Perplexity: Introducing Hybrid Agentic Inference & Search as Code (SaC)
- 2. Juni
- 1 Min. Lesezeit
Key Takeaways:
Perplexity announced some great updates such as introducing Hybrid Agentic Inference and Search as Code
Hybrid Agentic Inference enables you to split tasks between a local model running on your machine and frontier models in the cloud. This keeps private data on your device and maximizes token efficiency
Only let Perplexity access a local folder and run a local model via a subagent, then switching to more powerful, expensive models in the cloud
Search as Code changes how Perplexity approaches Search Retrieval and Query Fanouts: Instead of the LLM calling MCP tools, it spawns python scripts to call search functions tailored to the task
Traditionally, AI systems have treated search as a monolith: an AI model issues a query, the search engine runs its predefined pipeline, and the model consumes the results as context
However, the most powerful AI systems will require the ability to steer how that context is retrieved, processed, aggregated, and rendered to the model.
This new architecture empowers models to reach into the search stack itself rather than merely consume its final outputs.
we expose the components of the search stack as primitives within an SDK. For any request that needs search, a model assembles these primitives on-demand into a retrieval pipeline tailored to that specific request.
No usage of a traditional Search API: Instead, we've carefully engineered an Agentic Search SDK that exposes the individual building blocks of search at the most atomic level possible.
Do not waste time or thoughts, just test it
Sources:
