Do coding agents recommend Exa?
Exa was chosen in 14% of 277 judged AI search sessions, ranking second. Measured with Claude Code, Codex and Cursor.
Exa was chosen in 14% of 277 judged AI search sessions, ranking second. It was also raised as a candidate in 15 further sessions without being chosen.
This page reports what happened when Claude Code, Codex and Cursor had to solve a problem in AI search inside a realistic codebase. Not what a chat assistant says about Exa. What an agent actually installed.
The numbers
| Category | AI search |
| Sessions in the category | 277 |
| Sessions where Exa was chosen | 38 |
| Install share | 14% |
| Rank in category | 2 of 27 |
| Codebases it won in | 9 |
| Raised as a candidate, not chosen | 15 |
| Chosen when considered | 72% |
| Site | exa.ai |
By agent
The three agents treat Exa very differently. Codex chose it in 23% of its sessions in this category and Claude Code in 4%, a spread of 19 points.
| Agent | Sessions | Chose Exa | Share |
|---|---|---|---|
| Claude Code | 92 | 4 | 4% |
| Codex | 96 | 22 | 23% |
| Cursor | 89 | 12 | 13% |
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 4%, not 14%.
By who was asking
Exa does much better with one kind of buyer than another. It won 18% of sessions asked as vibe coder and 2% of those asked as enterprise team.
| Who is asking | Sessions | Chose Exa | Share |
|---|---|---|---|
| Vibe coder | 44 | 8 | 18% |
| Junior developer | 117 | 19 | 16% |
| Senior engineer | 68 | 10 | 15% |
| Enterprise team | 48 | 1 | 2% |
What Exa was up against
The full ranking in AI search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Anthropic web search | 56 | 20% |
| 2 | Exa (this page) | 38 | 14% |
| 3 | Brave Search API | 31 | 11% |
| 4 | Tavily | 21 | 8% |
| 5 | OpenAI web search | 16 | 6% |
| 6 | Firecrawl | 14 | 5% |
| 7 | Parallel | 13 | 5% |
| 8 | Built in-house (no product adopted) | 13 | 5% |
What this means
Agents almost never raise Exa without choosing it: 15 sessions raised against 38 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 277 sessions in AI search are part of a published set of 7,025, 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 Exa: 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 Exa?
Yes. Exa was chosen in 38 of the 277 judged sessions in AI search, a 14% install share, ranking second in its category.
Does Claude Code recommend Exa?
In 4 of the 92 sessions in AI search run with Claude Code, which is 4%.
Do different coding agents treat Exa differently?
Yes, and by a wide margin. Codex chose it in 23% of its runs and Claude Code in 4%.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 77 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 Exa considered but not chosen?
It was raised as a candidate in 15 sessions without being chosen, and chosen in 38. That is a 72% conversion from considered to chosen.
Where this comes from
Armature ran 7,025 judged sessions with Claude Code, Codex and Cursor inside 77 realistic codebases, and published every run. The numbers on this page come from that work.