Do coding agents recommend Azure AI Document Intelligence?
Azure AI Document Intelligence is the most chosen document processing, taking 24% of 801 judged document processing sessions.
Azure AI Document Intelligence is the most chosen document processing, taking 24% of 801 judged document processing sessions. It was also raised as a candidate in 146 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 document processing inside a realistic codebase. Not what a chat assistant says about Azure AI Document Intelligence. What an agent actually installed.
The numbers
| Category | Document processing |
| Sessions in the category | 801 |
| Sessions where Azure AI Document Intelligence was chosen | 193 |
| Install share | 24% |
| Rank in category | 1 of 42 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 146 |
| Chosen when considered | 57% |
| Site | azure.microsoft.com |
By agent
The agents treat Azure AI Document Intelligence very differently. Codex chose it in 32% of its sessions in this category and Claude Code in 11%, a spread of 21 points.
| Agent | Sessions | Chose Azure AI Document Intelligence | Share |
|---|---|---|---|
| Claude Code | 180 | 20 | 11% |
| Codex | 235 | 75 | 32% |
| Cursor | 180 | 47 | 26% |
| Grok Build CLI | 30 | 5 | 17% |
| Muse Code | 176 | 46 | 26% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Claude Code, your real position here is 11%, not 24%.
By who was asking
Azure AI Document Intelligence performs similarly across the four kinds of buyer, from 19% to 29%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Azure AI Document Intelligence | Share |
|---|---|---|---|
| Vibe coder | 68 | 14 | 21% |
| Junior developer | 327 | 62 | 19% |
| Senior engineer | 270 | 79 | 29% |
| Enterprise team | 136 | 38 | 28% |
What Azure AI Document Intelligence was up against
The full ranking in document processing, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Azure AI Document Intelligence (this page) | 193 | 24% |
| 2 | Anthropic Claude | 150 | 19% |
| 3 | Amazon Textract | 103 | 13% |
| 4 | Google Cloud Document AI | 49 | 6% |
| 5 | OpenAI models | 46 | 6% |
| 6 | Google Gemini | 45 | 6% |
| 7 | Docling | 24 | 3% |
| 8 | Apache PDFBox | 23 | 3% |
What this means
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
Where these numbers come from
The 801 sessions in document processing are part of a published set of 15,051, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every document processing run can be replayed on the board.
If you work on Azure AI Document Intelligence: 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 Document Intelligence?
Yes. Azure AI Document Intelligence was chosen in 193 of the 801 judged sessions in document processing, a 24% install share, ranking first in its category.
Does Claude Code recommend Azure AI Document Intelligence?
In 20 of the 180 sessions in document processing run with Claude Code, which is 11%.
Do different coding agents treat Azure AI Document Intelligence differently?
Yes, and by a wide margin. Codex chose it in 32% of its runs and Claude Code in 11%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 92 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 Document Intelligence considered but not chosen?
It was raised as a candidate in 146 sessions without being chosen, and chosen in 193. That is a 57% conversion from considered to chosen.
Where this comes from
Armature ran 15,051 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 92 realistic codebases, and published every run. The numbers on this page come from that work.