How Grok Bot designers use AI agents to build personal sites and product prototypes | John Bai & Peng Zheng
Episode
41 min
Read time
2 min
Topics
Productivity, Health & Wellness, Startups
AI-Generated Summary
Key Takeaways
- ✓Personal site automation pipeline: Build a check-in system by connecting Grok Bot to Google Places API so that sending a photo, screenshot, or place name triggers automatic location lookup, coordinate retrieval, perspective correction, people removal, and 3D miniature image generation in both light and dark versions — eliminating manual CMS updates entirely.
- ✓Figma MCP remote design workflow: Connect Grok Bot to Figma via the Figma MCP integration, then specify layout preferences upfront — such as artboard spacing of 50–100 pixels — so the bot executes production design tasks like icon placement and asset scaling via voice memo while you are physically away from your computer.
- ✓Prototype without gatekeepers: Use a dev bot to convert voice-described interaction concepts directly into working coded prototypes, bypassing the traditional PM prioritization and engineering resource allocation process. This "trash can method" makes exploration inexpensive, allowing designers to test and discard ideas without justifying ROI or consuming sprint capacity.
- ✓Bot specialization by life domain: Organize Grok Bot instances into distinct life and work categories — calendar manager, email manager, chief of staff, legal adviser, language tutor — and chain tasks together, such as purchasing 3D printing filament and automatically updating a Notion inventory record in a single delegated instruction.
- ✓Insurance coverage bot setup: Create a dedicated bot loaded with your specific insurance plan details, then submit any receipt, prescription, or provider invoice to it for automatic coverage analysis. The bot flags whether follow-up claims are needed and confirms maximum savings are captured, removing manual policy cross-referencing from routine healthcare decisions.
What It Covers
Grok Bot designers John Bai and Peng Zheng demonstrate two AI agent workflows: Peng's automated personal website check-in pipeline using Google Places API and AI image generation, and John's Figma-connected design bot that handles production work and prototyping remotely via voice memos.
Key Questions Answered
- •Personal site automation pipeline: Build a check-in system by connecting Grok Bot to Google Places API so that sending a photo, screenshot, or place name triggers automatic location lookup, coordinate retrieval, perspective correction, people removal, and 3D miniature image generation in both light and dark versions — eliminating manual CMS updates entirely.
- •Figma MCP remote design workflow: Connect Grok Bot to Figma via the Figma MCP integration, then specify layout preferences upfront — such as artboard spacing of 50–100 pixels — so the bot executes production design tasks like icon placement and asset scaling via voice memo while you are physically away from your computer.
- •Prototype without gatekeepers: Use a dev bot to convert voice-described interaction concepts directly into working coded prototypes, bypassing the traditional PM prioritization and engineering resource allocation process. This "trash can method" makes exploration inexpensive, allowing designers to test and discard ideas without justifying ROI or consuming sprint capacity.
- •Bot specialization by life domain: Organize Grok Bot instances into distinct life and work categories — calendar manager, email manager, chief of staff, legal adviser, language tutor — and chain tasks together, such as purchasing 3D printing filament and automatically updating a Notion inventory record in a single delegated instruction.
- •Insurance coverage bot setup: Create a dedicated bot loaded with your specific insurance plan details, then submit any receipt, prescription, or provider invoice to it for automatic coverage analysis. The bot flags whether follow-up claims are needed and confirms maximum savings are captured, removing manual policy cross-referencing from routine healthcare decisions.
Notable Moment
While live on the podcast recording, John's Figma bot continued completing a marketing asset production task in the background — autonomously updating copy, backgrounds, and images across multiple templates — demonstrating that design production work can run concurrently with other professional obligations without any active supervision.
