AI Intelligence
Institution Intelligence
AI insight
Institution insight
- What changed
- Attendance and collection indicators moved in different directions this period.
- Why it matters
- An institution-level average hides the classes and departments that are actually moving.
- Recommended action
- Start with the groups that diverged furthest from their own baseline, not from the institution average.
Supporting signals
- Groups above baseline6
- Groups below baseline3
- Period comparedLast 30 days
Signals are produced by deterministic analytics. AI explains them and proposes an action; it does not compute them.
How it works
Signals first, then reasoning.
Baselines, not averages
Every class, department, and cohort is compared against its own history. A group that has always run at 88% is not an exception; a group that just moved from 94% to 88% is.
Exception detection
The platform surfaces what moved outside its usual range, rather than listing every metric it holds and leaving the reading to you.
Cross-signal correlation
Attendance, academic, and operational indicators are read together, so a finding carries the other signals that moved with it.
Explained, not asserted
Each finding states what changed, why it matters, and the supporting signals behind it — traceable back to the records that produced them.
Scoped by role
Management sees the institution. Other roles see only the part of it their permissions cover.
Deterministic underneath
Every number comes from the analytics layer. AI interprets and explains; it never performs the calculation.
In the product
What a principal opens it for.
- Attendance trends across classes and departments
- Fee collection against the expected trend
- Academic indicators by group
- Operational changes since the last period
- Areas that moved outside their usual range
- Supporting signals behind every finding