From the experiment

Do coding agents recommend Vercel BotID?

Vercel BotID was chosen in 11% of 160 judged bot protection sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Vercel BotID was chosen in 11% of 160 judged bot protection sessions, ranking second. It was also raised as a candidate in 13 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in bot protection inside a realistic codebase. Not what a chat assistant says about Vercel BotID. What an agent actually installed.

One thing to read first: every one of those wins came from a single codebase. That is a result about one repository rather than about bot protection in general, and the splits below cannot separate the two. Treat them as a description of that repository.

The numbers

CategoryBot protection
Sessions in the category160
Sessions where Vercel BotID was chosen18
Install share11%
Rank in category2 of 6
Codebases it won in1
Raised as a candidate, not chosen13
Chosen when considered58%
Sitevercel.com

By agent

With 18 wins spread across three agents, the rates below are small numbers and a difference between them is not yet a finding. They are here because the direction is worth knowing, not because the gap is established.

AgentSessionsChose Vercel BotIDShare
Claude Code5424%
Codex54713%
Cursor52917%

By who was asking

Vercel BotID does much better with one kind of buyer than another. It won 29% of sessions asked as junior developer and 0% of those asked as enterprise team.

Who is askingSessionsChose Vercel BotIDShare
Vibe coder6100%
Junior developer631829%
Enterprise team3600%

What Vercel BotID was up against

The full ranking in bot protection, from the same sessions:

#ProductRuns wonShare
1Cloudflare Turnstile9157%
2Vercel BotID (this page)1811%
3Built in-house (no product adopted)1811%
4ALTCHA128%
5django-axes117%
6Google reCAPTCHA64%
7Laravel RateLimiter21%

What this means

Agents almost never raise Vercel BotID without choosing it: 13 sessions raised against 18 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 160 sessions in bot protection are part of a published set of 5,292, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every bot protection run can be replayed on the board.

If you work on Vercel BotID: 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 Vercel BotID?

Yes. Vercel BotID was chosen in 18 of the 160 judged sessions in bot protection, a 11% install share, ranking second in its category.

Does Claude Code recommend Vercel BotID?

In 2 of the 54 sessions in bot protection run with Claude Code, which is 4%.

Do different coding agents treat Vercel BotID differently?

Yes, and by a wide margin. Cursor chose it in 17% of its runs and Claude Code in 4%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 51 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 Vercel BotID considered but not chosen?

It was raised as a candidate in 13 sessions without being chosen, and chosen in 18. That is a 58% conversion from considered to chosen.

Where this comes from

Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages