逐日AI微信小程序
← 返回全部课程题库

30 天从前端工程师到 Agent 工程师

课程题库 · 127 / 127 道题

标签
还有 136 个标签
#operations6#sse6#deployment5#message-bus5#tool-calling5#agent-loop4#behavioral4#error-handling4#evaluation4#framework-design4#mcp4#routing4#concurrency3#context-engineering3#interview-prep3#langgraph3#llm-basics3#model-routing3#orchestration3#prompt-injection3#protocol3#redis-streams3#scalability3#scheduling3#agent-design2#auth2#checkpointing2#communication2#cost-control2#database2#debugging2#interview-process2#latency2#long-term-memory2#memory2#ordering2#prompt-engineering2#rate-limiting2#react2#resume2#retrieval2#sharding2#state-machine2#state-management2#tool-design2#tool-permissions2#trade-offs2#ux2#agent-basics1#agent-quality1#async1#atomicity1#cancellation1#capacity-planning1#career1#chunking1#compression1#configuration1#consistent-hashing1#context1#context-compression1#context-management1#correctness1#customer-support1#data-modeling1#deliberate-practice1#docker1#documentation1#engineering-tradeoffs1#escalation1#event-driven1#fallback1#fan-out1#fencing-token1#forking1#framework-selection1#frontend1#global-market1#hybrid-search1#interrupt-merge1#isolation1#json-parsing1#jwt1#knowledge-organization1#lease1#least-privilege1#llm-as-judge1#loop-guard1#mobile1#multi-tenancy1#nodejs1#performance1#persistence1#pgvector1#portfolio1#prioritization1#proactive-messaging1#product-engineering1#project-storytelling1#prompt1#provider-abstraction1#quiet-hours1#ranking1#recall1#reconnect1#redis1#reflection1#replay1#reporting1#rerank1#retrieval-quality1#retry1#retry-semantics1#rrf1#sampling1#sandboxing1#schema-design1#secrets-management1#self-assessment1#self-introduction1#self-presentation1#service-architecture1#session-management1#split-brain1#star1#stateless1#storytelling1#structured-output1#system-prompt1#testing1#timezone1#tool-execution1#tools1#tracing1#transport1#vector-database1

D1 LLM API 基础:messages/roles、token、流式、temperature;Agent 到底是什么

  • 什么是 token 和上下文窗口?它们如何影响 Agent 的设计?What are tokens and the context window, and how do they shape agent design?
    国内高频海外高频基础#llm-basics#context

    🔒 解锁 D1 后查看答题要点。

  • messages 里的 system / user / assistant 三种角色各起什么作用?为什么要有 system?What do the system / user / assistant roles do, and why does system exist?
    国内高频海外高频基础#llm-basics#prompt

    🔒 解锁 D1 后查看答题要点。

  • 为什么 LLM 应用几乎都用流式输出?SSE 和 WebSocket 该怎么选?Why do LLM apps stream responses, and how do you choose between SSE and WebSockets?
    国内高频海外高频进阶#streaming#protocol

    🔒 解锁 D1 后查看答题要点。

  • 聊天机器人和 Agent 的本质区别是什么?What fundamentally separates a chatbot from an agent?
    国内高频海外高频基础#agent-basics

    🔒 解锁 D1 后查看答题要点。

  • temperature 和 top_p 分别控制什么?什么场景用 0,什么场景用 0.7?What do temperature and top_p control, and when would you use 0 versus 0.7?
    海外高频基础#llm-basics#sampling

    🔒 解锁 D1 后查看答题要点。

  • 流式回复到一半网络断了,前端和后端各要做什么?EventSource 的自动重连能用上吗?A streaming reply is cut off mid-way. What do the client and server each do, and can EventSource auto-reconnect help?
    国内高频海外高频进阶#streaming#reliability#sse

    🔒 解锁 D1 后查看答题要点。

  • 用户切到后台或者直接关掉网页,回来后怎么恢复那条还在生成的回复?The user backgrounds the app or closes the tab. How do you restore a reply that was still being generated?
    国内高频海外高频深入#streaming#reliability#architecture

    🔒 解锁 D1 后查看答题要点。

  • 断线重试之后,怎么保证不重复计费、也不重复执行已经做过的工具调用?After a retry, how do you avoid double billing and re-executing tool calls that already ran?
    国内高频海外高频深入#reliability#tools#idempotency

    🔒 解锁 D1 后查看答题要点。

  • 移动端 App 里的对话,网络频繁抖动,你会怎么设计重连策略?On mobile, connectivity is flaky. How would you design the reconnection strategy for a chat feature?
    国内高频海外高频进阶#reliability#mobile#streaming

    🔒 解锁 D1 后查看答题要点。

  • 用户主动点「停止生成」和网络意外断开,在服务端看起来都是连接没了,怎么区分处理?A user pressing stop and a dropped connection both look like a closed connection server-side. How do you tell them apart?
    国内高频海外高频深入#streaming#reliability#ux

    🔒 解锁 D1 后查看答题要点。

D2 工具调用原理:JSON Schema、tool_use 循环;不用框架手写 Agent Loop

  • function calling 的完整流程是怎样的?Walk me through the complete function calling flow.
    国内高频海外高频基础#tool-calling#agent-loop

