Overview
The product takes the large model as the cognitive core and the self-developed active agent engine as the core. As long as students express their intentions naturally, the agent can independently complete multi-step task planning, cross-system tool arrangement and execution. From "Check my grades for this semester" to "Remind me to hand in my homework tomorrow afternoon", one sentence can be completed without repeated switching between independent systems such as academic affairs, academic staff, and libraries. The product has a complete active intelligent link of "active perception — active decision — active touch": the system understands the students' habits and needs through behavior acquisition and image analysis. The large model decides whether and when to remind, and then pushes the service to the students, realizing the transition from "people looking for functions" to "function looking for people". At the same time, the product has built-in cross-session AI memory and MCP standard tool ecology, which is more and more understandable to users, and can flexibly dock with various campus systems. The project is dedicated to enabling every college student to have a campus smart assistant who understands him from the first day of admission.
Connected profiles
More General-purpose agents products
Sources · 0Sources & provenance
English text is maintained separately from the original record. Consult the original source before citing a fact.
No source links are available for this profile.
Original source text
Names may use phonetic renderings when no English name is supplied. The original wording is retained below.
产品以大模型为认知核心、以自研主动式 Agent 引擎为中枢，学生只需自然表达意图，Agent 便能自主完成多步任务规划、跨系统工具编排与执行。从“帮我查一下这学期的成绩”到“记得提醒我明天下午交作业”，一句话即可办妥，无需在教务、学工、图书馆等独立系统间反复切换。产品具备“主动感知—主动决策—主动触达”的完整主动智能链路：系统通过行为采集与画像分析理解学生习惯与需求，由大模型决策是否提醒、何时提醒，再经 推送把服务送到学生面前，实现从“人找功能”到“功能找人”的转变。同时，产品内置跨会话 AI 记忆与 MCP 标准工具生态，越用越懂用户，并可灵活对接各类校园系统。项目致力于让每位大学生从入学第一天起便拥有一位越用越懂他的校园智能助手。