产品

Perplexity Brain 可自动编写并更新个性化 Agent 技能

精选理由

Perplexity 的 Brain 会翻你过去的会话轨迹,自动给你写 Agent 技能。8 周测试里 72.9% 用户拿到了个性化技能,失败率还降了 11%。做 Agent 自我改进方向的人值得看看这个实证数据。

Perplexity 公布了 Computer Brain 的自改进技能研究:Brain 在已有的工作知识 wiki 基础上,会根据用户过往会话自动编写和更新 Agent 技能。一个改进 Agent 会读取完整会话轨迹(工具调用、推理过程、结果),识别重复出现的模式,只有证据充足时才提出新技能或更新。

正文

内置技能的变更则需要经过失败场景的成对回放测试和工程师审查后才能上线。在为期 8 周的生产流量随机测试中,72.9% 的用户获得了至少一个新个性化技能,而手动添加技能的比例仅 6.5%;工具调用失败率下降 11%,不满意的会话线程下降 7.6%,成本和延迟无可测变化。

原文 · Aravind Srinivas

Sharing new research on self-improving skills in Perplexity Computer. Brain, which already maintains a knowledge wiki about your work, now also writes and updates agent skills for you based on your past sessions. An improvement agent reads the full session trajectories (tool calls, reasoning, results), finds recurring patterns, and only proposes a new skill or an update when there’s enough evidence. Built-in skills that every user gets go through paired replay on failure scenarios and engineer review before any change goes live. In an 8-week randomized test on production traffic, 72.9% of users got at least one new personal skill vs 6.5% who added one manually. Tool call failures dropped 11% and dissatisfied threads dropped 7.6%, with no measurable change in cost or latency. Perplexity @perplexity_ai Computer's personalized self-improvement agent, Brain, now automatically creates self-improving agent skills for you. Brain learns how you work from past sessions and memory, then writes and updates personalized skills for future tasks. 🔗 View Quoted Tweet📊 31 ⚡

产业坐标与信源核验

本条情报归属 AITOP「产品」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Perplexity、Agent技能、智能体、自动化工作流,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「Aravind Srinivas」(@AravSrinivas),经 AITOP 多维评分管线结构化提炼。