    🔒 解锁 D2 后查看答题要点。

  • 什么是 ReAct 模式?它和你手写的工具调用循环是什么关系?What is the ReAct pattern, and how does it relate to a hand-rolled tool-calling loop?
    国内高频海外高频进阶#react#agent-loop#tool-calling

    🔒 解锁 D2 后查看答题要点。

  • 工具执行报错时,应该怎么把错误信息传给模型?有没有不该传的?When a tool fails, how should the error reach the model — and what must never reach it?
    国内高频海外高频进阶#tool-calling#error-handling

    🔒 解锁 D2 后查看答题要点。

  • 怎么防止 Agent 循环停不下来?只加一个最大步数够吗?How do you keep an agent loop from running forever — is a max-step counter enough?
    国内高频海外高频深入#agent-loop#reliability#cost

    🔒 解锁 D2 后查看答题要点。

D3 Pi SDK 上手:三层架构、Agent Loop 对照(dg P01/P02/M02/M03)

  • Agent 框架内部的 Agent Loop 一般要解决哪些问题?What problems does an agent framework's built-in agent loop have to solve?
    国内高频海外高频基础#agent-loop#framework-design

    🔒 解锁 D3 后查看答题要点。

  • 选择使用 Agent 框架还是手写 Agent,你会怎么权衡?How do you decide between adopting an agent framework and hand-rolling the loop?
    国内高频海外高频进阶#framework-design#engineering-tradeoffs

    🔒 解锁 D3 后查看答题要点。

  • Pi SDK 的三层架构分别对应什么职责?这样分层解决了什么问题?What are the responsibilities of Pi SDK's three layers, and what does that layering buy you?
    国内高频海外高频基础#framework-design#architecture

    🔒 解锁 D3 后查看答题要点。

  • 用了 Agent 框架之后,你怎么知道它内部到底发生了什么?出问题从哪里查?Once you adopt an agent framework, how do you know what it is doing internally, and where do you start debugging?
    国内高频海外高频深入#observability#framework-design#debugging

    🔒 解锁 D3 后查看答题要点。

D4 模型接入与系统提示词:多 provider 抽象与 fallback、覆盖默认人设(dg P03/P04/M04)

  • 为什么生产级 Agent 通常要接入多个模型 provider?Why do production agents usually integrate more than one model provider?
    国内高频海外高频基础#model-routing#reliability

    🔒 解锁 D4 后查看答题要点。

  • 设计模型 fallback 策略时要权衡哪些因素?What trade-offs shape a model fallback strategy?
    国内高频海外高频进阶#model-routing#reliability#cost

    🔒 解锁 D4 后查看答题要点。

  • 系统提示词(system prompt)在 Agent 里起什么作用?为什么不能用框架默认的?What does the system prompt do in an agent, and why not rely on the framework default?
    国内高频海外高频进阶#prompt-engineering#system-prompt

    🔒 解锁 D4 后查看答题要点。

  • 如何在成本和延迟之间给不同任务选择合适的模型?How do you pick the right model per task, balancing cost against latency?
    国内高频海外高频进阶#model-routing#cost#latency

    🔒 解锁 D4 后查看答题要点。

D5 工具系统与事件驱动:参数校验、错误回传让模型自纠错、事件订阅(dg P05/P06/M05/M07)

  • 设计 Agent 的工具时你会遵循哪些原则?名字、描述、参数分别该怎么写?What principles do you follow when designing tools for an agent — how do you write the name, the description and the parameter schema?
    国内高频海外高频基础#tool-design#prompt-engineering

    🔒 解锁 D5 后查看答题要点。

  • 工具调用报错或参数非法时,你怎么让模型自己纠正而不是直接失败?When a tool call fails validation or errors out, how do you get the model to correct itself instead of failing the whole turn?
    国内高频海外高频进阶#tool-calling#error-handling

    🔒 解锁 D5 后查看答题要点。

  • Agent 的事件系统一般会暴露哪些生命周期事件?为什么不能只等最终返回值?Which lifecycle events does an agent runtime typically expose, and why is waiting for the final return value not enough?
    国内高频海外高频进阶#event-driven#observability

    🔒 解锁 D5 后查看答题要点。

  • 怎么限定工具的权限边界,避免 Agent 越权操作?把规则写进系统提示词够不够?How do you bound an agent's tool permissions, and is putting the rules in the system prompt enough?
    国内高频海外高频深入#tool-permissions#security#prompt-injection

    🔒 解锁 D5 后查看答题要点。

D6 消息、上下文工程与压缩、会话存储/恢复/分叉(dg M06/M08/M09/M10)

  • 长对话里上下文放不下了,你会怎么压缩?什么时候触发、压掉什么、保留什么?When a long conversation outgrows the context window, how do you compress it — when do you trigger, what do you drop, and what do you keep?
    国内高频海外高频进阶#context-engineering#compression#cost

    🔒 解锁 D6 后查看答题要点。

  • 会话的持久化、恢复和分叉分别解决什么问题?实现时各有什么坑?What problems do session persistence, restore, and forking each solve, and what goes wrong in each?
    国内高频海外高频进阶#session-management#persistence#forking

    🔒 解锁 D6 后查看答题要点。

  • 短期上下文和长期记忆的边界怎么划?一条信息该往哪放,你的判断依据是什么?Where do you draw the line between short-term context and long-term memory, and how do you decide where a given fact belongs?
    国内高频海外高频基础#memory#context-engineering

