PostHog, without opening PostHog.
Read-only product analytics: trends, funnels, flags, experiments and surveys (shared workspace key).
In your channel
Ask Ray for something in PostHog and it posts this card in the thread. One click, and the task you asked for carries on where it left off.
What Ray can and cannot do in PostHog
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 PostHog
- Get event definitions
- Get event definition by name
- Get experiment details
- Get feature flag details
- Get feature flag status
- Get funnel insights in project
- Get surveys stats
- Get survey response statistics
- List and manage project annotations
- List and manage project feature flags
- List project actions
- List project dashboards
- List project experiments
- List project surveys
- Project funnel advanced analytics
- Project trend analytics
- Retrieve project action details by id
- Retrieve project annotation details
- Retrieve project cohorts with pagination
- Retrieve project cohort details
- Retrieve project event details by id
- Retrieve project event values
- Retrieve project experiment results
- Retrieve project insights with pagination
- Retrieve project insight details
- Retrieve project trend insights
- Retrieve specific project dashboard details
- Retrieve survey details with uuid and project id
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 PostHog and answers from it in the thread. Writing to PostHog 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.
- Delete alert
- Archive survey response
- Run endpoint
- Delete customer profile config
- Cancel project insights
How Ray works with PostHog
No workflow to build, and nothing to maintain when the work changes.
- 01
Connect PostHog
One click, right where you asked. Ray posts a connect card, you authorise PostHog with your own account, and the work you asked for picks up where it left off.
- 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 PostHog, 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 PostHog, and tell Dana it is being looked at.
Ray
Checked PostHog. The spec was last edited on Tuesday and the open question about refunds is still unanswered.
What does connecting PostHog to Ray actually do?
Ray is an AI teammate that works in your team chat, on Slack today. Connect PostHog and it can do the PostHog 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.
Every person on the team connects their own PostHog account, so Ray can only reach what that person can already reach, and the history in PostHog shows who actually asked.
Security and permissions
- You authorise PostHog on its own login screen. Your password never passes through Ray.
- 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.
- Disconnect PostHog in a message, or uninstall Ray and every connection it held is revoked.
More analytics & bi integrations
Ray uses them together in a single run when a request spans more than one.
Put Ray to work in PostHog.
Free to start, no credit card, and it asks before it acts.