← Voyacover
Built for university completion teams
Persist

They already earned the credits. Something else stopped them.

Roughly 39 million Americans hold college credit and federal loan debt but no finished credential. Persist is the eligibility engine that tells each of them, and you, exactly which rule is blocking them and which pathway still works.

Engine built and tested·  proposing a pilot with one institution
01

The stop-out problem

Your hardest-to-recover students are the ones who nearly finished.

A near-completor is a student you already admitted, already taught, and already have a transcript for. They stopped one or two terms short, and now they carry the debt without the credential that would have paid for it. Re-enrolling one of them is cheaper than recruiting a new applicant, and it moves your completion rate instead of just your headcount.

What makes this urgent rather than perennial: the One Big Beautiful Bill Act (H.R.1) took effect July 1, 2026, and created a new set of stop-out triggers. Grad PLUS is gone for borrowers whose enrollment continuity is broken. Lifetime federal loan caps now apply to debt already borrowed, not just new borrowing. Both of those turn a returning student into an ineligible one, silently, and the student usually finds out from a denial letter rather than an advisor.

Which means a share of your own stopped-out population became harder to re-enroll this month, and nobody has the list.

02

What Persist is

A rules engine, not a chatbot.

Financial-aid eligibility is fragmented, effective-dated, and changes under people. So the core of Persist is a versioned encoding of the actual rules, and a deterministic evaluator that runs them. No language model sits in the decision path.

Versioned federal rules

Each rule is a dated record with its statutory citation, so an answer given today can be reproduced and defended a year from now, and a rule change is a diff instead of a rewrite.

Deterministic evaluation

The same student profile always produces the same flags and the same pathways. Every output traces back to the specific rule that produced it. Nothing is generated or guessed.

Pathways, not verdicts

Being blocked from federal borrowing is not the same as being unable to finish. The engine matches prior-learning credit, Workforce Pell, employer tuition benefits, and state completion programs against the student's actual situation.

8
federal rules encoded, each effective-dated and cited to OBBBA H.R.1
21
states with a verified statewide completion program, including NY
74
passing assertions in the engine test suite, run against composite profiles
0
language models in the decision path, by design
Students on campus

See it run

This is working code, not a deck.

Student intakeFederal rulesBlocking flagsPathway matchState programsOutcome logged
Student intake · composite profile
PA few questions and I'll tell you exactly what's standing between you and finishing. No forms, no appointment.
MI already know. I got denied.
PGrad PLUS, for the fall term?
MYes. No explanation. Just denied.
PWhen did your master's at the first school end, and when did you start the MBA?
MFinished May 2021. Started the MBA July 2022.
PThat's a 431-day gap, which breaks enrollment continuity under OBBBA, effective July 1, 2026. You're treated as a new borrower, and Grad PLUS doesn't exist for new borrowers anymore. The denial isn't about your credit or your record.
MSo that's it. I'm done.
PThat's one of two things blocking federal money. You've borrowed $105,000 in Grad PLUS across both schools, and the new lifetime cap counts debt you already hold, not just new borrowing.
MThen why are we still talking.
PBecause federal borrowing isn't the only way to finish. You have two years of graduate coursework behind you and you're in New Jersey. That's two moves that need no loan at all.
What the engine returned
BLOCKEDGrad PLUS eliminated, 431-day continuity break grad_plus_elimination_2026
BLOCKED$105,000 already borrowed, at or over the new lifetime cap lifetime_loan_caps_2026
PATHWAYPrior-learning-credit petition, ~3 weeks, ~$200, no new federal borrowing
NJSome College, No Degree Initiative, ask the registrar whether they're a grant recipient
PWant me to write the exact question to ask your registrar?

Every line she was told traces to a named rule. Here is the same profile run through the engine directly, which is what actually produced those four results.

persist · sample profile · run 2026-07-27
Case for: Maria (composite, sample profile)  (as of 2026-07-27)

Flags:
  [BLOCKING] (grad_plus_elimination_2026)
    You have prior Grad PLUS borrowing, but a 431-day gap in
    enrollment breaks continuity under OBBBA, H.R.1, effective
    2026-07-01. You're treated as a new borrower and Grad PLUS is
    not available to you, regardless of how close you are to
    finishing.