    🔒 解锁 D6 后查看答题要点。

  • 上下文工程和 RAG 检索是什么关系?只做 RAG 不做上下文管理会出什么问题?How do context engineering and RAG relate, and what breaks if you do RAG without context management?
    国内高频海外高频深入#context-engineering#rag#retrieval

    🔒 解锁 D6 后查看答题要点。

D7 封装成服务:Fastify + SSE + Docker(dg P07);W1 复盘

  • 流式返回大模型回复,你会选 SSE 还是 WebSocket?为什么?For streaming LLM responses, would you pick SSE or WebSocket, and why?
    国内高频海外高频基础#sse#streaming#api-design

    🔒 解锁 D7 后查看答题要点。

  • 把一个本地跑的 Agent 脚本改造成生产服务,接口层要重点考虑哪些事?When turning a local agent script into a production service, what does the interface layer have to get right?
    国内高频海外高频进阶#api-design#service-architecture#streaming

    🔒 解锁 D7 后查看答题要点。

  • 把一个 Node 服务打包成 Docker 镜像,Dockerfile 里有哪些关键决定?What are the key decisions in a Dockerfile that packages a Node service?
    国内高频海外高频进阶#docker#deployment#nodejs

    🔒 解锁 D7 后查看答题要点。

  • 一个 SSE 长连接服务上线,心跳、连接断开处理和优雅退出分别在解决什么问题?For a long-lived SSE service in production, what problems do heartbeats, disconnect handling and graceful shutdown each solve?
    国内高频海外高频深入#sse#reliability#deployment

    🔒 解锁 D7 后查看答题要点。

  • 自我介绍时,怎么在两分钟里讲清楚一个 Agent 项目的价值?In a two-minute self-introduction, how do you convey the value of an agent project?
    国内高频海外高频基础#interview-prep#communication

    🔒 解锁 D7 后查看答题要点。

D8 为什么 Gateway/Worker 分离;Postgres 表设计(sessions/runs/messages)+ Drizzle

  • 为什么生产级 Agent 服务通常要把 Gateway 和 Worker 拆开?什么情况下不该拆?Why do production agent services usually split a gateway from workers, and when should you not split?
    国内高频海外高频基础#architecture#scalability

    🔒 解锁 D8 后查看答题要点。

  • 什么是无状态服务?它对水平扩展意味着什么?Worker 算不算有状态?What makes a service stateless, what does that mean for horizontal scaling, and are workers stateful?
    国内高频海外高频进阶#stateless#scalability

    🔒 解锁 D8 后查看答题要点。

  • 消息总线是至少一次投递,同一条消息被重复投递时,怎么保证不会产生两条 run?With at-least-once delivery, how do you guarantee a redelivered message does not create two runs?
    国内高频海外高频深入#idempotency#database#reliability

    🔒 解锁 D8 后查看答题要点。

  • sessions / runs / messages 这三张表你会怎么设计主键与索引?为什么不用自增主键?How would you design primary keys and indexes for sessions, runs and messages, and why avoid auto-increment ids?
    国内高频海外高频进阶#database#schema-design#idempotency

    🔒 解锁 D8 后查看答题要点。

D9 Redis Streams 消息总线:XADD/XREADGROUP/XACK/XAUTOCLAIM、consumer group、毒消息

  • Redis Streams 的 consumer group 是怎么工作的?为什么它既能做工作队列又能做发布订阅?How does a Redis Streams consumer group work, and why can it serve both as a work queue and as pub/sub?
    国内高频海外高频基础#message-bus#redis-streams

    🔒 解锁 D9 后查看答题要点。

  • XACK 和 XAUTOCLAIM 分别解决什么问题?XACK 放在业务处理之前和之后有什么区别?What problems do XACK and XAUTOCLAIM each solve, and what changes if you XACK before instead of after doing the work?
    国内高频海外高频进阶#message-bus#redis-streams#error-handling

    🔒 解锁 D9 后查看答题要点。

  • 什么是 at-least-once?既然消息会被重复投递,业务上到底要怎么保证幂等?What is at-least-once delivery, and given that messages get redelivered, how do you actually make the business side idempotent?
    国内高频海外高频深入#message-bus#idempotency#reliability

    🔒 解锁 D9 后查看答题要点。

  • Redis Streams 和 Kafka 该怎么选?什么情况下 Streams 明显不够用?How do you choose between Redis Streams and Kafka, and when is Streams clearly not enough?
    国内高频海外高频进阶#message-bus#redis-streams#architecture

    🔒 解锁 D9 后查看答题要点。

  • 一条消息反复处理失败怎么办?请设计一个毒消息隔离机制。What do you do with a message that keeps failing? Design a poison-message isolation mechanism.
    国内高频海外高频进阶#message-bus#error-handling#reliability

    🔒 解锁 D9 后查看答题要点。

D10 分片与租约:userId 哈希→shard、SET NX + TTL + Lua 续约、同用户顺序、handoff

  • 为什么要对 userId 做哈希分片,而不是让消费组随机派发?分片数应该怎么选?Why hash user ids into shards instead of letting the consumer group dispatch freely, and how do you pick the shard count?
    国内高频海外高频基础#sharding#consistent-hashing#scalability

