§ Suite · ServicesFive tools · one workspace
What Illuma actually does.
Each service is one instrument. Pick the tab to see the tool, how it works, and what makes it different.
Output includes
- Ranked moves — highest-impact first
- Per-school breakdown for every candidate move
- Counterfactual perturbation of the same ML model as the chances calc
- Essays + activities included as heuristic overlays (tagged as such)
- Compass visualization — needle swings to whatever move you hover
Under the hood
ML models + calibration layers, not a ChatGPT wrapper.
1
Counterfactual engine
For each candidate move, perturb the profile and recompute admit probability at every school on your list.
2
Per-school delta view
Not just 'this helps' — 'this helps 4pp at Berkeley and 1pp at Purdue.'
3
Honest heuristic tag
Essay and 'add a national award' moves aren't in the ML feature vector. They're flat-delta heuristics, clearly marked so you don't mistake them for model output.
Ready to try it?
First eval free. No credit card required to sign up.