Break a mobile feasibility deadlock by building the smallest functional prototype of the disputed capability, run it on a real phone, and use the result to replace abstract arguments with concrete technical and product questions.
Source episode · 40:00
How I AI: Anjan Panneer Selvam and a new model of B2B product managementwith Claire Vo
Anjan describes a team blocked on a mobile avatar capture idea with no mobile developer, then builds a narrow Expo app in Rork that captures a selfie in different expressions and uses it to show what is possible before production engineering begins.
A runnable mobile prototype that demonstrates the critical interaction on a real device, records limitations and implementation questions, and gives the team a shared reference for the production approach.
AI tool for building functional mobile prototypes
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Write the deadlock as a testable question, such as whether a camera flow works well enough on employee phones. Name what evidence would change the team's view and exclude everything that does not help answer it.
Ask Rork to build one runnable Expo flow with the minimum navigation and state needed for the test. Use synthetic content and include permissions, cancellation, error, retry, and completion states.
Build a runnable Expo prototype to test this question: [question]. Implement only this flow: [steps]. Use synthetic data. Include permission denied, cancellation, error, retry, and success states. Clearly label mocked behavior and list the packages and device capabilities used. Do not add unrelated screens or production integrations.
Connect the real device capability at the center of the dispute, such as camera capture, while keeping analysis or backend behavior mocked unless it is also part of the question. Show the user what was captured and allow a retry or correction.
Implement the [camera or device capability] for this prototype. Request only the required permission, explain why it is needed, allow cancel and retry, show the captured result, and avoid storing or uploading it unless explicitly configured. Label any simulated recognition or backend response.
Run the prototype on a representative physical phone and demonstrate both the happy path and a failure path to the engineering team. Ask what the demo proves, what it does not prove, and what they would change for production.
Store the prototype with its question, status, code, dependency versions, device and OS tested, screenshots, known limitations, and feedback. Share it as a prototype, not a roadmap commitment or production estimate.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Log your workouts effortlessly without ever opening a spreadsheet. This workflow uses the Claude mobile app to parse a simple voice note and automatically update your workout tracking spreadsheet in the background.
Create a custom email management interface within Claude to read, triage, and draft replies without opening the Gmail tab. This workflow helps you reclaim focus and compound your learnings by training your AI on every interaction.
Build a fully automated system in Claude to generate personalized, interactive HTML proposals and client onboarding materials, saving hours on administrative work and creating a high-touch experience.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.