Perplexity Search as Code: agents write their own retrieval

Perplexity Research released the Search as Code (SaC) architecture, splitting the search API into programmable primitives and letting AI Agents write their own Python retrieval scripts to execute in a sandbox. On 200 CVE-tracking tasks, accuracy rose from 25% in the mainstream pipeline to 100%, token consumption was cut by 85%, and WANDR was accelerated 2.5×. The architecture has landed in Perplexity Computer and the Agent API.