    🔒 解锁 D10 后查看答题要点。

  • 租约为什么必须配合 TTL?续约为什么要用 Lua 脚本,而不是先 GET 再 PEXPIRE?Why must a lease carry a TTL, and why renew it with a Lua script instead of GET followed by PEXPIRE?
    国内高频海外高频进阶#lease#redis#atomicity

    🔒 解锁 D10 后查看答题要点。

  • 两个 worker 同时认为自己持有同一个 shard 的租约(脑裂)会造成什么后果,怎么规避?What happens when two workers both believe they hold the same shard lease (split brain), and how do you mitigate it?
    国内高频海外高频深入#split-brain#fencing-token#reliability

    🔒 解锁 D10 后查看答题要点。

  • 在一个多 worker 的 Agent 服务里,怎么保证同一个用户的消息严格按顺序被处理?In a multi-worker agent service, how do you guarantee that one user's messages are processed in strict order?
    国内高频海外高频进阶#ordering#sharding#distributed-systems

    🔒 解锁 D10 后查看答题要点。

D11 run 状态机、输出流回传、按 runId 保序、SSE 等待者、30s 打断合并

  • 怎么设计一次 Agent 执行(run)的状态机?需要覆盖哪些异常状态?How would you design the state machine for one agent run, and which failure states must it cover?
    国内高频海外高频基础#state-machine#distributed-systems

    🔒 解锁 D11 后查看答题要点。

  • 多个客户端同时订阅同一次执行的流式输出,怎么保证每个客户端都收到完整且有序的内容?Several clients subscribe to the same run's streaming output at once. How do you guarantee each of them receives the full content in order?
    国内高频海外高频进阶#sse#ordering#fan-out

    🔒 解锁 D11 后查看答题要点。

  • 用户在 Agent 还没回复完的时候又发来一条消息,应该怎么处理?A user sends another message while the agent is still answering the previous one. How should the system handle it?
    国内高频海外高频进阶#interrupt-merge#state-machine#cost

    🔒 解锁 D11 后查看答题要点。

  • 流式接口的客户端断线重连后,怎么做到既不丢片段也不重复?After a streaming client reconnects, how do you deliver every missed chunk exactly once — no gaps, no duplicates?
    国内高频海外高频深入#sse#idempotency#reconnect

    🔒 解锁 D11 后查看答题要点。

D12 长期记忆:pgvector、embedding、chunking、memory_search 工具

  • 为什么 Agent 需要额外的长期记忆,而不是把历史全部塞进上下文?Why does an agent need a separate long-term memory instead of stuffing all history into the context window?
    国内高频海外高频基础#long-term-memory#rag#cost

    🔒 解锁 D12 后查看答题要点。

  • pgvector 和专用向量数据库相比,优劣分别是什么?你会怎么选?How does pgvector compare with a dedicated vector database, and how would you choose?
    国内高频海外高频进阶#vector-database#pgvector#architecture

    🔒 解锁 D12 后查看答题要点。

  • chunking 的切分策略会怎么影响检索效果?切多大合适?How does the chunking strategy affect retrieval quality, and how do you pick a chunk size?
    国内高频海外高频进阶#chunking#rag#retrieval-quality

    🔒 解锁 D12 后查看答题要点。

  • 把记忆检索包装成 memory_search 这样的工具时,参数设计上要注意什么?What matters when designing the parameters of a retrieval tool such as memory_search?
    国内高频海外高频深入#tool-design#security#long-term-memory

    🔒 解锁 D12 后查看答题要点。

D13 cron 调度(中心调度→stream 投递)+ 成本计量(token→USD 台账、usage report)

  • 服务部署了多个实例,定时任务为什么不能让每个实例各自起一个 cron?你会怎么做?When a service runs multiple replicas, why not let each replica start its own cron? What would you do instead?
    国内高频海外高频基础#scheduling#distributed-systems#cost

    🔒 解锁 D13 后查看答题要点。

  • 让你从零设计一套 token 成本计量和台账系统,你会怎么做?How would you design a token cost metering and ledger system from scratch?
    国内高频海外高频进阶#cost#observability#data-modeling

    🔒 解锁 D13 后查看答题要点。

  • 一份 LLM 应用的 usage report 通常要覆盖哪些维度?这些维度分别用来做什么决策?Which dimensions should a usage report for an LLM product cover, and what decision does each one drive?
    国内高频海外高频进阶#observability#cost#reporting

    🔒 解锁 D13 后查看答题要点。

  • 怎么保证一个 cron 任务不会被重复投递或重复执行?幂等键应该怎么构造?How do you keep a cron job from being published or executed twice, and how should the idempotency key be built?
    国内高频海外高频深入#idempotency#scheduling#distributed-systems

    🔒 解锁 D13 后查看答题要点。

D14 部署运维:compose 多 worker、心跳、健康检查、优雅停机、dev/prod 隔离;W2 复盘

  • 多实例部署下,怎么设计心跳和健康检查?两者是同一件事吗?With multiple replicas, how do you design heartbeats and health checks? Are they the same thing?
    国内高频海外高频进阶#observability#deployment#distributed-systems

    🔒 解锁 D14 后查看答题要点。

  • 什么是优雅停机?为什么直接 kill 进程有风险?请说出具体步骤。What is graceful shutdown, and why is killing a process outright risky? Walk through the steps.
    国内高频海外高频进阶#deployment#reliability#operations

