Rethinking Search as Code Generation

kept by eddie jun 02

Perplexity introduces Search as Code (SaC), an architecture that exposes search stack components as programmable SDK primitives for AI agents to compose via generated Python code.

{{IW4QaZoc2}}
Perplexity open-sources Bumblebee, a read-only scanner that checks developer machines for risky packages, extensions, and AI tool configs during supply-chain incidents.
also on Perplexity Computer, Perplexity, #developer-tools
How AI Agents Reshape Knowledge Work
Perplexity's agent orchestrator, Computer, cuts knowledge-work time by 87% and cost by 94% by shifting users from manual execution to supervision and expanding task scope across occupational boundaries.
also on Perplexity Computer, #ai-agents, #developer-tools
Search | The Moat of the Search Index - by FD - Robonomics
The author argues that the traditional search index moat is largely gone because AI assistants like ChatGPT use multi-hop reasoning across multiple sources, hiding individual search failures.
also on Perplexity, #search-engine
Perplexity Comet: A Reversing Story
The article provides a technical deep-dive into Perplexity's agentic browser Comet, detailing its dual-channel communication, hard boundaries, and page representation for AI interaction.
also on Perplexity, #ai-agents, #developer-tools