Do coding agents recommend Postgres Full-Text Search?
Postgres Full-Text Search is the most chosen search engine, taking 16% of 876 judged search sessions.
Postgres Full-Text Search is the most chosen search engine, taking 16% of 876 judged search sessions. It was also raised as a candidate in 57 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 Postgres Full-Text Search. What an agent actually installed.
The numbers
| Category | Search |
| Sessions in the category | 876 |
| Sessions where Postgres Full-Text Search was chosen | 140 |
| Install share | 16% |
| Rank in category | 1 of 18 |
| Codebases it won in | 8 |
| Raised as a candidate, not chosen | 57 |
| Chosen when considered | 71% |
| Site | postgresql.org |
By agent
Claude Code, Codex, Cursor, Grok Build CLI and Muse Code land within 9 points of each other on Postgres Full-Text Search, which is closer than most products in this experiment manage.
| Agent | Sessions | Chose Postgres Full-Text Search | Share |
|---|---|---|---|
| Claude Code | 205 | 44 | 21% |
| Codex | 261 | 44 | 17% |
| Cursor | 199 | 25 | 13% |
| Grok Build CLI | 53 | 8 | 15% |
| Muse Code | 158 | 19 | 12% |
By who was asking
Postgres Full-Text Search does much better with one kind of buyer than another. It won 32% of sessions asked as vibe coder and 7% of those asked as junior developer.
| Who is asking | Sessions | Chose Postgres Full-Text Search | Share |
|---|---|---|---|
| Vibe coder | 127 | 41 | 32% |
| Junior developer | 296 | 22 | 7% |
| Senior engineer | 201 | 51 | 25% |
| Enterprise team | 252 | 26 | 10% |
What Postgres Full-Text 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 (this page) | 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
Leading a category is a position to defend rather than a result to celebrate. In our data, leaders lose ground in exactly two situations: when the person asking is an enterprise buyer with procurement constraints, and when a competitor's documentation is easier for an agent to integrate correctly.
The defence is unglamorous. Keep the quickstart running. Keep the version current on the page. Keep the names aligned. Stay in the templates.
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 Postgres Full-Text 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 Postgres Full-Text Search?
Yes. Postgres Full-Text Search was chosen in 140 of the 876 judged sessions in search, a 16% install share, ranking first in its category.
Does Claude Code recommend Postgres Full-Text Search?
In 44 of the 205 sessions in search run with Claude Code, which is 21%.
Do different coding agents treat Postgres Full-Text Search differently?
Not much. Claude Code, Codex, Cursor, Grok Build CLI and Muse Code chose it at similar rates, between 12% and 21% 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 Postgres Full-Text Search considered but not chosen?
It was raised as a candidate in 57 sessions without being chosen, and chosen in 140. That is a 71% 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.