Perplexity 把搜索从工具调用升级为代码生成，解决了智能体多步搜索效率低、难适配的问题。做 AI 智能体或搜索产品的开发者值得关注，可以直接在 Agent API 里体验。
Perplexity CEO Arav Srinivas 宣布，公司正从传统的“搜索作为网络抓取工具调用”转向“搜索即代码”架构。新架构让 AI 智能体直接编写 Python 代码调用搜索栈，而非逐次循环函数调用。这一转变旨在适应未来智能体环境中代码执行成为知识工作主流方式的趋势，使多步骤原语组合更自然，对智能体框架的变更更具适应性，并能受益于下一代模型在编程能力上的持续提升。该架构已通过 Perplexity Agent API 提供，并默认用于 Computer 模式。
We’re moving away from search as a web fetch tool call to search as codegen to be future proof in a ...
We’re moving away from search as a web fetch tool call to search as codegen to be future proof in a world where code execution inside agent harnesses is the way to do almost all of our knowledge work. Doing this lets you compose multi-step primitives far more naturally and be much more adaptable to changes made to the agent harness, as well as benefit from improvements in coding capabilities that are guaranteed to come from the next generation of frontier models. Perplexity @perplexity_ai Introducing Search as Code, our new search architecture for AI agents. It writes Python that calls our search stack directly, instead of looping through function calls one at a time. Available in the Perplexity Agent API, and now default in Computer. research.perplexity.ai/articles/rethi… 🔗 View Quoted Tweet 💬 21 🔄 10 ❤️ 168 👀 19415 📊 39 ⚡