From the experiment

Do coding agents recommend Resolve AI?

Resolve AI was chosen in 20% of 179 judged ai sre sessions, ranking second. Measured with Claude Code, Codex and Cursor.

Published September 15, 2026 Read as Markdown

Resolve AI was chosen in 20% of 179 judged ai sre sessions, ranking second. It was also raised as a candidate in 77 further sessions without being chosen.

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

The numbers

CategoryAi sre
Sessions in the category179
Sessions where Resolve AI was chosen35
Install share20%
Rank in category2 of 26
Codebases it won in4
Raised as a candidate, not chosen77
Chosen when considered31%
Siteresolve.ai

By agent

The three agents treat Resolve AI very differently. Codex chose it in 35% of its sessions in this category and Cursor in 8%, a spread of 27 points.

AgentSessionsChose Resolve AIShare
Claude Code71710%
Codex722535%
Cursor3638%

A single blended install share would report the midpoint and hide both ends. If most of your users run Cursor, your real position here is 8%, not 20%.

By who was asking

Resolve AI does much better with one kind of buyer than another. It won 63% of sessions asked as senior engineer and 0% of those asked as vibe coder.

Who is askingSessionsChose Resolve AIShare
Vibe coder3000%
Junior developer6058%
Senior engineer301963%
Enterprise team591119%

What Resolve AI was up against

The full ranking in ai sre, from the same sessions:

#ProductRuns wonShare
1Sentry Seer4726%
2Resolve AI (this page)3520%
3Datadog Bits AI Dev Agent + Datadog Bits Investigation2615%
4Cursor Automations158%
5Claude Code GitHub Action116%
6Cursor Cloud Agents95%
7incident.io AI SRE42%
8Cursor Automations + Cursor Cloud Agents32%

What this means

A solid second or third position in a category means the agent is genuinely choosing rather than reaching automatically. That is a winnable position, because the inputs it uses can be changed.

The fastest gains are usually in the sessions that were nearly won: read them, find the step where the agent moved on, and fix that step.

Where these numbers come from

The 179 sessions in ai sre are part of a published set of 7,852, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.

Every ai sre run can be replayed on the board.

If you work on Resolve AI: 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 Resolve AI?

Yes. Resolve AI was chosen in 35 of the 179 judged sessions in ai sre, a 20% install share, ranking second in its category.

Does Claude Code recommend Resolve AI?

In 7 of the 71 sessions in ai sre run with Claude Code, which is 10%.

Do different coding agents treat Resolve AI differently?

Yes, and by a wide margin. Codex chose it in 35% of its runs and Cursor in 8%.

How was this measured?

Real coding agents at pinned versions were run in sandboxes inside 90 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 Resolve AI considered but not chosen?

It was raised as a candidate in 77 sessions without being chosen, and chosen in 35. That is a 31% conversion from considered to chosen.

Where this comes from

Armature ran 7,852 judged sessions with Claude Code, Codex and Cursor inside 90 realistic codebases, and published every run. The numbers on this page come from that work.

Read next

All library pages