Do coding agents recommend Anthropic web search?
Anthropic web search was chosen in 13% of 639 judged AI search sessions, ranking third. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Anthropic web search was chosen in 13% of 639 judged AI search sessions, ranking third. It was also raised as a candidate in 25 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 AI search inside a realistic codebase. Not what a chat assistant says about Anthropic web search. What an agent actually installed.
The numbers
| Category | AI search |
| Sessions in the category | 639 |
| Sessions where Anthropic web search was chosen | 86 |
| Install share | 13% |
| Rank in category | 3 of 42 |
| Codebases it won in | 12 |
| Raised as a candidate, not chosen | 25 |
| Chosen when considered | 77% |
| Site | anthropic.com |
By agent
The agents treat Anthropic web search very differently. Claude Code chose it in 58% of its sessions in this category and Grok Build CLI in 0%, a spread of 58 points.
| Agent | Sessions | Chose Anthropic web search | Share |
|---|---|---|---|
| Claude Code | 140 | 81 | 58% |
| Codex | 192 | 1 | 1% |
| Cursor | 136 | 1 | 1% |
| Grok Build CLI | 35 | 0 | 0% |
| Muse Code | 136 | 3 | 2% |
A single blended install share would report the midpoint and hide both ends. If most of your users run Grok Build CLI, your real position here is 0%, not 13%.
By who was asking
Anthropic web search performs similarly across the four kinds of buyer, from 7% to 16%. That is unusual: the category leader changed with the persona in 23 of the 31 categories we measured.
| Who is asking | Sessions | Chose Anthropic web search | Share |
|---|---|---|---|
| Vibe coder | 106 | 17 | 16% |
| Junior developer | 208 | 33 | 16% |
| Senior engineer | 157 | 25 | 16% |
| Enterprise team | 168 | 11 | 7% |
What Anthropic web search 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 (this page) | 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
Agents almost never raise Anthropic web search without choosing it: 25 sessions raised against 86 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 639 sessions in AI search 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 AI search run can be replayed on the board.
If you work on Anthropic web search: 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 Anthropic web search?
Yes. Anthropic web search was chosen in 86 of the 639 judged sessions in AI search, a 13% install share, ranking third in its category.
Does Claude Code recommend Anthropic web search?
In 81 of the 140 sessions in AI search run with Claude Code, which is 58%.
Do different coding agents treat Anthropic web search differently?
Yes, and by a wide margin. Claude Code chose it in 58% of its runs and Grok Build CLI in 0%.
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 Anthropic web search considered but not chosen?
It was raised as a candidate in 25 sessions without being chosen, and chosen in 86. That is a 77% 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.