AI for student-records (SIS) software
Let staff ask the data a question, inside the permissions they already have.
For SIS, analytics and student-success vendors. Let staff ask enrollment, retention and revenue data a question in plain English, inside the permissions they already have, under your name. Use it to win renewals, or sell it as a paid AI tier.
Built for: SIS, analytics and student-success vendors.
admin.northstarcampus.com / reports / ask
In · Dean of student success asks
Which first-year programs are behind last year's pace for spring re-enrollment?
Out · Cohortly
Registered for spring vs same week last year
Outreach list: 78 students for 6 advisors
Run it step by step on the Cohortly page.
Try it step by stepIllustrative demo on a fictional institution. Not client work.
Where these products get stuck
What gets in the way, and how we handle it.
- 01
Every question is a report request
Plain-English questions, answered as tables and charts
Cohortly shows the query it ran, so staff can check the answer.
- 02
Words mean different things
Each institution's own definitions
Term, cohort, active and at-risk use the institution's meaning, not a generic one.
- 03
The strictest terms in the market
Permissions and isolation inherited
Read-only, scoped to what each user can already see, institution by institution.
AI inside your product
The modules that fit this kind of platform.
Each one is shown on a fictional institution.
What it connects to: Read-only access to a de-identified copy of your reporting schema or warehouse in the Build Sprint; in production, row-level permissions are inherited from your product.
Ask your enrollment and retention data a question in plain English.
Fits: SIS, analytics, student success, compliance-training completion
A support agent for your learners and admins, grounded in your help center.
Fits: LMS support, student services
Proof
What we have built that this rests on.
57 featured AI case studies: AI products and brownfield AI builds, each written up on our Work page.
Cosmic AI
B2B Software · Multi-tenant AI analytics SaaS
Companies onboard themselves and connect several databases to one AI copilot, kept apart
Every new customer used to need its own copilot instance. Now a company signs up, connects several databases and invites its team.
MIRA
Healthcare & Wellness · Multi-clinic intake SaaS
Clinics sign up, pay per provider and run their own AI patient intake
The AI intake worked in three practices but was hard coded. Now any clinic signs up, pays per provider and runs it, and names never reach the model.
Transcripts U.S.
Government, Legal & Defense · Legal transcript marketplace
Attorneys receive deposition transcripts that even the marketplace cannot read
The marketplace could once read every transcript it held; now each file is encrypted in the agency's browser and opens only in the paying attorney's.
Read next: Every new question is a report request. Let your SIS customers ask it themselves
How it works
Three ways to start, each at a fixed price.
Records and analytics vendors usually start with Cohortly answering a set of their customers' real reporting questions on a de-identified copy of the schema.
EdTech Product Review · 30 minutes, no chargeStart here. We look at your product with you, agree the buyer outcome you want, and tell you which of the three below fits.
Book a 30-minute Product ReviewNo AI yet, and a module fits
Build Sprint
$10,000 fixed3 weeks
Pick it when: One of our modules delivers the outcome you want.
- One buyer outcome (2–3 related capabilities) working in your staging, behind a feature flag
- Pull requests to your repo, built on your catalog and synthetic or de-identified data
- Quality and safety evals, the cost to serve and a packaging recommendation
- A fixed-price quote for production
Something new, or a plan first
Planning Sprint
$5,000 fixed2 weeks
Pick it when: You need something our modules don't cover, or want a plan before you build.
- Where AI fits across your product, including beyond our modules
- A prioritized capability map, with what each one depends on
- A readiness review of your architecture, data and permissions
- A fixed-price quote to build it and take it to production
AI already built or tried
AI Scorecard
$5,000 fixed2 weeks
Pick it when: You've already built or tried an AI feature in your product, live or not.
- One AI feature you've built, tested in staging on 50 of your own cases
- Data-safety and misuse tests, and an accessibility pass on the AI screens
- Cost per learner and a packaging recommendation
- A scorecard, ranked fixes, draft security answers and a fixed quote
Not a compliance audit or certification.
Production, at a fixed quote
We take what your Sprint built or planned live for your customers, by pull request, with no standing production access. It typically includes load testing at your peak and a spend cap per institution. Your Sprint or Scorecard fee counts toward it.
After go-live, optional support
The product is finished and yours to run. If you want us to stay on: a named lead engineer, a monthly quality and cost report, testing before any model change, and more capabilities, each at its own fixed quote.
Stop after any Sprint and keep what you got.
How a Build Sprint runs
- In the setup week we map your integrations and agree what the Sprint touches.
- We follow your coding standards, tests and CI; your engineers review and merge every pull request.
- Half at signature, half when the Sprint Pack is delivered.
- Your time: about 2 to 3 hours a week from a product owner, plus an engineer to review pull requests.
Product improvements you can measure
What we agree to measure: quality and cost on test sets in the Build Sprint, adoption and outcomes once it is in production, so the decision rests on your numbers, not ours.
Self-serve answers
Report requests closed without engineering time
Accuracy you can check
Share of answers matching a reviewed test set
We set the success measures with you in the setup week.
Built for education data
Controls your customers' security reviews ask about.
Each control is a design fact about how the module is built and how we work, not a compliance claim.
Works with what you run
Reads catalog, courses, rosters and gradebook through the APIs and roles your product already has.
Synthetic data in Sprints
Sprint work uses synthetic or de-identified data and ships as pull requests to your repo.
Cited, and staff approve
Answers cite their source; anything that changes a grade, application or record waits for staff.
We work within your FERPA, COPPA, accessibility, security and institutional requirements. Compliance depends on the complete product, contracts, policies and operating environment; Datics does not present software engineering alone as legal certification.
How we handle student dataQuestions we hear on the first call
Straight answers before you book.
Can it write to student records?
No. Cohortly is designed to be read-only; lists and briefs go to the staff who asked.
How do we know the answers are right?
Each answer shows its query, and the Build Sprint tests it against a set of your customers' real questions.
Does it predict which students will drop out?
No. 'At-risk' uses each institution's own rules, not a prediction score.
Does it work with our warehouse?
Yes: your reporting database or warehouse, read-only, with a layer for each institution's own definitions.
Other EdTech platforms we build for
See your customers ask their own data a question.
Bring one product, workflow or AI feature. In 30 minutes we tell you which of the three ways to start fits, what it would cost to serve and what your customers' security review will ask.
Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.