    🔒 解锁 D14 后查看答题要点。

  • 滚动发布时,如何避免正在处理的任务被打断?During a rolling deploy, how do you keep in-flight tasks from being interrupted?
    国内高频海外高频进阶#deployment#reliability#operations

    🔒 解锁 D14 后查看答题要点。

  • 怎么设计 dev 与 prod 的隔离,防止本地开发影响线上数据?How do you isolate dev from prod so local development cannot touch production data?
    国内高频海外高频基础#operations#security#configuration

    🔒 解锁 D14 后查看答题要点。

  • 系统设计:请设计一个 IM Agent 平台——用户在即时通讯软件里和一个 AI 助手对话,助手能调用工具、记住长期偏好、还能定时主动推送。要求支撑十万日活。System design: design an IM agent platform where users chat with an AI assistant inside a messaging app. The assistant calls tools, remembers long-term preferences, and proactively pushes scheduled messages. Target 100k daily active users.
    国内高频海外高频深入#system-design#distributed-systems#cost#operations

    🔒 解锁 D14 后查看答题要点。

D15 多 Agent 模式全景(Router/Supervisor、Planner-Executor、Critic、Swarm、Blackboard)与何时不该用;LangGraph 入门

  • 常见的多 Agent 协作模式有哪些?分别适合什么形状的任务?What are the common multi-agent collaboration patterns, and what shape of task suits each?
    国内高频海外高频基础#multi-agent#orchestration#architecture

    🔒 解锁 D15 后查看答题要点。

  • LangGraph 里节点、边、状态分别扮演什么角色?如果不用框架,你自己会怎么实现?In LangGraph, what roles do nodes, edges and state play? If you had no framework, how would you implement it yourself?
    国内高频海外高频进阶#langgraph#orchestration#state-management

    🔒 解锁 D15 后查看答题要点。

  • 从单 Agent 升级到多 Agent,通常是被什么信号触发的?升级之后系统会多付出什么?What signals typically trigger the move from a single agent to a multi-agent system, and what does the upgrade cost you?
    国内高频海外高频进阶#multi-agent#cost#architecture

    🔒 解锁 D15 后查看答题要点。

  • 什么情况下不应该引入多 Agent 系统?请给出可操作的判据,而不是「视情况而定」。When should you not introduce a multi-agent system? Give operational criteria, not it depends.
    国内高频海外高频深入#multi-agent#architecture#trade-offs

    🔒 解锁 D15 后查看答题要点。

D16 Supervisor 动态路由:structured output 路由、override、routingReason

  • Supervisor 模式里的路由决策一般怎么实现?请说说这个节点该做什么、不该做什么。How is the routing decision usually implemented in a supervisor pattern? What should that node do, and what should it not do?
    国内高频海外高频基础#multi-agent#routing#langgraph

    🔒 解锁 D16 后查看答题要点。

  • 为什么要让模型输出 structured output 而不是自然语言来做路由?自然语言到底差在哪?Why use structured output rather than natural language for routing? What exactly goes wrong with free text?
    国内高频海外高频进阶#structured-output#routing#reliability

    🔒 解锁 D16 后查看答题要点。

  • 路由不确定或者路由错误时,系统应该怎么兜底?阈值该怎么定?How should the system handle an uncertain or wrong routing decision, and how do you pick the threshold?
    国内高频海外高频深入#routing#fallback#reliability

    🔒 解锁 D16 后查看答题要点。

  • routingReason 这类调试信息在生产系统里有什么价值?只是打日志而已吗?What is a field like routingReason actually worth in production? Is it just logging?
    国内高频海外高频进阶#observability#routing#debugging

    🔒 解锁 D16 后查看答题要点。

D17 Planner–Executor–Critic + 共享工作区:workspace state、toolBudget、并行 fan-out、review 回路

  • Planner-Executor-Critic 这种结构解决了什么问题?它和 Supervisor 路由的区别在哪?What problem does the Planner-Executor-Critic structure solve, and how is it different from Supervisor routing?
    国内高频海外高频基础#multi-agent#orchestration#architecture

    🔒 解锁 D17 后查看答题要点。

  • 多个子任务并行执行、都要写同一份共享状态时,怎么设计才不会互相覆盖?When several subtasks run in parallel and all write the same shared state, how do you design it so they do not clobber each other?
    国内高频海外高频深入#multi-agent#state-management#concurrency

    🔒 解锁 D17 后查看答题要点。

  • 为什么要给每个子任务设 toolBudget 这样的预算?超了预算之后你会怎么处理?Why give each subtask a tool-call budget, and what do you do when it runs out?
    国内高频海外高频进阶#cost-control#reliability#agent-design

    🔒 解锁 D17 后查看答题要点。

  • Critic 的评审回路怎么防止陷入死循环?除了次数上限还有什么要防的?How do you keep a Critic review loop from spinning forever, and what else needs guarding besides a retry cap?
    国内高频海外高频进阶#reflection#loop-guard#reliability

    🔒 解锁 D17 后查看答题要点。

D18 历史保真与摘要、多模态占位、checkpointer 持久化

  • 记忆应该怎么分层?短期上下文、摘要、长期记忆分别放什么、丢了会怎么样?How should agent memory be layered? What belongs in short-term context, in summaries, and in long-term memory — and what happens when each is lost?
    国内高频海外高频基础#memory#context-management#multi-agent

