Advanced Guide to AI Prototyping with Sachin Rekhi (Reforge)
The Growth Podcast
Why AI Prototypes Often Feel Like 'Slop'
Sachin defines AI slop, explaining generic styling, vanilla features, and why initial outputs can't be shipped.
Today’s Episode
When you first start using AI prototyping tools, you get wowed.
You type “create me a CRM application” and boom a fully functioning app appears in 60 seconds.
But here’s the problem.
It looks generic. The styling is basic. The features are vanilla. You’d never ship this to customers.
This is AI slop.
Sachin Rekhi was the former Head of Product at LinkedIn Sales Navigator. He’s now teaching thousands of PMs at Reforge how to master AI prototyping.
----
Brought to you by - Reforge:
Get 1 month free of Reforge Build (the AI prototyping tool built for PMs) with code BUILD
----
Key Takeaways:
1. Product shaping changes everything - Anthropic builds multiple prototypes for every problem, launches internally, sees what people use, then productionizes winners. This used to only be possible at Apple with massive labs.
2. AI slop is real - Type "create a CRM" and you get generic styling, vanilla features, basic scenarios. Looks magical but you'd never ship it. The challenge is going from slop to production-grade prototypes.
3. The 15-skill mastery ladder - Apprentice level: prompting, editing, design consistency. Journeyman: versioning, debugging, diverging. Master: functional prototyping, product shaping, analytics integration.
4. Design consistency starts with baselining - Take screenshot of your product. Recreate it. Iterate until perfect. Save as template. Now every prototype inherits your design system automatically.
5. Diverging is the secret weapon - Generate 4 design variants instead of 1. Magic Patterns has this built in. Or use multiple tools to get 8 options. Evaluate alternatives like designers do.
6. Functional prototypes unlock real validation - Integrate OpenAI API for actual responses. Add PostHog for session recordings and heatmaps. Build surveys. Track clicks. Test with real data, not mockups.
7. The tools face-off: which to actually use - Bolt for speed. V0 for beautiful UIs. Replit for full-stack. Magic Patterns for product teams with diverging. Reforge Build for context integration. Cursor for technical PMs.
8. The $5/month unlimited execution hack - Host n8n on Hostinger instead of paying per execution. Get unlimited runs. Build workflow that backs up to Google Drive for version history.
9. PMs can build what used to require engineering - Calendar integration. Email agents. Analytics dashboards. Multi-model comparison. Survey collection. All from prompts. No code required.
10. Traditional workflows beat agents for production - Workflows save tokens, run faster, and are more reliable. Use agents only when tasks need real decision-making. For known processes, use workflows.
----
Where to Find Sachin
* X
* Youtube
----
Related Content
Newsletters:
* Product Requirements Documents
Podcasts:
* Everything You Need to Know About AI
----
PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!
If you want to advertise, email productgrowthppp at gmail.
The AI-powered Podcast Player
