The honest answers.
What ran is, what it does today, and how it treats your data — no spin.
How is this different from Notion AI or Glean?
Two things. Every answer cites the exact source it came from, so you can check it — and when your sources disagree, it flags the conflict instead of picking one. And it doesn't just answer: it takes on real multi-step work, and anything that leaves your workspace waits for your approval.
What can it actually do today?
Connect Notion, Slack, Drive, Gmail, and Outlook into one workspace, ask across all of it with citations, and hand it multi-step work — build a document, reconcile figures, draft an outward message — behind an approval you control.
How long does it take to deploy?
Connect your existing tools and set up roles in an afternoon. Nothing to migrate.
Does ran train on our data?
No. Your documents are never used to train models — ours or anyone else's. Your data stays in your workspace, and nothing leaves it without your explicit approval.
How does ran decide who sees what?
You assign each person a role. Every answer is scoped to what that role is allowed to see — enforced in the database, so nothing surfaces to someone who shouldn't see it.
Can ran take actions, not just answer?
Yes. Ran can carry out multi-step tasks across your tools — but every external action waits for your approval before it runs.
How is pricing structured?
One flat rate per workspace — no seat counting. See the pricing page for details.
When does early access open?
Rolling. Once you're on the list you'll hear from Gabriel within a week.