    🔒 解锁 D18 后查看答题要点。

  • 长对话做摘要时,怎么保证关键信息不丢?在多 Agent 场景下这件事有什么特别的?When summarizing a long conversation, how do you keep the critical information from being lost — and what is different about this in a multi-agent system?
    国内高频海外高频进阶#context-compression#multi-agent#reliability

    🔒 解锁 D18 后查看答题要点。

  • 从 checkpoint 恢复执行(replay)需要注意什么?说几个真实会踩的坑。What do you need to watch out for when replaying execution from a checkpoint? Give failure modes you would actually hit.
    国内高频海外高频深入#checkpointing#replay#reliability

    🔒 解锁 D18 后查看答题要点。

  • checkpointer 在多 Agent 系统里解决了什么问题?它的代价是什么?What problem does a checkpointer solve in a multi-agent system, and what does it cost?
    国内高频海外高频进阶#checkpointing#cost#operations

    🔒 解锁 D18 后查看答题要点。

D19 跨服务 Agent 集成:用户级 JWT 铸造、JWKS 验签、inject/memory/usage 三类接口、幂等 externalId

  • 两个服务之间调用,你会用服务级令牌还是用户级令牌?分别适用于什么场景?For service-to-service calls, would you use a service token or a user token? When does each apply?
    国内高频海外高频进阶#auth#security#api-design

    🔒 解锁 D19 后查看答题要点。

  • JWKS 验签是怎么工作的?为什么跨服务场景下它比共享密钥更合适?How does JWKS-based verification work, and why does it fit cross-service scenarios better than a shared secret?
    国内高频海外高频基础#auth#jwt#security

    🔒 解锁 D19 后查看答题要点。

  • 跨服务调用的幂等键该怎么设计?由谁生成、存在哪、重复了返回什么?How do you design an idempotency key for cross-service calls — who generates it, where does it live, and what do you return on a repeat?
    国内高频海外高频进阶#idempotency#distributed-systems#api-design

    🔒 解锁 D19 后查看答题要点。

  • 设计一组给外部服务调用的 Agent 平台接口,你会怎么划分职责边界?You are designing the API surface an Agent platform exposes to other services. How do you draw the responsibility boundaries?
    国内高频海外高频深入#api-design#security#architecture

    🔒 解锁 D19 后查看答题要点。

D20 定时 Job 与主动关怀:时区、quiet hours、每日上限、通知 provider 抽象

  • 系统主动发给用户的消息,和用户自己触发的消息,在系统设计上有什么不同?How does a system-initiated message differ from a user-triggered one, from a system design point of view?
    国内高频海外高频基础#proactive-messaging#system-design#product-engineering

    🔒 解锁 D20 后查看答题要点。

  • 做一个面向全球用户的定时推送服务,时区上你会踩到哪些坑?夏令时切换那天怎么处理?Building a scheduled push service for users worldwide, what timezone pitfalls would you hit, and how do you handle the DST switchover day?
    国内高频海外高频深入#timezone#scheduling#correctness

    🔒 解锁 D20 后查看答题要点。

  • quiet hours 和每日发送上限这两条规则你会怎么实现?它们应该放在链路的哪一步判断?How would you implement quiet hours and a per-user daily cap, and where in the pipeline should they be evaluated?
    国内高频海外高频进阶#rate-limiting#quiet-hours#cost-control

    🔒 解锁 D20 后查看答题要点。

  • 模型调用、支付、通知渠道你都做过 provider 抽象。通知这一份接口和另外两份有什么不同?You have abstracted model calls, payments and notification channels behind providers. How does the notification interface differ from the other two?
    国内高频海外高频进阶#provider-abstraction#api-design#retry-semantics

    🔒 解锁 D20 后查看答题要点。

D21 评估与可观测:golden set、LLM-as-judge、tracing、失败率/成本面板;Pi vs LangGraph 总结;W3 复盘

  • 怎么评估一个 Agent 的效果?和传统后端服务的测试有什么不同?How do you evaluate an agent's quality, and how does it differ from testing a conventional backend service?
    国内高频海外高频进阶#evaluation#testing#agent-quality

    🔒 解锁 D21 后查看答题要点。

  • 用大模型给大模型的输出打分(LLM-as-judge),有哪些不可靠的地方?怎么办?What makes LLM-as-judge unreliable, and what do you do about it?
    国内高频海外高频深入#evaluation#llm-as-judge#reliability

    🔒 解锁 D21 后查看答题要点。

  • 多 Agent 系统的可观测性要看哪些东西?和单 Agent 有什么不一样?What does observability look like for a multi-agent system, and how does it differ from a single agent?
    国内高频海外高频进阶#observability#tracing#distributed-systems

    🔒 解锁 D21 后查看答题要点。

  • 什么时候该用 LangGraph 这类编排框架,什么时候不该用?When should you reach for an orchestration framework like LangGraph, and when should you not?
    国内高频海外高频进阶#architecture#framework-selection#langgraph

    🔒 解锁 D21 后查看答题要点。

  • 系统设计:一个多 Agent 客服平台已经上线,团队每周改几次提示词,但没人说得清质量是变好还是变差,成本也只有一个月底的总数。请为它设计一套评估与可观测体系。System design: a multi-agent support platform is live, the team edits prompts several times a week, nobody can say whether quality is improving, and cost is only known as a month-end total. Design its evaluation and observability system.
    国内高频海外高频深入#system-design#evaluation#observability#cost

