Skip to content

Latest commit

 

History

History
47 lines (24 loc) · 3.16 KB

File metadata and controls

47 lines (24 loc) · 3.16 KB

Perception Learning — 2:55 Demo Script

The video must be public on YouTube, under three minutes, and include spoken coverage of how GPT‑5.6 and Codex were used.

0:00–0:20 — The problem

Show: Library hero and OpenStax shelf.

Say: “Students usually submit an answer after the interesting thinking has already disappeared. Perception Learning turns an OpenStax lesson into a visible reasoning loop: predict, test, explain, revise—and gives a teacher evidence while there is still time to help.”

0:20–0:48 — A book becomes an investigation

Show: Open Physics, change the reading level, highlight the direct OpenStax source, and open the Mechanical Energy lab.

Say: “This is not a chatbot pasted onto a textbook. The reading is layered by audience, every model is section-linked and teacher-reviewed, and the learner must commit a forecast before the deterministic simulation reveals the mechanism.”

0:48–1:18 — Real classroom delivery

Show: Teach → copy join code → Class → join as Alex → Teach → Assign learning. Emphasize that only the live learner is selected by default.

Say: “This class begins empty—there are no fabricated students or analytics. This is a real join, and the assignment is persisted in Cloudflare D1 and delivered to the learner inbox—not merely written into a teacher-side feed.”

1:18–1:48 — The science interaction

Show: Class → Start assignment → commit a Mechanical Energy forecast → run the lab → change release height → explain the conserved quantity.

Say: “The model is interactive, repeatable, keyboard- and touch-friendly. AI can propose a model, but only validated deterministic code produces the evidence. The learner’s forecast, confidence, parameter changes, and explanation form the proof trail.”

1:48–2:20 — The feedback loop that did not exist before

Show: Save a note or generate a mid-lesson question. Return to Teach, open Alex’s trace, generate the bounded brief, and send a nudge.

Say: “The teacher sees observable learning actions in order, with private notes hidden unless the learner explicitly opts in. Cloudflare AI turns the trace into a bounded instructional brief—never a diagnosis or automatic grade. The teacher stays in control and sends one focused move.”

2:20–2:36 — Prove delivery

Show: Return to Class. The assignment says Continue and the teacher message appears.

Say: “The response arrives where the learner is working, closing the loop from assignment to evidence to intervention.”

2:36–2:55 — Codex, GPT‑5.6, and architecture

Show: README architecture, test output, and Cloudflare dashboard or deployment URL.

Say: “GPT‑5.6 and Codex helped design the product, map multiple OpenStax sections into simulations, implement the Cloudflare Worker and D1 schema, write the scientific and end-to-end tests, perform a harsh product audit, and iterate the responsive interface. The deployed runtime remains Cloudflare Workers, Workers AI, D1, and static assets.”

End on the product name and one sentence: “Perception Learning makes reasoning visible while it can still change.”