From the experiment

Do coding agents recommend Microsoft Entra ID?

Microsoft Entra ID was chosen in 10% of 201 judged authentication sessions, ranking third. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Microsoft Entra ID was chosen in 10% of 201 judged authentication sessions, ranking third. It was also raised as a candidate in 10 further sessions without being chosen.

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

The numbers

CategoryAuthentication
Sessions in the category201
Sessions where Microsoft Entra ID was chosen21
Install share10%
Rank in category3 of 17
Codebases it won in2
Raised as a candidate, not chosen10
Chosen when considered68%
Siteentra.microsoft.com

By agent

The three agents agree closely on Microsoft Entra ID, choosing it at rates within 1 points of each other.

AgentSessionsChose Microsoft Entra IDShare
Claude Code65711%
Codex68710%
Cursor68710%

By who was asking

Microsoft Entra ID does much better with one kind of buyer than another. It won 48% of sessions asked as enterprise team and 0% of those asked as senior engineer.

Who is askingSessionsChose Microsoft Entra IDShare
Vibe coder2600%
Junior developer6200%
Senior engineer6900%
Enterprise team442148%

What Microsoft Entra ID was up against

The full ranking in authentication, from the same sessions:

#ProductRuns wonShare
1WorkOS AuthKit5326%
2Auth04623%
3Microsoft Entra ID (this page)2110%
4Built in-house (no product adopted)2110%
5Clerk2010%
6Better Auth84%
7Keycloak73%
8Google Identity31%

What this means

Agents almost never raise Microsoft Entra ID without choosing it: 10 sessions raised against 21 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 201 sessions in authentication 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 authentication run can be replayed on the board.

If you work on Microsoft Entra ID: 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 Microsoft Entra ID?

Yes. Microsoft Entra ID was chosen in 21 of the 201 judged sessions in authentication, a 10% install share, ranking third in its category.

Does Claude Code recommend Microsoft Entra ID?

In 7 of the 65 sessions in authentication run with Claude Code, which is 11%.

Do different coding agents treat Microsoft Entra ID differently?

Not much. The three agents chose it at similar rates, between 10% and 11% 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 Microsoft Entra ID considered but not chosen?

It was raised as a candidate in 10 sessions without being chosen, and chosen in 21. That is a 68% 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