AI for EdTech

Rehearsly by Datics AI

Learners practice the conversation and get scored, inside your course.

Learners practice real conversations by voice with an AI counterpart, are scored against your rubric and get specific coaching, so your courses measure practice, not just completion. It ships inside your platform, under your name.

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

learn.northstarcampus.com / insurance-licensing-ce / practice

In · Practice scenario

Dana, a skeptical prospect, raises price and timing objections on a five-minute voice call, scored against a six-step rubric.

Out · Rehearsly

Score: 3 of 6 rubric steps

  • Open and ask permission
  • Acknowledge the objection
  • Ask about current coverage
  • Present a plan that fits
  • Confirm the budget
  • Agree a specific next step

0:31 · Ask what they have today before presenting a plan.

Same demo, step by step below.

Try it step by step

Illustrative demo on a fictional institution. Not client work.

Try a practice call

Take the learner's seat. Dana pushes back, and the rubric scores what you say.

Northstar Workforce Academy (fictional). A learner in an insurance licensing CE course takes a five-minute voice call with a skeptical prospect who raises price and timing objections.

Practice scenario · Insurance licensing CE

Input

Dana, skeptical prospect

Mood: guarded · Objections: price, timing · Level 1 · Five-minute voice call

Set up by the instructor in the scenario library, no engineering needed.

Course rubric

  1. 1Open and ask permission
  2. 2Acknowledge the objection
  3. 3Ask about current coverage
  4. 4Present a plan that fits
  5. 5Confirm the budget
  6. 6Agree a specific next step

Steps light up as you hit them during the call.

You're the agent. Pick what to say at each turn; Dana answers, and the rubric scores you.

  1. 1Loading the scenario and persona
  2. 2Connecting the voice call

Illustrative demo on a fictional institution. Not client work.

AI inside the workflow

Rehearsly inside the product, not a chatbot beside it.

Northstar Learn today: instructors open each scorecard to see who needs which scenario.

learn.northstarcampus.com / insurance-licensing-ce / practice

Northstar LearnDashboardCoursesLearnersPracticeReportsAdmin
PracticeCohortScenariosScorecardsRubricsLeaderboard

Cohort practice

5 of 5 records

Assign
Search

Average rubric score by step

All regions · last 8 periods

RefLearnerStatus
LRN-201K. JohnsonPracticing
LRN-204P. NguyenPracticing
LRN-207S. OrtizPracticing
LRN-209L. BeckerReady
LRN-212J. OkoyePracticing

Open each scorecard, compare steps by hand, assign scenarios one by one.

The assistant runs Rehearsly, branded as Northstar Coach, 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 Rehearsly 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.

Build practice scenarios, run them by voice or chat, and prove the skill with scores an instructor signs off.

Build the practice

Scenario library

In the demo

Instructors set the persona, mood, objections and level for each scenario without engineering help.

Run it

Voice roleplay

In the demo

A live two-way voice call with an AI counterpart that adapts to what the learner says.

Prove the skill

Rubric scoring

In the demo

Scores each attempt step by step against the course rubric.

Prove the skill

Coaching

In the demo

Timestamped feedback on the moments that cost points, plus the next scenario to try.

Prove the skill

Cohort analytics

In the demo

Shows instructors the weakest rubric step across a cohort and who needs which scenario.

Proof: the work it builds on

Built on a voice-roleplay and rubric-scoring engine we've delivered.

Insurance Sales Lab

EdTech · Workforce learning / Voice AI

Insurance agents practice calls with an AI prospect, scored on the company's script

Practice used to wait for a human coach, and feedback varied. Now agents call an AI prospect any time and get the same checklist score.

Brownfield AIInside a live productHuman approval
Read case study

Dental clinical documentation AI

AI engine · Review and approve

AI clinical documentation inside the dentist appointment workflow

Live transcription, patient context and AI-drafted clinical notes with dentist review and approval.

HealthcareClinical AIHuman-in-the-loop
Read case study

A leadership author's company

EdTech · Leadership practice app

Leadership exercises on phone, desktop and web, shipped from one codebase for launch

The app existed only as a web prototype with a store deadline close; we shipped it to phones and desktops from the same code, no rewrite.

ModernizationEdTechUnder client brand
Read case study

Why it sells

What Rehearsly does for your business.

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

A reason to renew

Your customers get practice scores to show, not just completion rates, when they report on training.

An answer for RFPs

Scored practice with instructor sign-off gives you a concrete answer when buyers ask what your AI does for learners.

A paid AI tier

Sell practice sessions as an add-on, priced from the cost per session we measure in the Build Sprint.

Controls

What Rehearsly 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

    Learners practicing a conversation, and the instructors and program admins who set scenarios and review progress.

  • What it connects to

    Your course player, plus the gradebook, CE tracking or HRIS your customers report from.

  • What a person approves

    Scores are advisory; instructors sign learners off. Retention and consent are set by you and your customers.

  • 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 Rehearsly.

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

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

    Three of your scenarios, practiced by voice and scored

    • Voice roleplay
    • Rubric scoring
    • Coaching
    • 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 getRehearsly 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
  2. Then · Live in production

    A finished product, yours to run

    • Fixed quote
    • Tested before launch
    • Switch per institution
    • A finished, working Rehearsly 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 Rehearsly:

    • Scenario library
    • Scenario generator
    • Chat roleplay
    • +4 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 Rehearsly.

Do scores replace instructor sign-off?

No. Scores are advisory. Instructors sign learners off, and a check-ride is a graded attempt an instructor reviews.

What happens to voice recordings?

Retention and consent are set by you and your customers; recordings aren't used to train models for anyone else.

Can learners practice without speaking?

Yes. Chat roleplay offers the same practice by typing, for quiet settings and accessibility.

What if a learner goes off-script?

The AI counterpart is designed to adapt to what the learner actually says, and the rubric scores each step, so going off-script shows up in the score and the coaching.

What does a practice session cost to run?

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

See Rehearsly on your own product.

Bring your product and one workflow. In 30 minutes we look at where Rehearsly 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.