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

Brad Menezes, CEO of Superblocks, believes that billion-dollar startup ideas often lie in the system prompts of existing AI unicorns. These lengthy prompts guide foundational AI models in generating applications tailored to specific tasks. Superblocks recently raised $23 million and shared system prompts from notable AI coding products. Menezes noted that while system prompts contribute to their success, 'prompt enrichment' plays an even larger role, involving the infrastructure built around leveraging language models, which together create effective AI solutions for enterprises.
Every single company has a completely different system prompt for the same foundational model. They're trying to get the model to do exactly what's required for a specific domain.
The system prompt itself is maybe 20% of the secret sauce. The other 80% is 'prompt enrichment', which includes the infrastructure a startup builds around the calls to the LLM.
Read at TechCrunch
[
|
]