AACOM Educating Leaders '26, Las Vegas, NV, April 22-24

All In! Example Submission


Not sure how to get started?


AACOM’s Mark Speicher, PhD, MHA, has created an example submission to showcase one approach to sharing a pitch. The structure and format here are not required, they are up to you! The only requirement is that you explain your idea as either a 90-second video or as a written pitch in 500 words or less. Good luck!

5 playing cards - stethoscope, brain, caduceus, whitecoat, DO

All In! FAQs

All In! Vegas Pitch Showdown
EXAMPLE SUBMISSION


Idea Title

AAndy: AI Osteopathic Admissions Advising
That Paves the Way for Applicant Success 

Two Sentence Summary

AAndy is an AI advising platform that gives every osteopathic applicant the kind of high-quality, person-centered guidance usually reserved for the well-connected. It aligns applicant stories with college of osteopathic medicine (COM) missions, provides information on application completeness and competitiveness and routes talent toward the right programs faster and more fairly. 

Option 1: 90-Second Video Pitch

Create your video and upload it to YouTube. Please include a link to your video on the form.


Option 2: 500 Word Written Pitch

Problem

COMs face rising demand to create well-trained osteopathic physicians, while traditional applicant pools shrink. First-gen, economically disadvantaged, rural, military and career-changer applicants lack advising, and many undergraduates don’t have access to advising that understands osteopathic medical education. This leads to poor mission fit, preventable rejections and avoidable burnout before day one.

Solution

AAndy combines Natural Language Processing (NLP) analysis of personal statements and experiences, Machine Learning (ML) predictions of interview likelihood and fit, a brief psychometric conversation for career fit and wellbeing and Retrieval-Augmented Generation (RAG) from trusted COM and applicant data. It delivers equitable, explainable guidance to applicants and efficient triage to COM admissions teams.

How It Works

Inputs

AACOMAS structured and unstructured data (10+ years; 20,000+ apps/year), COM materials and user-provided preferences.

Engines

NLP (mission alignment), ML (school-specific interview likelihood), psychometrics (career fit, resilience), RAG over COM catalogs, policies, outcomes and advising checklists.

UX

An advisor-style chatbot that proactively elicits key details, returns ranked school suggestions with explanations, and uses sensitivity flags to escalate to humans.

PoliceBot

An AI Agent provides oversight of information accuracy, detection of bias, notifications of errors or insensitive or harmful language or interactions and equity for both COMs and applicants at scale.

The User Experience

When Maria, a 30-year-old paramedic from rural Kansas, found AAndy on the AACOM web site, she wasn’t sure where to begin. She’d spent years in emergency medicine but didn’t have a pre-med advisor—or confidence that medical school was still an option. AAndy greeted her with a conversational prompt, asking about her experiences, goals and personal motivations for medical school and osteopathic medicine.

As Maria uploaded her transcript, MCAT score and personal statement draft, AAndy’s NLP engine analyzed her narrative for alignment with COM missions. It highlighted her focus on rural health and osteopathic principles, showing her which programs valued similar commitments.

The ML prediction engine, drawing on a decade of AACOMAS data, estimated interview likelihood across 44 COMs and offered a ranked list—transparent, not mysterious—explaining why certain programs were a strong fit. Maria’s opportunity to attend medical school was 65 percent at one midwestern COM, but rose to 83 percent after AAndy recommended two additional schools aligned with her service record and osteopathic philosophy.

Then came the psychometric conversation

AAndy guided her through short reflections on stress tolerance and community support, returning personalized wellbeing resources and prompting a growth mindset exercise—features informed by AACOM’s resilience research. Behind the scenes, AAndy’s “police bot” checked every interaction for bias and language tone. Maria came away with a clear, data-informed strategy and a sense of belonging.

Three months later, she was accepted to a mission-aligned COM—her story reinforcing AAndy’s promise: Advise everyone. Align to mission. Advance DO medicine.

Closing: AAndy

Advise everyone. Align to mission. Advance DO medicine. High Rollers, this is your chance to go All In! on AAndy so every strong applicant finds the right DO home, and COMs build classes that care for every community.