LaunchDarkly, without opening LaunchDarkly.
What is on where, what depends on it, and who changed it last.
“@Ray is the new checkout flag on in production?”
What Ray can and cannot do in LaunchDarkly
Reading is free, because reading changes nothing. Everything that writes waits for you. The rest is not on Ray’s list.
Runs on its own
What Ray reads in LaunchDarkly
- Feature flags, their status in every environment, and what depends on them
- Projects, environments, and segments
- Experiments, scheduled changes, and the audit log
Reading changes nothing, so Ray never stops to ask whether it may look something up.
Asks first, every time
What Ray answers with
Ray reads LaunchDarkly and answers from it in the thread. Writing to LaunchDarkly is not switched on yet, so there is nothing here to approve.
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.
- Turn a flag on or off
- Create or delete a flag, environment, or segment
- Approve a change request
- Add or remove members and custom roles
How Ray works with LaunchDarkly
No workflow to build, and nothing to maintain when the work changes.
- 01
Connect LaunchDarkly
LaunchDarkly 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
Ray answers where you asked
Ray only reads LaunchDarkly, so there is nothing here to approve. It looks up what it needs and replies in the thread.
Priya
@Ray the checkout bug is back. Take a look in LaunchDarkly, and tell Dana it is being looked at.
Ray
Checked LaunchDarkly. The spec was last edited on Tuesday and the open question about refunds is still unanswered.
What does connecting LaunchDarkly to Ray actually do?
Ray is an AI teammate that works in your team chat, on Slack today. Connect LaunchDarkly and it can do the LaunchDarkly 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.
LaunchDarkly 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 LaunchDarkly. Every write still stops for approval first.
Security and permissions
- You paste the LaunchDarkly 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 LaunchDarkly in a message. Uninstall Ray and every connection it held is revoked.
More dev & deploys integrations
Ray uses them together in a single run when a request spans more than one.
Put Ray to work in LaunchDarkly.
Free to start, no credit card, and it asks before it acts.