Perplexity 分享内部实践：Agent 开始越来越多地调用其他 Agent
Perplexity 内部已经是 Agent 给 Agent 发提示词了，他们还把 git 当作整套编排的核心，做法挺值得对照自己的工作流看看。
Perplexity 联合创始人 Arav Srinivas 发文称，公司内部的 Agent 提示词已不再由人工输入，越来越多场景是团队成员的 Agent 相互提示、监听自动化流程和人类反馈。这套编排以 git 为核心：Agent 以代码模式运行，运行轨迹纳入版本控制，形成可递归的自动化闭环。Perplexity 将业务事实的 ground truth 集中在 git 仓库和数据仓库中，而非中间产物，以此连接组织内大量云工具并 24/7 监控数据。Srinivas 提到，即便是 AI 原生公司，Perplexity 也花了数月开发和文化转型才走到这一步。
Agents are going to be used increasingly by other agents. Simply because the orchestration is easier and can centralize around one compounding system of record: git. When agents run code-mode and traces are version controlled, you get to a real recursive loop, measurable by less human in the loop. Johnny Ho @randomjohnnyh At Perplexity, agent prompts are no longer typed by humans: increasingly teammates are prompting each other, listening to automations, and ambiently listening to human feedback. Perplexity bridges the context between a large number of cloud tools and software services: searching and processing more than a human could possibly track manually. Hard decisions, restraint, and judgment before shipping are of course still enforced by humans. A particularly important value at Perplexity is to always seek the truth. In today's stack, this means centralizing the ground truth in git repos and data warehouses when answering questions about the business, instead of looking at intermediate, often inaccurate or outdated artifacts. This is what enterprise cloud agents like Perplexity are especially good at: connecting the dots across your organization and monitoring the facts 24/7. Even as an AI-native company it took us many months of development and cultural transformation to get to this point. It will be fascinating what the world looks like when all businesses reach this level of automation and beyond. 🔗 View Quoted Tweet 💬 12 🔄 2 ❤️ 18 👀 3459 📊 9 ⚡
