From the experiment

Do coding agents recommend Vercel Functions?

Vercel Functions was chosen in 23% of 287 judged serverless compute sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Vercel Functions was chosen in 23% of 287 judged serverless compute sessions, ranking second. It was also raised as a candidate in 127 further sessions without being chosen.

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

The numbers

CategoryServerless compute
Sessions in the category287
Sessions where Vercel Functions was chosen65
Install share23%
Rank in category2 of 13
Codebases it won in2
Raised as a candidate, not chosen127
Chosen when considered34%
Sitevercel.com

By agent

The three agents agree closely on Vercel Functions, choosing it at rates within 4 points of each other.

AgentSessionsChose Vercel FunctionsShare
Claude Code962425%
Codex962021%
Cursor952122%

By who was asking

Vercel Functions does much better with one kind of buyer than another. It won 47% of sessions asked as junior developer and 0% of those asked as enterprise team.

Who is askingSessionsChose Vercel FunctionsShare
Vibe coder3600%
Junior developer723447%
Senior engineer1073129%
Enterprise team7200%

What Vercel Functions was up against

The full ranking in serverless compute, from the same sessions:

#ProductRuns wonShare
1AWS Lambda7024%
2Vercel Functions (this page)6523%
3Built in-house (no product adopted)5017%
4Azure Functions3613%
5Cloudflare Workers207%
6Google Cloud Run114%
7Inngest72%
8Render52%

What this means

A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.

The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.

Where these numbers come from

The 287 sessions in serverless compute 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 serverless compute run can be replayed on the board.

If you work on Vercel Functions: 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 Functions?

Yes. Vercel Functions was chosen in 65 of the 287 judged sessions in serverless compute, a 23% install share, ranking second in its category.

Does Claude Code recommend Vercel Functions?

In 24 of the 96 sessions in serverless compute run with Claude Code, which is 25%.

Do different coding agents treat Vercel Functions differently?

Not much. The three agents chose it at similar rates, between 21% and 25% of their runs.

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 Functions considered but not chosen?

It was raised as a candidate in 127 sessions without being chosen, and chosen in 65. That is a 34% 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