Skip to content
AI College Prep Academy

Pre-Engineering Track · Inaugural Summer 2028

Senior engineer-led · Practicing PhDs co-teach · Selective admissions

Build the engineering AI agent the next generation of mechanical, electrical, and biomedical engineers will keep open during their first design review.

Capstone agent · Build hardware AI.
I built an AI agent that suggests CAD revisions based on tolerance constraints.

High school students in a maker lab examining a robotics prototype, working on a hardware AI agent

What your child will build

The CAD-revision agent

An agentic system that takes an engineering drawing, reasons about tolerances and material specifications, suggests revisions for manufacturability, and produces a design-review memo a junior engineer can present to their team lead.

Claude APIModel Context Protocol (MCP)OpenSCAD or FreeCAD CLIpgvector (spec library)Vercel deploy

What it does

  • Ingests a CAD drawing or parametric model and parses dimensions, tolerances, and materials
  • Cross-references manufacturing constraints — tolerance stack-up, material yield, machining feasibility
  • Suggests revisions with reasoning grounded in design-for-manufacturability principles
  • Surfaces edge-case failure modes from a curated spec library
  • Generates a design-review memo with a prioritized revision list
  • Logs an audit trail of every reasoning step for the team lead's review
Practicing engineer archetype (sample profile) — Working engineer · McCormick School of Engineering, AI College Prep Academy Pre-Engineering co-teaching faculty (sample profile)

Co-Teaching Faculty

Practicing engineer archetype (sample profile)

Working engineer · McCormick School of Engineering

Our pre-engineering track is co-taught by a practicing engineer — recruited from McCormick School of Engineering and the broader hardware and systems engineering ecosystem — alongside a senior software engineer. Your child works directly with an engineer who has shipped physical products and who can articulate the difference between a clever simulation and a manufacturable design. The mentor relationship continues past the program: pre-engineering students who perform well receive a personal letter of recommendation and direct introductions into the broader practitioner network.

Students leave understanding the difference between a design that runs in CAD and a design that survives a manufacturing review.

Curriculum Deep-Dive

Week 2 — Engineering AI deep-dive

The pre-engineering cohort splits off from the shared Week 1 foundations and works directly with the engineer on tolerance reasoning, manufacturability, and the design-review patterns unique to hardware AI.

  • CAD parsing and parametric model ingestion — turning drawings into structured data
  • Tolerance stack-up reasoning — propagating dimensional variance through assemblies
  • Design-for-manufacturability heuristics — machining, injection molding, additive
  • Failure-mode retrieval from a curated spec library
  • Hands-on architecture review with the engineer: where AI accelerates, where it must defer to human judgment
  • Capstone scoping: pick a real mechanical or electronics design, 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-Engineering work. Inaugural cohort is Summer 2028 — these are not real-alumni outcomes.

Sample student work — Lucas T. (rising 12th)

Tolerance stack-up review agent for a 3D-printed assembly

Built an agent that reviews a multi-part 3D-printed assembly, propagates dimensional tolerances through the stack, and surfaces interferences before the print job runs.

Claude + OpenSCAD CLI + pgvector + Streamlit

Sample student work — Anika P. (rising 11th)

Material-substitution recommender for a mechanical part

Built an agent that takes a part spec and proposes alternative materials with revised tolerances and cost implications, citing yield strength and machinability data.

Claude + LangGraph + Postgres + Next.js

Why this track wins for admissions

A capstone an admissions reader can verify.

An admissions reader at a top pre-engineering university — MIT, Stanford, Caltech, Berkeley EECS, Carnegie Mellon, Northwestern McCormick — is looking for the rare applicant who has built something real and can talk about the engineering judgment behind it. Most strong pre-engineering applicants present FIRST Robotics seasons, science-fair projects, and AP Physics scores — all important, all common. Far fewer can sit across from an interviewer and discuss the design tradeoffs in tolerance stack-up automation, the limits of simulation, or what a manufacturing review actually evaluates. Your child finishes the program with a working CAD-revision 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 engineering specific, hands-on, and verifiably their own.

Talk through your child’s admissions strategy
College admissions counselor reviewing a college essay draft with a high school student in a warm advisor's office

Pre-Engineering FAQ

Track-specific questions from parents.

Pre-Engineering · Selective by design

Ready to give your child the agentic-hardware ai. advantage?

Selective admissions. We expect a 40 to 60 percent admit rate. Rolling applications through Spring 2028.