From the experiment

Do coding agents recommend Azure AI Foundry Agent Service?

Azure AI Foundry Agent Service was chosen in 3% of 681 judged agent frameworks sessions, ranking eighth. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Azure AI Foundry Agent Service was chosen in 3% of 681 judged agent frameworks sessions, ranking eighth. It was also raised as a candidate in 8 further sessions without being chosen.

This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in agent frameworks inside a realistic codebase. Not what a chat assistant says about Azure AI Foundry Agent Service. 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 agent frameworks in general, and the splits below cannot separate the two. Treat them as a description of that repository.

The numbers

CategoryAgent frameworks
Sessions in the category681
Sessions where Azure AI Foundry Agent Service was chosen19
Install share3%
Rank in category8 of 35
Codebases it won in1
Raised as a candidate, not chosen8
Chosen when considered70%
Siteai.azure.com

By agent

With 19 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 Azure AI Foundry Agent ServiceShare
Claude Code23700%
Codex243115%
Cursor20184%

By who was asking

Azure AI Foundry Agent Service does much better with one kind of buyer than another. It won 18% of sessions asked as enterprise team and 0% of those asked as senior engineer.

Who is askingSessionsChose Azure AI Foundry Agent ServiceShare
Vibe coder16300%
Junior developer15700%
Senior engineer25400%
Enterprise team1071918%

What Azure AI Foundry Agent Service was up against

The full ranking in agent frameworks, from the same sessions:

#ProductRuns wonShare
1Built in-house (no product adopted)17025%
2Vercel AI SDK9514%
3Cursor SDK9414%
4Inngest507%
5Temporal294%
6Prism284%
7OpenAI Agents SDK244%
8LangGraph233%

What this means

Agents almost never raise Azure AI Foundry Agent Service without choosing it: 8 sessions raised against 19 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 681 sessions in agent frameworks 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 agent frameworks run can be replayed on the board.

If you work on Azure AI Foundry Agent Service: 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 AI Foundry Agent Service?

Yes. Azure AI Foundry Agent Service was chosen in 19 of the 681 judged sessions in agent frameworks, a 3% install share, ranking eighth in its category.

Does Claude Code recommend Azure AI Foundry Agent Service?

In 0 of the 237 sessions in agent frameworks run with Claude Code, which is 0%.

Do different coding agents treat Azure AI Foundry Agent Service differently?

Not much. The three agents chose it at similar rates, between 0% and 5% 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 AI Foundry Agent Service considered but not chosen?

It was raised as a candidate in 8 sessions without being chosen, and chosen in 19. That is a 70% 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