Build a bedside keyboard that captures an idea with one keypress and routes the text to the right destination.
Source episode · 31:31
How I AI: Jason Levin's Workflows for Agentic Memes, Vibe Coding, and Hardware Hackingwith Claire Vo
31:31 to 35:25: Jason combines a compact keyboard and Raspberry Pi so a bedtime idea can trigger a capture script and route the text through ChatGPT.
A reliable low-friction capture device that records, timestamps, and routes ideas without opening a phone.
OpenAI conversational AI
Workflow automation platform
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
5 steps
Connect a simple, inexpensive mini-keyboard to a Raspberry Pi. This creates the physical, screen-free device for capturing your ideas.
Connect the keyboard to the Raspberry Pi and map the dedicated capture key.
Use ChatGPT to guide you through writing a Python script for the Raspberry Pi. The script's function is to act as a keylogger, capturing all text typed on the connected keyboard.
Write a local listener that opens a text capture, timestamps it, and stores it before any network call.
Modify the Python script to listen for the 'Enter' key. Configure it so that when 'Enter' is pressed, the script captures all text typed since the last time 'Enter' was pressed.
Trigger capture on [key combination] and show a clear ready, sent, or failed signal.
Program the script to send the captured text to a Zapier webhook via an API request. This step moves your idea from the local Raspberry Pi to your cloud-based automation workflow.
POST the saved idea and idempotency key to [webhook], retrying safely after network failure.
Set up a Zapier workflow that starts with the webhook trigger. Add a filter or path step to parse the incoming text for specific keywords, which will determine the note's destination. For example, route text containing 'Lin Eng' to create a new ticket in Linear, or text with 'email' to your inbox.
Classify each idea into [destinations], retain the raw inbox copy, and log the routing reason.
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
Create context-aware guardrails for your enterprise AI agent using a 'Project' governance layer. As a project owner, define rules, scope tools, and require human-in-the-loop approval for sensitive actions, ensuring safe and effective AI use.
Transform a successful AI chat session into a reusable skill that anyone in your company can use. Package prompts, tools, and code into a standardized workflow, making it easy to share and scale automation across your organization.
Use a natural language AI agent to instantly generate and iterate on custom data dashboards. This workflow queries your company's data securely, allowing non-technical users to perform their own 'last mile' data analysis without filing tickets.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.