Rehearsly · EdTech AI module
Voice roleplay practice with rubric scoring, inside your course.
Rehearsly lets learners practise real conversations by voice against an AI counterpart, then scores them against your rubric and gives specific coaching, so skills courses can measure practice and not just completion.
A reference build, not software you license. It ships under your product's name.
learn.northstarcampus.com / insurance-licensing-ce / practice
Northstar Workforce Academy · Rehearsly
DemoStep 1 of 4
Illustrative demo on a fictional institution. Not client work.
The problem
Courses that teach a conversation (a sales call, a patient intake, a de-escalation, a manager check-in) end in a multiple-choice quiz because live roleplay needs an instructor or a partner for every session. Completion goes up; nobody knows whether the learner can actually do it.
The worked example
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.
Real-time voice (speech recognition plus a real-time model), a stateful roleplay engine rather than disconnected prompts, rubric-driven scoring, and admin tools for scenarios and difficulty. Embeds in your course player; scores can be written back to your gradebook through your product's API. Scores are advisory, recordings are kept 30 days, and no voiceprints are created.
AI inside the workflow
Rehearsly inside the product, not a chatbot beside it.
Switch between the product as it ships today and the same screen with the module working inside it. Ask a question, then approve what it prepares.
Northstar Learn · fictional product
Northstar Learn today: instructors open each scorecard to see who needs which scenario.
The assistant runs Rehearsly, branded as Northstar Coach, the way it would ship under your product's name.
Illustrative demo on a fictional institution. Not client work.
What it does
What Rehearsly does inside your product.
Best fit: Workforce learning, CE, health-professions education, bootcamps.
Scenario library
Instructors set the persona, mood, objections and difficulty for each scenario without engineering help.
Live voice roleplay
Two-way voice conversation that adapts to what the learner says, their pace and where they go off script.
Rubric scoring
Scores each session against the course rubric, such as script adherence, tone, confidence and how objections were handled.
Coaching
Specific, timestamped feedback after each attempt and a suggested next scenario.
Progress and motivation
Levels, streaks and cohort leaderboards; admin analytics by learner, scenario and rubric line.
Where it comes from: The engine behind a voice training product we built for a US insurance training firm.
Read the AI Roleplay Assistant case studyHow it works
One AI feature, working inside your product, in two weeks. $10,000, fixed.
In two weeks: three of your scenarios running by voice with your rubric, scored on recorded test sessions, plus the cost per practice session.
- 01
EdTech Product Review
30 minutes, free
We look at your product with you and pick the module or capability that protects your next release, what it would cost to serve, and what your customers' security review will ask.
- 02
The Sprint
$10,000, two weeks, fixed
One AI feature working inside your product: running in your staging environment on your catalog, documents or synthetic data, behind a feature flag, delivered as pull requests. You also get quality and safety evals, a cost estimate on two models, a data-flow sheet and a fixed-price quote for production.
- 03
Targeted Unlock, then Capability Waves
Quoted at the end of the Sprint
The first production capability, delivered by pull request into your repo with no standing production access. Then the next module, on the foundation the first one built.
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.
- Runs on your catalog, documents or data through the APIs your product already exposes. No rebuild.
- Sprint work uses synthetic or de-identified data and ships as pull requests to your repo. No production student data.
- Every answer that matters shows its source; material actions go to a person for approval.
- Built around FERPA, COPPA, accessibility and institutional requirements.
- Built to ship under your product's name. Model and hosting are your choice.
We build around 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 dataWork this builds on
Projects we have delivered that use the same engine or the same engineering pattern.
Voice Roleplay Trainer
Insurance Sales Training · Skills Practice / Voice AI
AI voice roleplay that makes skills practice measurable
Agents pick a scenario, a prospect personality and a difficulty, hold a live voice call with an AI prospect, and get a scorecard, transcript and coaching against the firm's own method.
Leadership-development practice app
EdTech · Learning App / Mobile & Desktop
A leadership-development practice app taken from the web to iOS, Android and desktop
A daily leadership practice built on seven inner archetypes, taken from a web app to native iOS, Android, Windows, macOS and Linux apps from one codebase.
Document-to-Structure Suite
Enterprise Process Modeling · Content Generation / Structured Drafting
Source documents turned into structured models, SOPs and job aids
Word and PDF process documentation turned into standard BPMN models, SOPs and job aids, shipped as a subscription product over six releases.
Other EdTech modules
Pathly
AI course and program recommendations
An advising agent that knows your catalog and books the next step.
Fits: Admissions, enrollment, CE and corporate learning catalogs
Intakely
Admissions document automation
Admissions documents in, a checked application record out.
Fits: Admissions and credentialing
Cohortly
Ask your enrollment and retention data
Ask your enrollment and retention data a question in plain English.
Fits: SIS, analytics, student success
Docently
AI support for your LMS and learners
A support agent for your learners and admins, trained on your help center.
Fits: LMS support, student services, K-12
Course Builder
AI course drafting from source documents
From an SOP or policy PDF to a draft course your instructional designers can edit.
Fits: Corporate LMS, compliance training, courseware and CE
Accessibility Check
WCAG reviews ahead of ADA Title II
An AI-assisted WCAG 2.1 AA review of your product, with fixes your team can ship.
Fits: Any vendor selling to public colleges, universities or districts
Lesson to Video
Lesson scripts into microlearning video
Lesson scripts into narrated, on-brand microlearning videos.
Fits: Microlearning, corporate LMS, courseware and CE
See Rehearsly on your own product.
Bring one product, workflow or AI initiative. In 30 minutes we pick the module that fits first, 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.