  [BLOCKING] (lifetime_loan_caps_2026)
    Total federal borrowing ($105,000) is at or over the new
    lifetime cap ($257,500 universal, $100,000 graduate-specific).
    This applies to debt already borrowed, not just new borrowing.

  [INFO] (pell_eligibility_cliffs_2026)
    SAI is under the $14,790 cutoff, Pell eligibility isn't
    blocked on this basis.

Matched pathways:
  - [prior_learning_credit] ~3 weeks, ~$200, no new federal borrowing
    Petition the registrar for credit from professional
    experience or military training.

State resources:
  - [NJ] Some College, No Degree (SCND) Initiative
    Ask the registrar or student success office whether they're
    an SCND grant recipient before assuming self-funded
    re-enrollment is the only option.
What that run demonstrates:
Two independent blocking rules found, each named and cited, not summarized into one vague "ineligible" Continuity measured in days from actual enrollment dates, the mechanism most students never see coming A pathway that requires no new federal borrowing, surfaced precisely because borrowing is blocked The student's state program pulled in automatically, with the exact question to ask the registrar
Worth knowing: the conversation above is a scripted walkthrough, not a live chatbot. Every fact in it is real output from the engine run below, but the conversational layer itself is deliberately not built yet, because the interface is the disposable part and the rules are the asset. The profile is a composite, not a real student, and the outcomes data behind pathway ranking is currently seeded rather than observed. Today the engine runs on self-reported student data only, there is no live feed into any SIS or NSLDS. State coverage is 21 states with verified programs, 15 more checked and deliberately excluded because no statewide program was verifiable, and 15 not yet checked. Persist reads the rules, it doesn't make the determination: your financial-aid office stays the authority on any individual student's eligibility.
03

The pilot

One cohort, one term, real numbers.

No integration, no data feed, no procurement cycle. Start with a list your completion team already has.

01

Pick one cohort

Stopped out within the last 24 months, past a credit threshold you set. A few hundred students is plenty.

02

Students self-report

A short intake they fill in themselves. No FERPA-covered record leaves your systems for this stage.

03

The engine runs

Each student gets named blocking rules, viable pathways, and state programs. Your advisors get the same view, in one list.

04

You measure re-enrollment

Re-enrollment and pathway completion after one term, against the cohort you'd have written off. Then decide.

04

Why this fits NYU

The exposure here is institutional, not just personal.

Grad PLUS dependency

Full-price graduate tuition leans on Grad PLUS. With it eliminated for continuity-broken borrowers, a returning graduate student can be academically welcome and financially blocked at the same time.

Retroactive caps

The new lifetime caps count debt already borrowed, so students who transferred in graduate credit from another institution can hit the ceiling on arrival. Combined-institution borrowing is exactly the case the engine checks.

New York is already encoded

SUNY/CUNY Reconnect, including the 2026/27 expansion to associate programs at eleven bachelor's-granting SUNY campuses, is in the state ruleset with its eligibility band and the question to ask.

Completion is the metric

Re-enrolling near-completors moves completion rates, which matters more under the program-level outcome accountability framework phasing in behind OBBBA. That rule is tracked in the engine as a watch item.

05

Data & compliance

Scoped narrow on purpose.

The fastest way to make this project unworkable would be to start by asking for institutional data. So it doesn't.

Self-reported only, today

Students enter their own enrollment history, borrowing, and state. No SIS, NSLDS, or transcript integration exists, which keeps the FERPA and GLBA surface near zero for a pilot.

Institutional data is gated

Any future record-level feed happens only behind a signed school-official agreement and review by an education-data privacy attorney. That's a deliberate later decision, not something bundled into a pilot.

Auditable by construction

Every determination names the rule, its effective date, and its citation. If a rule changes, previously issued guidance can be re-run and diffed rather than trusted.

Advisory, not a determination

Output is written as "here is the rule that applies and the question to ask," never as an official eligibility ruling. Your aid office remains the decision-maker.

Let's talk

Start with the students you already have.

Twenty minutes to see whether one cohort and one term of measurement is worth running before the fall census.

Persist · an eligibility engine for near-completors · a separate project from Voyacover, same builder