How to get picked for databases by coding agents
Neon took 66% of 356 judged databases sessions. What the numbers say a vendor in this category should do.
If you sell databases, this page is the part of the market no dashboard shows you: what a coding agent does when a developer asks for databases and never compares vendors.
The numbers come from 356 judged sessions with Claude Code, Codex and Cursor, spread across 6 realistic codebases, with every session read by a judge.
What coding agents choose for databases
Across 356 judged sessions, Neon was chosen most often, in 66% of runs. Azure SQL Database was second with 10%.
| # | Product | Runs won | Share |
|---|---|---|---|
| 1 | Neon | 236 | 66% |
| 2 | Azure SQL Database | 35 | 10% |
| 3 | Azure Database for PostgreSQL Flexible Server | 29 | 8% |
| 4 | Amazon RDS for PostgreSQL | 17 | 5% |
| 5 | Supabase | 10 | 3% |
| 6 | MotherDuck | 7 | 2% |
| 7 | Scaleway Managed Database for PostgreSQL | 7 | 2% |
| 8 | Aiven | 5 | 1% |
| 9 | ClickHouse Cloud | 4 | 1% |
| 10 | DigitalOcean Managed PostgreSQL | 2 | 1% |
Full board, every run replayable: the databases leaderboard.
What the shape of this category means
One product takes 66% of runs. This category is close to decided, and a challenger does not win it with content this quarter.
Neon is in the training data, in the templates and in the repositories. At 66% of 356 sessions an agent reaches for it without deliberating.
No amount of writing changes that this quarter. What Azure SQL Database and the rest of the field can do is narrow: there are always requests the default fits badly, and those are winnable in full.
What does work is narrowing. Find the requests where the leader is a bad fit and own those completely. Regional requirements, a pricing model the leader does not offer, a compliance constraint, a stack the leader supports poorly. Write those pages in the words the request uses.
And check the persona split below. A category can be decided for one kind of buyer and open for another.
The agents do not agree with each other
In this category all three agents put Neon first, which is less common than it sounds: across the eighteen categories we measured, Claude Code and Codex disagreed on the leader in nine of them.
| Agent | Runs | Picked most often |
|---|---|---|
| Claude Code | 129 | Neon (87) |
| Codex | 103 | Neon (63) |
| Cursor | 124 | Neon (86) |
Even where they agree, they get there differently. Codex ran a web search in 53% of decision runs and Claude Code in 1.6%, so what you publish reaches one of them in half its databases sessions and the other in almost none.
Who is asking changes the answer
Every request was written as a specific kind of person. In this category Neon led for every persona, which is a sign of a strong default.
| Who is asking | Runs | Picked most often |
|---|---|---|
| Vibe coder | 60 | Neon |
| Junior developer | 106 | Neon |
| Senior engineer | 190 | Neon |
What you are really competing against
In this category agents never chose to build it themselves. Every session ended with a product. That is good news: you are in a straight vendor comparison, and the levers that work are the ones you control.
Considered, and never chosen
Because the judge records every product an agent raised and not only the one it picked, this board also shows who kept reaching the shortlist and losing. In databases the clearest case is Turso: on the table in 105 sessions, chosen in none.
| Product | Raised in | Chosen in |
|---|---|---|
| Turso | 105 sessions | 0 |
| DuckDB | 68 sessions | 0 |
| BigQuery | 66 sessions | 0 |
| PlanetScale | 63 sessions | 0 |
| MongoDB Atlas | 58 sessions | 0 |
Being rejected is a better position than being unknown, and a cheaper one to fix. The product is already in the agent's head and on the list. Whatever ended those 360 sessions is recorded in each transcript, one reason at a time.
What to do about it in databases
- Skip the build-versus-buy argument. No databases session in this experiment ended with the agent writing its own implementation. Every one adopted a product, so the whole contest is against the other names in the table above.
- Do not attack Neon head on. At 66% it is the default an agent reaches for without deliberating. Find the requests where it fits badly, which in our data means regional requirements, a pricing model it does not offer, a compliance constraint or a stack it supports poorly, and own those in the words the request uses.
The work that applies to every category rather than to this one is written up separately: audit your documentation, write a quickstart an agent can follow, and how to measure install share.
Every database on this board
One page per product, with its install share, the per-agent split, and how often it was raised without being chosen.
- Do coding agents recommend Neon? — chosen in 66% of sessions
- Do coding agents recommend Azure SQL Database? — chosen in 10% of sessions
- Do coding agents recommend Azure Database for PostgreSQL Flexible Server? — chosen in 8% of sessions
- Do coding agents recommend Amazon RDS for PostgreSQL? — chosen in 5% of sessions
- Do coding agents recommend Supabase? — chosen in 3% of sessions
- Do coding agents recommend PostgreSQL? — raised in 339 sessions, chosen in none
- Do coding agents recommend SQLite? — raised in 319 sessions, chosen in none
- Do coding agents recommend Turso? — raised in 105 sessions, chosen in none
- Do coding agents recommend DuckDB? — raised in 68 sessions, chosen in none
- Do coding agents recommend BigQuery? — raised in 66 sessions, chosen in none
- Do coding agents recommend PlanetScale? — raised in 63 sessions, chosen in none
Where these numbers come from
356 judged sessions in databases across 6 codebases, part of a published set of 5,292. Real coding agents at pinned versions, in sandboxes, inside realistic codebases, with a simulated project owner in the loop and a blind judge on every session. The full method is on one page: how we measured this.
Every databases run can be replayed on the board.
<!-- generated by scripts/write-data-pages.mjs -->
Common questions
How many codebases is this based on?
356 judged sessions across 6 realistic codebases. A category only runs on repositories where its seam is open, so coverage differs: some categories ran on more than ten codebases and some on two.
What database do coding agents choose?
Across 356 judged sessions, Neon was chosen most often, in 66% of runs. Azure SQL Database was second with 10%. The result changes by agent and by who is asking.
Do Claude Code and Codex pick the same database?
Yes. All three agents we tested put Neon first in this category, which is unusual: they disagree in half of the categories we measured.
How often do agents build databases themselves instead of installing something?
Never, in this category. Every one of the sessions ended with the agent adopting a product rather than writing the code itself.
How can a vendor improve its position here?
Make the quickstart run when pasted, state the current version on the documentation page, use one name across product, package and import, write pages for the symptoms users describe rather than only the category name, and get into the repository through templates and framework integrations.
Which databases do agents consider but never choose?
Turso (raised in 105 sessions, chosen in none), DuckDB (raised in 68 sessions, chosen in none), BigQuery (raised in 66 sessions, chosen in none), PlanetScale (raised in 63 sessions, chosen in none), MongoDB Atlas (raised in 58 sessions, chosen in none). Being considered and not chosen is a different problem from being unknown, and it is usually fixable.
Where this comes from
Armature ran 5,292 judged sessions with Claude Code, Codex and Cursor inside 51 realistic codebases, and published every run. The numbers on this page come from that work.