Michelle Blomberg

RiverCity capstone

Case study · AI Tools & Strategy · Learning Design

A readiness check and rehearsal for the capstone’s live stakeholder defense: confirm the engagement is complete, then practice answering randomized questions on camera before the real thing.

Module 8 · Capstone · preparation tool, the live defense is graded

A time-series line that rises steadily then breaks and drops at a marked distribution-shift point

Run the simulation

Runs entirely on your device. Recordings never upload. Start in the panel below, or open it full screen →.

What this simulation is

The capstone is a single, defended, end-to-end consulting engagement for a recurring client, RiverCity, taking a genuine decision from a one-page brief through scoping, a leakage-safe build, an unannounced distribution-shift event that breaks earlier models, a detection-and-adaptation cycle, and a live stakeholder defense. It integrates every outcome in the course.

This tool is the preparation layer: a readiness checklist that confirms the engagement is complete, then a recorded defense that speaks randomized questions on camera so the student can rehearse and self-assess. The live meeting with the sponsor is still the graded defense. It is built on the reusable Defense practice engine.

What it helps you do

Why it resists AI substitution

The graded object is fifteen weeks of decisions on a private, messy, shifting engagement, defended live before people who push back. A model can draft text, but it cannot own the specific choices this student made or answer the sponsor’s follow-ups in real time.