Building the CareKind Investor MVP

Understand, build, test, and explain CareKind’s coming investor-MVP work—from the fixed-camera edge pipeline through evidence-based cloud review, phone and screen-duration policies, SMS delivery, evaluation, and the later ready-to-install system—while making sound product, safety, privacy, and engineering decisions.

6 sections · 28 lessons

Course outline

The Product and the Proof

  1. Podcast: What the Investor MVP Must Prove
  2. Podcast: Evidence Before Conclusions
  3. Workshop: Read the Roadmap as a Dependency Graph

Inside the Edge Pipeline

  1. Podcast: One Camera Stream, Many Time Scales
  2. Podcast: Action Areas, Screen Areas, and Coordinate Geometry
  3. Podcast: Designing a Sensitive Candidate Gate

Physical Events and Cloud Review

  1. Podcast: Capturing Hand Hits Without Calling Them Abuse
  2. Podcast: Detecting Falls When Doll Pose Disappears
  3. Podcast: The Frame the VLM Never Saw
  4. Workshop: Two Reviews From One Physical Candidate

Phones, Screens, and Time

  1. Podcast: Choosing the Second Pretrained Edge Model
  2. Podcast: Prolonged Visible Phone Use
  3. Podcast: Screen Exposure Without Claiming Attention
  4. Workshop: Deterministic Duration State Machines

Turning Detection Into a Product

  1. Podcast: Possible Event—Reviewing
  2. Podcast: Dana’s Review and the Automatic Demo
  3. Podcast: Protected Evidence and SMS
  4. Podcast: From Mac Demo to Ready to Install

Evaluation, Iteration, and Fundraising

  1. Podcast: Diagnose the Stage That Failed
  2. Podcast: Labels, Regressions, and Honest Accuracy
  3. Podcast: Expert Review Is Not Evaluations
  4. Podcast: Why the Rehearsal Queue Got Noisy
  5. Podcast: Fair Replay Needs Frozen Identities
  6. Podcast: B1 Stops Ordinary Activity From Opening Windows
  7. Podcast: B2 Admission Is Not a Precision Gain
  8. Podcast: When to Train a Temporal Classifier
  9. Podcast: Running the Work Through Linear and Orca
  10. Capstone: Rehearse and Explain the CareKind MVP

Start learning with Wondering