An agentic system that runs customer discovery, iterates landing-page copy from real interview transcripts, drafts support replies, and produces a weekly metrics memo a solo founder can act on before their next standup.
Claude APIModel Context Protocol (MCP)pgvector (interview corpus)Next.jsVercel deploy
What it does
Conducts a structured discovery interview from a founder's hypothesis brief
Transcribes and clusters interview themes — pain points, objections, willingness to pay
Iterates landing-page copy A/B variants grounded in real interview language
Triages incoming support requests and drafts replies in the founder's voice
Produces a weekly metrics memo with the actions a solo founder should take
Logs an audit trail of every customer touchpoint for review
Co-Teaching Faculty
Startup founder archetype (sample profile)
Working founder · Booth Polsky Center network
Our pre-entrepreneurship track is co-taught by a working founder — recruited from the Booth Polsky Center, Pritzker Group network, and broader regional founder ecosystem — alongside a senior software engineer. Your child works directly with someone who has run customer-discovery interviews on a real product, shipped landing-page iterations against real revenue, and built the back-office automation that lets a one-person team feel like five. The mentor relationship continues past the program: pre-entrepreneurship students who perform well receive a personal letter of recommendation and direct introductions into the broader practitioner network.
“Students leave understanding why customer-discovery transcripts matter more than pitch decks — and how to read a week of metrics in five minutes.”
Curriculum Deep-Dive
Week 2 — Founder AI deep-dive
The pre-entrepreneurship cohort splits off from the shared Week 1 foundations and works directly with the founder on customer-discovery automation, copy iteration, and the operational rhythms unique to a one-person team.
01Customer-discovery interview design — structured questions and theme clustering
02Transcript analysis and pain-point taxonomy from real interview corpora
03Landing-page copy iteration grounded in customer language
04Support-triage automation — drafting in the founder's voice with audit trails
05Hands-on architecture review with the founder: where the agent earns its keep, where the founder must show up themselves
06Capstone scoping: pick a real micro-startup hypothesis, write the spec, agree on an evaluation rubric
Week 1 foundations are shared across all 5 tracksWeek 3 builds + admissions coaching
Sample student work
What your child could build.
Sample capstone projects illustrating the scope of Pre-Entrepreneurship work. Inaugural cohort is Summer 2028 — these are not real-alumni outcomes.
Sample student work — Ezra C. (rising 11th)
Customer-discovery interview agent for a school-tutoring micro-startup
Built an agent that runs a structured 10-question discovery interview, transcribes the response, and produces a pain-point summary with quotes for the founder's next iteration of landing-page copy.
Claude + LangGraph + pgvector + Next.js
Sample student work — Naomi B. (rising 12th)
Support-reply drafter for a side-project SaaS
Built an agent that triages incoming support emails, classifies by urgency, drafts replies in the founder's voice, and surfaces the open issues that should be addressed in the product roadmap.
Claude + Postgres + Streamlit
Why this track wins for admissions
A capstone an admissions reader can verify.
An admissions reader at a top pre-entrepreneurship university — Stanford GSB undergraduate engineering, Wharton entrepreneurship concentration, MIT Sloan, Booth early-entry programs — is looking for the rare applicant who has done more than win a business-plan competition. Most strong pre-entrepreneurship applicants present DECA wins, business-club leadership, and side-project pitch decks — all important, all common. Far fewer can sit across from an interviewer and discuss the operational realities of customer discovery, the discipline of iterating copy against real interview language, or what a one-person founder's weekly metrics memo actually contains. Your child finishes the program with a working back-office agent at a personal URL, an architecture writeup an admissions reader can verify, and a Common App essay built around the project — a piece of writing that makes their interest in entrepreneurship specific, operational, and verifiably their own.