Do coding agents recommend Playwright?
Coding agents raised Playwright in 68 of 639 judged AI search sessions and chose it alone in none of them, and only as part of a joint choice in 1.
Coding agents raised Playwright in 68 of 639 judged AI search sessions and chose it alone in none of them, and only as part of a joint choice in 1.
This page reports what happened when Claude Code, Codex, Cursor, Grok Build CLI and Muse Code had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about Playwright. What an agent actually installed.
The numbers
| Category | AI search |
| Sessions in the category | 639 |
| Sessions where Playwright was chosen | 0 |
| Install share | 0% |
| Raised as a candidate, not chosen | 68 |
| Chosen when considered | 0% |
| Site | playwright.dev |
Which agents raised Playwright
Every agent considered it and none chose it alone. Grok Build CLI raised it most often, in 26% of its AI search sessions.
| Agent | Sessions | Raised Playwright | Chose it alone |
|---|---|---|---|
| Claude Code | 140 | 13 (9%) | 0 |
| Codex | 192 | 23 (12%) | 0 |
| Cursor | 136 | 19 (14%) | 0 |
| Grok Build CLI | 35 | 9 (26%) | 0 |
| Muse Code | 136 | 4 (3%) | 0 |
Which buyers it came up for
It surfaced most for requests written as vibe coder, in 14% of those sessions. Knowing which buyer already has the product in mind tells you which pages to fix first.
| Who is asking | Sessions | Raised it |
|---|---|---|
| Vibe coder | 106 | 15 (14%) |
| Junior developer | 208 | 15 (7%) |
| Senior engineer | 157 | 21 (13%) |
| Enterprise team | 168 | 17 (10%) |
What Playwright was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Exa | 92 | 14% |
| 2 | Brave Search API | 89 | 14% |
| 3 | Anthropic web search | 86 | 13% |
| 4 | Tavily | 79 | 12% |
| 5 | OpenAI web search | 32 | 5% |
| 6 | Built in-house (no product adopted) | 32 | 5% |
| 7 | Firecrawl | 31 | 5% |
| 8 | Parallel | 29 | 5% |
What this means
Raised 68 times and never chosen alone is a specific, diagnosable result, and a better starting position than being unknown. The agent has the product in mind. It reached the shortlist 68 times and made it into 1 joint choice, but never into a choice of its own.
In our data the causes, in the order they occur:
- The quickstart does not run when pasted, so the agent abandoned it mid-integration.
- The documentation describes an interface that changed, so the generated code failed.
- The product name and the package name differ, so the install step went wrong.
- The fit was genuinely wrong for the repository, which is fine and worth knowing.
All but the last are fixable in days, and the reason is written down in the session transcript.
Where these numbers come from
The 639 sessions in AI search are part of a published set of 15,000, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every AI search run can be replayed on the board.
If you work on Playwright: 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 Playwright?
They raise it but rarely choose it. Across 68 sessions where Playwright came up as a candidate, agents never chose it alone; it was part of a joint choice in 1.
Does Claude Code recommend Playwright?
In 0 of the 140 sessions in AI search run with Claude Code, which is 0%.
Do different coding agents treat Playwright differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 0% and 0% of their runs.
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.
Where this comes from
Armature ran 15,000 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.