    🔒 解锁 D21 后查看答题要点。

D22 安全:prompt injection、工具最小权限、沙箱思路、密钥管理

  • 什么是 prompt injection?直接注入和间接注入有什么区别,为什么它不像 SQL 注入那样能被彻底修复?What is prompt injection? How do direct and indirect injection differ, and why can't it be fixed the way SQL injection was?
    国内高频海外高频基础#prompt-injection#security#agent-design

    🔒 解锁 D22 后查看答题要点。

  • 你们怎么防 prompt injection?如果我说「加个正则过滤掉危险关键词就行了」,你会怎么反驳我?How do you defend against prompt injection? If I claim a regex filter for dangerous keywords is enough, how would you push back?
    国内高频海外高频深入#prompt-injection#least-privilege#tool-permissions

    🔒 解锁 D22 后查看答题要点。

  • Agent 要执行不受信任的代码或命令时,有哪些沙箱隔离思路?你们选了哪一档,为什么?When an agent has to run untrusted code or commands, what sandboxing options do you have? Which tier would you pick and why?
    国内高频海外高频进阶#sandboxing#security#tool-execution

    🔒 解锁 D22 后查看答题要点。

  • Agent 系统里的密钥应该怎么管理?它绝对不能出现在哪些地方,轮换要怎么做才能不停机?How should secrets be managed in an agent system? Where must they never appear, and how do you rotate them without downtime?
    国内高频海外高频进阶#secrets-management#security#observability

    🔒 解锁 D22 后查看答题要点。

D23 MCP 与 Skills:协议、server/client、与 function calling 区别;Claude Agent SDK 一览

  • MCP 协议解决了什么问题?它和 function calling 有什么区别?What problem does MCP solve, and how is it different from function calling?
    国内高频海外高频基础#mcp#tool-calling#protocol

    🔒 解锁 D23 后查看答题要点。

  • MCP 里 server 和 client 分别承担什么角色?server 能暴露哪几类东西,传输方式有哪些?What roles do the MCP server and client play, what can a server expose, and which transports exist?
    国内高频海外高频进阶#mcp#protocol#transport

    🔒 解锁 D23 后查看答题要点。

  • 什么场景下应该考虑用 MCP,而不是直接写 function calling?不该用的时候硬上会付出什么代价?When should you reach for MCP instead of plain function calling, and what does it cost when you shouldn't?
    国内高频海外高频进阶#mcp#architecture#trade-offs

    🔒 解锁 D23 后查看答题要点。

  • 你要把一个第三方维护的 MCP server 接进生产环境,会担心什么、做哪些检查?You are about to attach a third-party MCP server in production. What worries you, and what do you check?
    国内高频海外高频深入#mcp#security#operations

    🔒 解锁 D23 后查看答题要点。

D24 RAG 进阶:hybrid search、rerank、引用、recall 评估

  • 为什么单纯的向量检索不够,还要加一路关键词检索?Why isn't pure vector search enough — what does keyword search add?
    国内高频海外高频基础#rag#hybrid-search#retrieval

    🔒 解锁 D24 后查看答题要点。

  • 两路检索结果怎么合并?为什么不能直接加权求和?How do you merge two retrieval rankings, and why not just take a weighted sum of the scores?
    国内高频海外高频进阶#rag#rrf#ranking

    🔒 解锁 D24 后查看答题要点。

  • 重排(rerank)一般怎么实现?它解决了初步检索的什么问题,代价是什么?How is reranking usually implemented, what problem does it solve, and what does it cost?
    国内高频海外高频进阶#rag#rerank#latency

    🔒 解锁 D24 后查看答题要点。

  • 怎么评估一个 RAG 系统的检索效果?评估集应该怎么构造?How do you evaluate retrieval quality in a RAG system, and how should the evaluation set be built?
    国内高频海外高频深入#rag#evaluation#recall

    🔒 解锁 D24 后查看答题要点。

D25 前端侧 Agent 体验:流式渲染、工具调用可视化、打断/重试、SSE hooks

  • 前端怎么消费 SSE 并实现打字机效果?为什么一般不用浏览器自带的 EventSource?How does a frontend consume SSE to render a typewriter effect, and why do people usually avoid the built-in EventSource?
    国内高频海外高频基础#sse#streaming#frontend

    🔒 解锁 D25 后查看答题要点。

  • 用户点了「停止生成」,前端调用 AbortController.abort() 之后,后端在做什么?The user hits Stop and the frontend calls AbortController.abort(). What is the backend doing at that moment?
    国内高频海外高频深入#streaming#cancellation#cost

    🔒 解锁 D25 后查看答题要点。

  • 流式场景下前端的状态管理要注意什么?为什么不能每个 token 都 setState?What is different about frontend state management under streaming, and why not call setState on every token?
    国内高频海外高频进阶#react#streaming#performance

    🔒 解锁 D25 后查看答题要点。

  • 失败重试怎么设计才不会产生重复副作用?工具调用过程要不要暴露给用户?How do you design retry so it does not duplicate side effects, and should the tool-call process be visible to the user?
    国内高频海外高频进阶#idempotency#retry#ux

    🔒 解锁 D25 后查看答题要点。

D26 系统设计专题:Agent 平台 / 客服 Agent / 多租户 / 成本控制

  • 系统设计环节只有 35 到 40 分钟,你会怎么分配时间?为什么第一步不是画架构图?You get 35 to 40 minutes for a system design round. How do you budget that time, and why is drawing the architecture not step one?
    国内高频海外高频基础#system-design#interview-process

