Create a repeatable exercise demonstration by pairing a consistent AI character with a real motion reference.
Source episode · 11:19
How I AI: Bryce Rattner Keithley's No-Code Playbook for Building a Fitness App with Replit, Gemini, and Claudewith Claire Vo
11:19 to 31:51: Bryce creates an anthropomorphic exercise character in Gemini, records herself performing the motion, and combines the still and reference video in Higgsfield using Kling.
A short animated exercise clip whose character, movement, framing, and loop fit the workout product.
Google AI assistant
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
3 steps
Generate a high-quality static image of your character using a model like Gemini. To get the exact starting position and setting you need for the animation, write a hyper-literal and precise prompt.
Create a full-body [animal] character in [setting], wearing [outfit], in the exact starting pose for [exercise], with consistent lighting and camera angle.
Record a short video of yourself performing the desired action or exercise. This will be your motion reference. It is critical that the orientation and general form in your video match the static image from the previous step.
Record one clean repetition at a steady pace, full body visible, fixed camera, and no occlusion.
Upload your static character image and motion reference video to Higgsfield. Use the Motion Control feature, powered by a model like Kling. To keep the background from your static image, set 'Scene Control' to 'Image'. Click generate to animate your character using the motion from your video.
Combine the approved still with the motion reference in Higgsfield using Kling; preserve character identity and exercise form.
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
Use a hybrid AI workflow to bridge design and development. Generate high-level design concepts and tokens with Claude, then use Codex for robust implementation of the technical components in your codebase.
Implement a QA loop for AI-generated code using Devin. This playbook combines automated code reviews with an agent-recorded video walkthrough for visual verification, ensuring high-quality merges at scale.
Build a reusable 'Watchdog' playbook in Devin to automatically monitor customer accounts. The agent proactively checks for errors, synthesizes a prioritized list of critical issues, and saves you time.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.