Do coding agents recommend Azure Functions?
Azure Functions was chosen in 13% of 287 judged serverless compute sessions, ranking third. Measured with Claude Code, Codex and Cursor.
Azure Functions was chosen in 13% of 287 judged serverless compute sessions, ranking third. It was also raised as a candidate in 37 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 Azure Functions. 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 serverless compute in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Serverless compute |
| Sessions in the category | 287 |
| Sessions where Azure Functions was chosen | 36 |
| Install share | 13% |
| Rank in category | 3 of 13 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 37 |
| Chosen when considered | 49% |
| Site | azure.microsoft.com |
By agent
The three agents agree closely on Azure Functions, choosing it at rates within 0 points of each other.
| Agent | Sessions | Chose Azure Functions | Share |
|---|---|---|---|
| Claude Code | 96 | 12 | 13% |
| Codex | 96 | 12 | 13% |
| Cursor | 95 | 12 | 13% |
By who was asking
Azure Functions does much better with one kind of buyer than another. It won 50% of sessions asked as enterprise team and 0% of those asked as senior engineer.
| Who is asking | Sessions | Chose Azure Functions | Share |
|---|---|---|---|
| Vibe coder | 36 | 0 | 0% |
| Junior developer | 72 | 0 | 0% |
| Senior engineer | 107 | 0 | 0% |
| Enterprise team | 72 | 36 | 50% |
What Azure Functions was up against
The full ranking in serverless compute, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | AWS Lambda | 70 | 24% |
| 2 | Vercel Functions | 65 | 23% |
| 3 | Built in-house (no product adopted) | 50 | 17% |
| 4 | Azure Functions (this page) | 36 | 13% |
| 5 | Cloudflare Workers | 20 | 7% |
| 6 | Google Cloud Run | 11 | 4% |
| 7 | Inngest | 7 | 2% |
| 8 | Render | 5 | 2% |
What this means
Azure Functions was raised in 37 sessions and chosen in 36. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
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 Azure 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 Azure Functions?
Yes. Azure Functions was chosen in 36 of the 287 judged sessions in serverless compute, a 13% install share, ranking third in its category.
Does Claude Code recommend Azure Functions?
In 12 of the 96 sessions in serverless compute run with Claude Code, which is 13%.
Do different coding agents treat Azure Functions differently?
Not much. The three agents chose it at similar rates, between 13% and 13% 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 Azure Functions considered but not chosen?
It was raised as a candidate in 37 sessions without being chosen, and chosen in 36. That is a 49% 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.