Datics AI
AI for EdTech

Cohortly by Datics AI

Ask your enrollment and retention data a question in plain English.

Deans, program leads and admins ask enrollment, retention and revenue data a question in plain English and get a table or chart, within what each user can already see. It ships inside your platform, under your name.

See it in your platform Try the demo

Built into your codebase and shipped under your name, on an engine we license to you.

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

Medical Assisting
61%
IT Support
66%
Business Admin
70%
Health IT
79%
Nursing prereqs
82%

Outreach list: 78 students for 6 advisors

Same demo, step by step below.

Try it step by step

Illustrative demo on a fictional institution. Not client work.

From question to chart

A plain-English retention question becomes the query, the chart and the next step.

Northstar College (fictional). The dean of student success asks which first-year programs are falling behind on spring re-enrollment.

Dean of student success · Northstar College

Input

Which first-year programs are behind last year's pace for spring re-enrollment?

Asked from the Reports page in week 8 of the fall term. Cohortly answers only from data this dean can already see in the product.

One question in plain English. The query, a chart and a next step out.

  1. 1Applying Northstar's definitions of 'first-year' and 're-enrolled'
  2. 2Writing the query
  3. 3Limiting it to programs you can see
  4. 4Comparing with the same week last year

Illustrative demo on a fictional institution. Not client work.

AI inside the workflow

Cohortly inside the product, not a chatbot beside it.

Northstar Campus today: every retention question becomes a report request and a spreadsheet.

admin.northstarcampus.com / reports / retention

Northstar CampusDashboardAdmissionsStudentsCoursesReportsAdmin
ReportsRetentionEnrollmentCompletionRevenueExports

Spring re-enrollment · first-year students

5 of 5 records

Export
Search

First-year students registered for spring, by week

All regions · last 8 periods

RefProgramStatus
PRG-MAMedical AssistingOpen
PRG-ITIT SupportOpen
PRG-BABusiness AdminOpen
PRG-HIHealth ITOpen
PRG-NPNursing prerequisitesOpen

Request a report, wait, filter in a spreadsheet, compare to last year by hand.

The assistant runs Cohortly, branded as Northstar Insights, the way it is built to ship under your product's name.

Illustrative demo on a fictional institution. Not client work.

What it does

What Cohortly can do.

"In the demo" items are shown above; "Sprint-ready" ones are built the same way. We pick the ones that fit your product; you don't need all of them.

Ask the data in plain English, watch for programs falling behind, and act with briefs and outreach lists for staff.

Ask

Plain-English questions

In the demo

Turns a question into a query over your data and returns a table or chart, with the query shown.

Ask

Institution definitions

In the demo

Uses each institution's own meaning of term, cohort, active and at-risk.

Watch

Weekly brief

In the demo

Writes the weekly read-out for a dean, program lead or employer admin.

Act

Outreach lists

In the demo

Builds lists of students for advisors to contact; nothing goes to students automatically.

Proof: the work it builds on

Built on a text-to-SQL engine we've delivered.

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.

AI-native productMulti-tenantPermission-aware
Read case study

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.

AI-native productMulti-tenantHIPAA-aligned
Read case study

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.

Brownfield AIInside a live productPermission-aware
Read case study

Why it sells

What Cohortly does for your business.

What your customers get, and what it does for your renewals and pricing.

A reason to renew

Customers get answers from their own data without waiting on a report request, inside your product.

An answer for RFPs

Read-only, permission-scoped answers with the query shown, for buyers who ask how AI handles student data.

A paid AI tier

Sell plain-English analytics as an add-on, priced from the cost per question we measure in the Build Sprint.

Built for:Student-records (SIS) software Also used in:Compliance and regulated training Admissions and enrollment platforms K-12 software

Controls

What Cohortly touches, and who approves.

Student data isn't used to train models for anyone else and stays in your cloud. Built and tested on synthetic or de-identified data.

  • Who uses it

    Deans, program leads, student-success staff and employer admins.

  • What it connects to

    Your reporting database or warehouse, read-only, with each institution's own definitions.

  • What a person approves

    It's read-only and doesn't contact students; lists and briefs go to the staff who asked.

  • Switch per institution

    On or off for each institution, with data settings their admins control.

See all controls and how we handle student data

How to get it

Two steps to a finished Cohortly.

Start with a three-week Build Sprint. Add more only if you want it.

  1. First · Build Sprint · $10,000 fixed

    Staff ask their data and spot changes early

    • Plain-English questions
    • Institution definitions
    • Weekly brief
    • In your staging, behind a feature flag
    • Delivered as pull requests
    • A test set your team reviews
    1. Week 1Setup
    2. Weeks 2–3Build
    3. You getCohortly in your staging and a fixed production quote
    Your time
    About 2–3 hours a week from a product owner
    Data
    Synthetic or de-identified
    The fee
    Counts toward production
    See Cohortly in your platform See a sample Build Sprint Pack

  2. Then · Live in production

    A finished product, yours to run

    • Fixed quote
    • Tested before launch
    • Switch per institution
    • A finished, working Cohortly in your product
    • Runs in your cloud, under your name
    • Fixed quote, agreed before we start

  3. Optional · Add more later

    Only if you want it

    More of Cohortly:

    • Saved views
    • Why did it change
    • Early alerts
    • +3 more

    Another module:

    • Each one quoted on its own
    • Nothing ongoing unless you ask

Already built or tried AI? Get it scored with the AI ScorecardNeed something else? Start with a Planning Sprint

FAQ

Questions about Cohortly.

Can it change student records?

No. It's read-only; lists and briefs go to the staff who asked, and nothing goes to students automatically.

How do users check an answer?

Each answer shows the query it ran, so staff can see exactly what was counted.

Does it predict which students will drop out?

No. 'At-risk' and similar terms use each institution's own definitions, not a prediction model.

Who can see what?

Answers are scoped to what each user can already see, with permissions inherited from your product.

What does a question cost to answer?

We measure the cost per question in the Build Sprint, on your schema, so you know it before you decide on production or pricing.

See Cohortly on your own product.

Bring your product and one workflow. In 30 minutes we look at where Cohortly fits, what it would cost to serve and what your customers' security review will ask.

Book a 30-minute Product Review All EdTech modules

Calls run in US Central time. No generic AI presentation: we discuss your product, users and production constraints.

See Cohortly in your platform