Every screen in CeliaConnect, explained.

What is CeliaConnect?

An AI assistant that reads every record overnight — without ever seeing a name.

CeliaConnect is an AI assistant that reads every prospective student’s record overnight — without ever seeing names, emails, phone numbers, addresses, or any other personally identifying information — and produces five outputs per student: Engagement (how active they are in the funnel right now), Readiness (how close their application file is to a decision), Yield (how likely they are to enroll if admitted), Risk (a low / medium / high / critical tier that combines the three), and a recommended next action (the single most useful thing a counselor should do next, with a one-line reason).

The four scores build on each other rather than standing alone. Engagement tells you whether a student is paying attention right now. Readiness tells you whether their file is complete enough to decide. Yield tells you whether they’re likely to say yes if you do. Risk combines all three into a single priority tier so you can surface the students who need attention today without reading every record. A student who is highly engaged but low-yield looks very different from one who is high-readiness but disengaged — Celia distinguishes them and explains why.

Every score and recommended action appears on the Celia tab inside each student’s record. Your whole team can also filter and sort the funnel by any score from the main student list — “show me all critical-risk students in the inquiry stage” becomes a single filter rather than a manual file review. The recommended action travels with the record into Slate’s Source Format so counselors working inside Slate see the same guidance without switching apps.

CeliaConnect runs overnight by default. Every morning, scores and recommended actions reflect the previous day’s Slate activity. Your administrator can configure more frequent runs from the Flows dashboard if your Slate data refreshes intraday. The AI sees only anonymized signals from your institution’s own data — a strict architectural guarantee, not a policy promise — so every analysis stays inside your tenant boundary and FERPA-aligned by design.