Do coding agents recommend Atlas Search?
Atlas Search was chosen in 4% of 876 judged search sessions, ranking eighth. Measured with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code.
Atlas Search was chosen in 4% of 876 judged search sessions, ranking eighth. It was also raised as a candidate in 56 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 search inside a realistic codebase. Not what a chat assistant says about Atlas Search. 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 search in general, and the splits below cannot separate the two. Treat them as a description of that repository.
The numbers
| Category | Search |
| Sessions in the category | 876 |
| Sessions where Atlas Search was chosen | 35 |
| Install share | 4% |
| Rank in category | 8 of 18 |
| Codebases it won in | 1 |
| Raised as a candidate, not chosen | 56 |
| Chosen when considered | 38% |
| Site | mongodb.com |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code agree closely on Atlas Search, choosing it at rates within 2 points of each other.
| Agent | Sessions | Chose Atlas Search | Share |
|---|---|---|---|
| Claude Code | 205 | 6 | 3% |
| Codex | 261 | 12 | 5% |
| Cursor | 199 | 8 | 4% |
| Grok Build CLI | 53 | 2 | 4% |
| Muse Code | 158 | 7 | 4% |
By who was asking
Atlas Search performs similarly across the four kinds of buyer, from 0% to 12%. That is unusual: the category leader changed with the persona in 24 of the 31 categories we measured.
| Who is asking | Sessions | Chose Atlas Search | Share |
|---|---|---|---|
| Vibe coder | 127 | 0 | 0% |
| Junior developer | 296 | 35 | 12% |
| Senior engineer | 201 | 0 | 0% |
| Enterprise team | 252 | 0 | 0% |
What Atlas Search was up against
The full ranking in search, from the same sessions:
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Built in-house (no product adopted) | 208 | 24% |
| 2 | Postgres Full-Text Search | 140 | 16% |
| 3 | OpenSearch | 104 | 12% |
| 4 | Typesense | 83 | 9% |
| 5 | Meilisearch | 74 | 8% |
| 6 | Oracle Indexed Search | 46 | 5% |
| 7 | Algolia | 45 | 5% |
| 8 | Elasticsearch | 42 | 5% |
What this means
Atlas Search was raised in 56 sessions and chosen in 35. That ratio is balanced enough that the ceiling is presence rather than integration: the product converts reasonably when it is on the table, and it is not on the table often enough.
Where these numbers come from
The 876 sessions in search are part of a published set of 15,287, run with real coding agents inside realistic codebases and judged blind. The full method is on one page: how we measured this.
Every search run can be replayed on the board.
If you work on Atlas 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 Atlas Search?
Yes. Atlas Search was chosen in 35 of the 876 judged sessions in search, a 4% install share, ranking eighth in its category.
Does Claude Code recommend Atlas Search?
In 6 of the 205 sessions in search run with Claude Code, which is 3%.
Do different coding agents treat Atlas Search differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 3% and 5% of their runs.
How was this measured?
Real coding agents at pinned versions were run in sandboxes inside 110 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 Atlas Search considered but not chosen?
It was raised as a candidate in 56 sessions without being chosen, and chosen in 35. That is a 38% conversion from considered to chosen.
Where this comes from
Armature ran 15,287 judged sessions with Claude Code, Codex, Cursor, Grok Build CLI and Muse Code inside 110 realistic codebases, and published every run. The numbers on this page come from that work.