Episode Transcript
I use AI to get me off my computer, not on my computer. And so the fact that you were at the gym, got asked to do something, and your disability be like, yep. Go for it. Get it done and finish your workout. It's like a much nicer way to work. I was able to just screenshot in Figma these two separate artboards of work that was already in progress. And doing so, I just pointed to those, had the bot do its work. I I didn't even read most of this stuff. It produced three outputs, copy pasted what Ben had sent me on Slack, and said, think got all these covered. While I'm on this call, work is getting done, which I really love. I think the fact that I don't have to do this stuff myself is a godsend. Now when I go somewhere, I can basically just send Grokbaud a photo, a screenshot, or literally just the name of the place, and it'll figure out what the place is. It'll look it up through Google Places API, and I get the right location it coordinates. It'll fix the perspective and then remove people and turn it into, like, a three d miniature visual style that I use on the site. AI can feel like a threat to the creative arts. Like, look. Your highest calling was never to design gradient fills in Figma. And what I tell people is Welcome back to How I AI. I'm Claire Vaux, product leader and AI obsessive here on a mission to help you build better with these new tools. Today, have John and Pong from the Grock Bot Design team, and they're gonna show us two really awesome AI design use cases. One, how to build a beautiful custom and easy to update personal site that meets the bar of a designer, and two, how Grock Bot was used to design Gropp Bot including where Figma Bro can make your life at the gym and work a lot easier. Let's get to it. This episode is brought to you by WorkOS. AI has already changed how we work. Tools are helping teams write better code, analyze customer data, and even handle support tickets automatically. But there's a catch. These tools only work well when they have deep access to company systems. Your copilot needs to see your entire code base. Your chatbot needs to search across internal docs. And for enterprise buyers, that raises serious security concerns. That's why these apps face intense IT scrutiny from day one. To pass, they need secure authentication, access controls, audit logs, the whole suite of enterprise features. Building all that from scratch? It's a massive lift. That's where Work OS comes in. Work OS gives you drop in APIs for enterprise features so your app can become enterprise ready and scale up market faster. Think of it like Stripe for enterprise features. OpenAI, Perplexity, and Cursor are already using Work OS …
Get the full transcript (7,756 words) + summary by email — free
One-time email with the complete transcript and AI summary of this episode. No account needed.
One email, no spam. We’ll also show you what SignalCast does.
You just read a 3-minute summary of a 38-minute episode.
Get How I AI summarized like this every Monday — plus up to 2 more podcasts, free.
Pick Your Podcasts — FreeKeep Reading
More from How I AI
Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy
Sep 7 · 50 min
Marketing Against the Grain
Meta’s AI Agent is Better Than OpenClaw (Manus AI Demo)
Feb 19
More from How I AI
GPT-6 Astra is a banger - here’s everything I’ve built
Sep 3 · 32 min
The Startup Ideas Podcast
Making $$$ with OpenClaw
Feb 18
More from How I AI
We summarize every new episode. Want them in your inbox?
Build your own company brain: the enterprise AI playbook from Stripe’s engineering team | Sharadh Krishnamurthy
GPT-6 Astra is a banger - here’s everything I’ve built
Grok Bot vs. OpenClaw: How I replaced my entire agent stack
How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)
I spent $20,000 on Devin in a month. Here’s what I learned | Ryan Carson (solo founder)
Similar Episodes
Related episodes from other podcasts
Marketing Against the Grain
Feb 19
Meta’s AI Agent is Better Than OpenClaw (Manus AI Demo)
The Startup Ideas Podcast
Feb 18
Making $$$ with OpenClaw
The Productivity Show
Feb 16
What's Possible with AI in 2026: From Flashy Demos to Quiet Leverage (TPS600)
This Week in Startups
Feb 12
How These 3 Founders are building on Open Claw | E2248
This Week in Startups
Jan 31
AI Bots Take Over | E2242
Explore Related Topics
This podcast is featured in Best AI Podcasts (2026) — ranked and reviewed with AI summaries.
Read this week's Health & Longevity Podcast Insights — cross-podcast analysis updated weekly.
You're clearly into How I AI.
Every Monday, we deliver AI summaries of the latest episodes from How I AI and 192+ other podcasts. Free for one show.
Start My Monday DigestNo credit card · Unsubscribe anytime