From Skills to Signals: Ascend Now Pilots Predictive AI Engine with Georgetown University
- Pavan Sampath
- Feb 26
- 3 min read
What if the way students learn soft skills could predict whether they're ready for college, at risk of dropping out, or aligned with the right career?
That's the question we've been working on. And we're now piloting the answer with Georgetown University's School of Continuing Studies.
The Problem No One Has Solved
For decades, schools have measured student success through a narrow set of indicators: grades, test scores, attendance, graduation rates.
But the competencies that research consistently identifies as most predictive of long-term success (self-regulation, communication, adaptability, growth mindset) remain largely invisible to the data systems schools rely on.
It's not that schools don't teach these skills. Many do, through SEL programs, advisory periods, and career readiness initiatives. The problem is that no system has been able to reliably convert qualitative skill development into quantitative, actionable signals. The kind that tell you whether a student is disengaging before they leave, whether they're actually ready for higher education, or whether the career path they're exploring fits who they actually are.
Edge 2.0 was built to close that gap.
What We're Building
Edge 2.0 is an AI-powered student intelligence platform that builds a comprehensive, living digital profile of each student. It captures personality, values, motivational drivers, learning preferences, social energy patterns, and cognitive style, then uses that profile to generate predictive indicators that matter to schools.
The system works across three layers.
First, the Intelligence Layer. Multiple data sources build dynamic student profiles stored in a vector database. Think of it as a living document that gets richer every time a student interacts with the platform.
Second, the NLP Engine. Proprietary conversational AI extracts behavioral signals from student interactions in real time. Students aren't filling out surveys. They're having adaptive conversations that feel like texting a mentor. And every conversation captures data that traditional assessments can't touch.
Third, Predictive Signals. Converging data points across multiple dimensions generate actionable indicators for schools. Not a single metric. A pattern.
Beyond Surveys: Conversational AI Assessment
Here's where it gets interesting.
The core innovation in Edge 2.0 is the replacement of traditional survey-based measurement with conversational AI assessments grounded in established pedagogical and psychometric frameworks including Fink's Taxonomy of Significant Learning, the Big Five personality model, Felder-Silverman learning styles, and Holland's RIASEC typology.
Rather than asking students to fill out forms (which, let's be honest, most students rush through), the system conducts adaptive conversations that match their personality and communication style. Each interaction captures both explicit skill data and a layer of behavioral metadata that traditional instruments simply cannot access.
The result is a multidimensional student profile that grows richer with every interaction, producing a 7-dimension skill assessment and a composite understanding-to-action mapping for each student.
What This Means for Schools
The student intelligence profiles convert into four categories of actionable indicators aligned directly with what schools actually care about.
Retention Risk Indicators. Composite risk scoring from converging behavioral, emotional, and engagement signals. Not binary flags, but gradient signals that allow counselors and administrators to intervene proactively, before a student reaches crisis point.
College and Career Readiness. Multi-factor matching algorithms that generate fit scores across 1,000+ careers and university programs, grounded in the student's actual psychometric and behavioral profile.
Teacher Intelligence. Student profiles queryable through natural language. A teacher can ask a question in plain English and receive AI-generated insights backed by cited evidence from real student data. No hallucinations. No guesswork.
Institutional Analytics. School-wide skill trajectories, wellbeing trends, intervention effectiveness, and comparative analytics against a global student index. Data that administrators can actually use for accreditation reporting, board presentations, and strategic planning.
The Georgetown Pilot: Early Results
Our partnership with Georgetown University's School of Continuing Studies began in 2024, when over 50 students from underserved backgrounds participated in the Summer College Immersion Program (SCIP) using the Edge platform. The results validated the core thesis.
94% of students reported learning important new skills. 84% said their schools didn't teach these skills enough. We measured a 12% increase in self-awareness and communication skills. And 9 out of 10 students rated the content as directly relevant to their lives.
Building on those results, we are now piloting the Edge 2.0 AI and NLP engine. Our first cohort has already completed the new conversational AI assessments, with early results showing significant improvements in student engagement and data quality compared to traditional methods.
When the AI adapts to a student's personality, uses their interests as reference points, and conducts conversations that feel natural rather than institutional, the quality of what students share changes fundamentally.
What's Next
We're expanding the pilot and actively looking for school networks, education groups, and institutions interested in testing Edge 2.0's predictive intelligence capabilities with their student populations. If your institution is exploring how AI can convert student development data into the signals that actually drive decisions (college readiness, career alignment, retention risk, measurable skill growth), we'd love to hear from you.
