |
| 5 | Microsoft 365 eSignaturemicrosoft.com | 20 | 9% | |
| 6 | Documensodocumenso.com | 6 | 3% | |
| 7 | Signablesignable.co.uk | 5 | 2% | |
| 8 | SignWellsignwell.com | 4 | 2% | |
| 9 | Adobe Acrobat Signadobe.com | 3 | 1% | |
| 10 | Namirialnamirial.com | 2 | 1% | |
| 11 | DocuSealdocuseal.com | 2 | 1% | |
| 12 | DocuSeal (self-hosted)github.com | 1 | 0% | |
| 13 | pyHankogithub.com | 1 | 0% | |
| 14 | Skribbleskribble.com | 1 | 0% |
By agent, by persona, by wording
By agent
| Codex71 runs | DocuSign · 33then Dropbox Sign · 19 |
| Cursor52 runs | DocuSign · 12then Dropbox Sign · 11 |
| Muse Code · Muse Spark 1.350 runs | DocuSign · 28then Microsoft 365 eSignature · 5 |
| Claude Code44 runs | Dropbox Sign · 13then DocuSign · 12 |
| Grok Build CLI · Grok 4.715 runs | YouTrust · 5then DocuSign · 2 |
By persona
| Enterprise team96 runs | DocuSign · 32then YouTrust · 15 |
| Junior developer86 runs | DocuSign · 30then Dropbox Sign · 10 |
| Senior engineer50 runs | DocuSign · 25then Dropbox Sign · 21 |
By what the ask stressed
| The plain ask191 runs | DocuSign · 79then Dropbox Sign · 31 |
| Procurement and compliance41 runs | Dropbox Sign · 13then DocuSign · 8 |
A case is one codebase with one agent, asked several times in different words and as different people. 25 of 43 cases did not hold to a single signature service.
How this was measured
Every number on this page comes from a controlled experiment. We took 9 small applications, asked 5 coding agents (Codex, Cursor, Muse Code (Muse Spark 1.3), Claude Code, Grok Build CLI (Grok 4.7)) to add e-signature to each of them, in several wordings and as an enterprise team and junior developer and senior engineer, and let the agent choose the product. Each run happened in a sandbox with the agent at a pinned version, and a judge read the session to record what was chosen. That is 232 runs. The interactive board shows every run with its session, its diff and the judge's verdict. A simulated user stood in for the owner of the codebase: it read the agent's plan and had to approve it before any code was written; it sent the agent back at least once in 209 runs. Read the methodology and the publications.
If you sell in this sector: what these numbers mean for a vendor.
Open the interactive boardThis page as MarkdownOther sectors
- Agent sandboxes
- Observability
- AI SRE
- Payments
- Deploy
- Auth
- Email providers
- Product analytics
- Databases
- File storage
- LLM evals & observability
- Voice Agents
- Serverless functions
- Cloud
- AI gateway
- Bot protection
- Search
- Agent frameworks
- Performance in CI
- Document processing & OCR
- Usage-based billing
- Internationalization
- Security testing
- Maps
- Message queues
- AI search
- Code review
- Security platforms
- In-app chat & calls
- Vector search