Neon, without opening Neon.
Branch the database from the thread, and see what changed.
- Free to start
- No card
- Every write waits for you
- One key for the workspace
Ask in your own words.
Nothing to configure and no builder to open. Copy one of these into a thread, swap in your own Neon details, and Ray takes it from there.
@Ray cut me a branch off main for the pricing migration.
@Ray what is different between the staging schema and main?
@Ray how much is the database costing us this month?
@Ray snapshot main before I run the migration.
What Ray can and cannot do in Neon
Reading is free, because reading changes nothing. Everything that writes waits for you. The rest is not on Ray’s list.
19 reads wired, 3 actions that wait for a human.
Runs on its own
What Ray reads in Neon
- Projects and their branches, with a count when you only want the number
- The schema on any branch, and the difference between two of them
- Databases and endpoints on a branch, and whether the last operation finished
- What the project is consuming, and the snapshots and backup schedule behind it
Reading changes nothing, so Ray never stops to ask whether it may look something up.
Asks first, every time
What waits for your approval
- Cutting a new branch off a parent, for a piece of work or a preview
- Renaming a branch, and marking one protected
- Taking a snapshot of a branch at a point in time
Ray posts a card showing exactly what it is about to do. Nothing happens until someone clicks approve, and no setting turns that off.
Not on the list
Things Ray is never handed
These are left out during curation, so they are not something Ray could do and decides against. They are not in front of it at all.
- Reveal a role password or hand back a connection string, which carries one inside it
- Restore a branch or a snapshot, because that overwrites what is there now
- Mint, list or delete API keys, move projects between organisations, or change who is a member
Exactly what Ray will ask you to approve.
Not a category of permission. These are the Neon actions Ray can take, each one stopping in the thread with the real content before it happens.
- Create a Neon branch
- Rename or protect a Neon branch
- Snapshot a Neon branch
Create a Neon branch
Showing Branch name, Project id and Branch init source, each carrying the exact content that will land.
How Ray works with Neon
No workflow to build, and nothing to maintain when the work changes.
- 01
Connect Neon
Neon has no per-person login, so it takes one workspace key. Ray posts a connect card, you paste the key on Ray's own page rather than in Slack, and it covers the whole team from then on.
- 02
Ask in plain words
In the conversation you were already having. Nothing to build, no trigger to map, no tab to open.
- 03
Approve, and it lands
Reading runs on its own. Anything that creates, sends or spends stops first and shows you the exact content.
Priya
@Ray the checkout bug is back. Take a look in Neon, and tell Dana it is being looked at.
Create a Neon branch
- Waiting on
- your approval
Ray uses Neon together with the rest of your tools.
One ask can read Neon, cross-reference what is in these, and land the finished result back in the thread. Not four connectors taking turns, one teammate with one memory.
What does connecting Neon to Ray actually do?
Ray is an AI teammate that works in your team chat, on Slack today. Connect Neon and it can do the Neon part of a request without anyone leaving the conversation: read what it needs, draft the change, and post it for approval before anything is written.
It is not a workflow builder. There is no trigger to configure and no automation to repair when your process shifts. You describe the outcome in the thread and Ray picks the actions, including actions in your other connected tools when the request spans more than one.
Neon has no per-person login, so it connects once with a single workspace key and covers the whole team. Ray reaches whatever that key reaches, which is worth scoping the way you want everyone to see Neon. Every write still stops for approval first.
Security and permissions
- You paste the Neon key on Ray’s own page, never in Slack. It goes straight to the connection and never reaches the model.
- Writes are gated in the execution path, not by a prompt. There is no setting that grants blanket approval.
- Each workspace is isolated at the database level, and that isolation is tested by trying to break it.
- An admin, or whoever connected it, can disconnect Neon in a message. Uninstall Ray and every connection it held is revoked.
Neon and Ray, answered
The questions teams ask before they connect Neon. Every answer is how this integration is built rather than a promise about it.
More dev & deploys integrations
Ray uses them together in a single run when a request spans more than one.
Put Ray to work in Neon.
Free to start, no credit card, and it asks before it acts.