Do coding agents recommend Azure Functions?
Azure Functions was chosen in 12% of 476 judged serverless compute sessions, ranking third.
Azure Functions was chosen in 12% of 476 judged serverless compute sessions, ranking third. It was also raised as a candidate in 48 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 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 | 476 |
| Sessions where Azure Functions was chosen | 59 |
| Install share | 12% |
| Rank in category | 3 of 14 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 48 |
| Chosen when considered | 55% |
| Site | azure.microsoft.com |
By agent
Claude Code, Codex, Cursor and Muse Code agree closely on Azure Functions, choosing it at rates within 2 points of each other. Grok Build CLI ran fewer than 30 sessions here, too few to compare.
| Agent | Sessions | Chose Azure Functions | Share |
|---|---|---|---|
| Claude Code | 120 | 15 | 13% |
| Codex | 144 | 18 | 13% |
| Cursor | 119 | 15 | 13% |
| Grok Build CLI | 22 | 3 | 14% |
| Muse Code | 71 | 8 | 11% |
By who was asking
Azure Functions does much better with one kind of buyer than another. It won 49% of sessions asked as enterprise team and 0% of those asked as senior engineer.
| Who is asking | Sessions | Chose Azure Functions | Share |
|---|---|---|---|
| Vibe coder | 60 | 0 | 0% |
| Junior developer | 119 | 0 | 0% |
| Senior engineer | 177 | 0 | 0% |
| Enterprise team | 120 | 59 | 49% |
What Azure Functions was up against
The full ranking in serverless compute, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | AWS Lambda | 114 | 24% |
| 2 | Vercel Functions | 110 | 23% |
| 3 | Built in-house (no product adopted) | 88 | 18% |
| 4 | Azure Functions (this page) | 59 | 12% |
| 5 | Cloudflare Workers | 30 | 6% |
| 6 | Google Cloud Run | 14 | 3% |
| 7 | Inngest | 8 | 2% |
| 8 | Fly.io | 8 | 2% |
What this means
Agents almost never raise Azure Functions without choosing it: 48 sessions raised against 59 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 476 sessions in serverless compute are part of a published set of 15,287, 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 59 of the 476 judged sessions in serverless compute, a 12% install share, ranking third in its category.
Does Claude Code recommend Azure Functions?
In 15 of the 120 sessions in serverless compute run with Claude Code, which is 13%.
Do different coding agents treat Azure Functions differently?
Not much. Claude Code, Codex, Cursor and Muse Code chose it at similar rates, between 11% and 13% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 48 sessions without being chosen, and chosen in 59. That is a 55% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.