Rethinking Search as Code Generation
Perplexity is introducing 'Search as Code' (SaC), a new architecture that allows AI agents to programmatically interact with search primitives. This shift moves away from monolithic search engines toward a more flexible, agent-driven retrieval strategy.
Why it matters
As AI agents become more complex, they require more granular control over data retrieval, making this a significant evolution in search infrastructure.
Evolving search from monolithic services to programmable primitives for the era of agent harnesses.
The content is a technical explanation of a new architectural approach in the AI industry.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in