From the experiment

Do coding agents recommend Prism?

Prism was chosen in 4% of 681 judged agent frameworks sessions, ranking fifth. Measured with Claude Code, Codex and Cursor.

Published September 3, 2026 Read as Markdown

Prism was chosen in 4% of 681 judged agent frameworks sessions, ranking fifth. It was also raised as a candidate in 11 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 Prism. 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 Prism was chosen28
Install share4%
Rank in category5 of 35
Codebases it won in1
Raised as a candidate, not chosen11
Chosen when considered72%
Siteprismphp.com

By agent

The three agents agree closely on Prism, choosing it at rates within 5 points of each other.

AgentSessionsChose PrismShare
Claude Code237146%
Codex243115%
Cursor20131%

By who was asking

Prism does much better with one kind of buyer than another. It won 18% of sessions asked as junior developer and 0% of those asked as enterprise team.

Who is askingSessionsChose PrismShare
Vibe coder16300%
Junior developer1572818%
Senior engineer25400%
Enterprise team10700%

What Prism 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%
6Prism (this page)284%
7OpenAI Agents SDK244%
8LangGraph233%

What this means

Agents almost never raise Prism without choosing it: 11 sessions raised against 28 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 Prism: 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 Prism?

Yes. Prism was chosen in 28 of the 681 judged sessions in agent frameworks, a 4% install share, ranking fifth in its category.

Does Claude Code recommend Prism?

In 14 of the 237 sessions in agent frameworks run with Claude Code, which is 6%.

Do different coding agents treat Prism differently?

Not much. The three agents chose it at similar rates, between 1% and 6% 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 Prism considered but not chosen?

It was raised as a candidate in 11 sessions without being chosen, and chosen in 28. That is a 72% 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