    🔒 解锁 D26 后查看答题要点。

  • 系统设计:请设计一个电商客服 Agent。它要能查订单和物流、按规则拟退款方案、回答商品与政策问题,并在搞不定时转人工。System design: design an e-commerce customer support agent. It looks up orders and shipments, drafts refunds by policy, answers product and policy questions, and escalates to a human when it cannot resolve the issue.
    国内高频海外高频深入#system-design#customer-support#escalation

    🔒 解锁 D26 后查看答题要点。

  • 一个多租户的 Agent 服务,数据隔离和计费隔离要怎么设计?什么时候该从共享表升级到独立库?For a multi-tenant agent service, how do you design data isolation and billing isolation, and when do you move from a shared table to a dedicated database per tenant?
    国内高频海外高频进阶#system-design#multi-tenancy#isolation

    🔒 解锁 D26 后查看答题要点。

  • 一个 Agent 系统的模型成本失控了,你会从哪几个层面着手控制?每一层大概能省多少?An agent system's model spend is out of control. Which levers do you pull, in what order, and roughly how much does each save?
    国内高频海外高频进阶#system-design#cost#capacity-planning

    🔒 解锁 D26 后查看答题要点。

D27 简历与项目包装:STAR、README、架构图、demo 视频、英文简历

  • 请用 STAR 法则讲一个你做过的技术项目。Walk me through a technical project of yours using the STAR framework.
    国内高频海外高频基础#behavioral#star#resume

    🔒 解锁 D27 后查看答题要点。

  • 讲讲你做过的最有挑战的一个项目,难在哪里?Tell me about the most challenging project you have worked on. What made it hard?
    国内高频海外高频深入#behavioral#project-storytelling

    🔒 解锁 D27 后查看答题要点。

  • 我们点开了你 GitHub 上的项目,你觉得一份好的 README 应该让我看到什么?Suppose I open one of your GitHub projects — what should a good README show me?
    国内高频海外高频进阶#behavioral#documentation#portfolio

    🔒 解锁 D27 后查看答题要点。

  • 你投过海外岗位吗?英文简历和中文简历在写法上有什么不同?Have you applied overseas? How does an English tech resume differ from a Chinese one?
    国内高频海外高频基础#behavioral#resume#global-market

    🔒 解锁 D27 后查看答题要点。

D28 模拟面试日:国内/海外各一套全流程,自评

  • 国内和海外技术面试的流程差异主要在哪里?你会怎么分别准备?How do domestic Chinese and overseas tech interview loops differ structurally, and how would you prepare for each?
    国内高频海外高频基础#interview-process#career

    🔒 解锁 D28 后查看答题要点。

  • 自我介绍环节最容易出的问题是什么?一段好的自我介绍应该长什么样?What most commonly goes wrong in the self-introduction, and what does a good one look like?
    国内高频海外高频进阶#self-presentation#communication

    🔒 解锁 D28 后查看答题要点。

  • 一次模拟面试之后,你怎么做一次客观的自我评估,而不是停在「感觉还行」?After a mock interview, how do you assess yourself objectively instead of settling for 'that felt okay'?
    国内高频海外高频进阶#self-assessment#deliberate-practice

    🔒 解锁 D28 后查看答题要点。

D29 弱项补强 + 编码热身:rate limiter、LRU、并发控制、流式 JSON 解析

  • 限流器有哪几种常见算法?各自的优缺点是什么?如果只能落地一种,你选哪个?What are the common rate limiting algorithms, what are their trade-offs, and which one would you actually ship?
    国内高频海外高频基础#rate-limiting#concurrency

    🔒 解锁 D29 后查看答题要点。

  • 怎么实现一个限制并发数的调度器?为什么不能直接用 Promise.all 或者 asyncio.gather?How would you build a scheduler that caps in-flight async tasks, and why is Promise.all or asyncio.gather not enough?
    国内高频海外高频进阶#concurrency#async

    🔒 解锁 D29 后查看答题要点。

  • 为什么流式场景下不能直接用 JSON.parse?你会怎么做增量解析?Why can't you just call JSON.parse in a streaming response, and how would you parse incrementally?
    国内高频海外高频深入#streaming#json-parsing

    🔒 解锁 D29 后查看答题要点。

D30 总复盘 + 投递启动:题库全量过一遍、知识地图、第二个月投递节奏、网站公开上线

  • 如果只剩最后一周准备面试,你会怎么安排复盘节奏?With only one week left before your interviews, how would you plan your review?
    国内高频海外高频基础#interview-prep#prioritization

    🔒 解锁 D30 后查看答题要点。

  • 怎么把零散的知识点组织成一张便于复习的知识地图?How do you turn scattered knowledge into a map that is actually useful for review?
    国内高频海外高频进阶#knowledge-organization#interview-prep

    🔒 解锁 D30 后查看答题要点。

  • 用 3 到 5 分钟讲一下你最近这段时间的成长路径,以及为什么转向 Agent 工程。Walk me through what you have been working on recently and why you moved toward agent engineering, in three to five minutes.
    国内高频海外高频深入#self-introduction#storytelling

    🔒 解锁 D30 后查看答题要点。