Superblocks CEO: How to find a unicorn idea by studying AI system prompts

INSUBCONTINENT EXCLUSIVE:
Brad Menezes, CEO of enterprise vibe-coding startup Superblocks, believes the next crop of billion-dollar startup ideas is hiding in almost
that AI startups use to instruct the foundational models from companies like OpenAI or Anthropic on how to generate their application-level
AI products
Customers can ask many AI tools to share theirs
Clark, Superblocks offered to share a file of 19 system prompts from some of the most popular AI coding products like Windsurf, Manus,
formerly of Founders Fund and Brex, and Aaron Levie, a Superblocks investor
builds around the calls to the LLM
accuracy.He said there are three parts of system prompts to study: role prompting, contextual prompting, and tool use.The first thing to
notice is that, while system prompts are written in natural language, they are exceptionally specific
You are a real code-wiz: few programmers are as talented as you at understanding codebases, writing functional and clean code, and iterating
helped Menezes see what other vibe coders emphasized
could handle more, such as security and access to enterprise data sources like Salesforce
While Menezes is not yet running the multibillion-dollar startup of his dreams, Superblocks has landed some notable companies as customers,
His software engineers are not allowed to write internal tools; they can only build the product
So his business folks have built agents for all their needs, like one that uses CRM data to identify leads, one that tracks support metrics,
Series A total amount raised.