context-course/pr_2/en/_app/immutable/nodes/28.92e486bb.js

import{s as G,n as I,o as R}from"../chunks/scheduler.b8c17244.js";import{S as D,i as H,e as U,s as n,c as i,h as J,a as N,d as a,b as r,f as j,g as l,j as K,k as B,l as V,m as s,n as u,t as m,o as p,p as c}from"../chunks/index.d374165a.js";import{C as X,H as Y,E as Z}from"../chunks/MermaidChart.svelte_svelte_type_style_lang.200f62db.js";import{Q as v}from"../chunks/Question.b45f7d7c.js";function ee(Q){let o,_,C,S,d,T,f,q,g,W="Test your ability to design and implement multi-agent workflows.",M,x,P,h,z,b,F,$,A,w,E,y,L,k,O;return d=new X({props:{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"}}),f=new Y({props:{title:"Quiz 2: Multi-Agent Workflows",local:"quiz-2-multi-agent-workflows",headingTag:"h1"}}),x=new v({props:{choices:[{text:"Always spawn as many subagents as possible for maximum parallelism",explain:"More subagents means more token usage, latency, and coordination overhead. Use subagents selectively."},{text:"Use subagents when tasks are independent and parallelizable, and the overhead is justified by the task complexity",explain:"Correct! Subagent workflows consume more tokens than single-agent runs. Only use them when the parallelism benefit outweighs the overhead.",correct:!0},{text:"Subagents are only for research tasks; never use for implementation",explain:"False. Worker subagents can implement fixes, write code, and make changes. Codex even has a built-in 'worker' agent type for this."},{text:"Subagents should always share the same context window as the parent",explain:"Subagents run as isolated instances with their own context. They communicate results back to the parent, not share context directly."}]}}),h=new v({props:{choices:[{text:"Subagents can directly access the parent agent's memory and variables",explain:"False. Subagents are isolated. They receive context from the parent via their task description and report results back."},{text:"Pass small context in the task description; for large data, write to a file and reference the path",explain:"Correct! Subagents can't access parent memory. Use task descriptions for small context and files for larger data.",correct:!0},{text:"Use global variables that all subagents can read",explain:"Subagents are separate instances. Global variables don't cross agent boundaries."},{text:"There's no way to share data between parent and subagent",explain:"False. The parent passes context in the task description, and subagents report results back. File system can also be used."}]}}),b=new v({props:{choices:[{text:"If a subagent fails, the entire workflow always fails",explain:"Not necessarily. Good design handles failures gracefully — retry, skip, or use partial results."},{text:"Design for failure: use timeouts, handle partial results, and have fallback strategies",explain:"Correct! Subagents can timeout, produce errors, or return unexpected results. Robust workflows handle these cases.",correct:!0},{text:"Assume all subagents will succeed; don't add error handling since it's just overhead",explain:"Risky. Network issues, token limits, and unexpected errors are common in multi-agent workflows."},{text:"If a subagent fails, immediately spawn 5 more to retry the same task",explain:"Wasteful. Diagnose the failure first, then retry selectively. Brute-force retries waste tokens."}]}}),$=new v({props:{choices:[{text:"Claude Code: use /agent spawn. Codex: use codex-agent spawn. They're identical.",explain:"Neither command exists. Claude Code uses conversational invocation; Codex uses natural language requests to spawn agents."},{text:"Claude Code: conversational invocation + custom agents in .claude/agents/. Codex: natural language requests + custom agents as TOML files in .codex/agents/.",explain:"Correct! Both platforms use natural language to trigger subagent creation, but configure custom agents differently — Claude Code with markdown files, Codex with TOML files.",correct:!0},{text:"Claude Code doesn't support subagents. Only Codex does.",explain:"False. Claude Code has robust subagent support via the Agent tool, conversational invocation, and custom agents."},{text:"Both platforms use the exact same subagent API and configuration format",explain:"No. Claude Code uses markdown-based agent definitions; Codex uses TOML. The invocation style is conversational for both but with different capabilities."}]}}),w=new v({props:{choices:[{text:"Codex has three built-in agent types: default (general), worker (implementation), and explorer (read-heavy codebase exploration)",explain:"Correct! These three built-in types cover the most common subagent use cases without requiring custom agent definitions.",correct:!0},{text:"Codex has no built-in agent types; you must always define custom agents",explain:"False. Codex ships with default, worker, and explorer agents that can be used immediately."},{text:"Codex only supports one agent at a time; there's no parallelism",explain:"False. Codex supports up to max_threads (default 6) concurrent agent threads."},{text:"Codex subagents require a separate codex-agent binary to manage",explain:"False. Subagents are managed through Codex itself — use /agent to switch between threads, or ask Codex in natural language."}]}}),y=new Z({props:{source:"https://github.com/huggingface/context-course/blob/main/units/en/unit4/quiz2.mdx"}}),{c(){o=U("meta"),_=n(),C=U("p"),S=n(),i(d.$$.fragment),T=n(),i(f.$$.fragment),q=n(),g=U("p"),g.textContent=W,M=n(),i(x.$$.fragment),P=n(),i(h.$$.fragment),z=n(),i(b.$$.fragment),F=n(),i($.$$.fragment),A=n(),i(w.$$.fragment),E=n(),i(y.$$.fragment),L=n(),k=U("p"),this.h()},l(e){const t=J("svelte-u9bgzb",document.head);o=N(t,"META",{name:!0,content:!0}),t.forEach(a),_=r(e),C=N(e,"P",{}),j(C).forEach(a),S=r(e),l(d.$$.fragment,e),T=r(e),l(f.$$.fragment,e),q=r(e),g=N(e,"P",{"data-svelte-h":!0}),K(g)!=="svelte-1oercc9"&&(g.textContent=W),M=r(e),l(x.$$.fragment,e),P=r(e),l(h.$$.fragment,e),z=r(e),l(b.$$.fragment,e),F=r(e),l($.$$.fragment,e),A=r(e),l(w.$$.fragment,e),E=r(e),l(y.$$.fragment,e),L=r(e),k=N(e,"P",{}),j(k).forEach(a),this.h()},h(){B(o,"name","hf:doc:metadata"),B(o,"content",te)},m(e,t){V(document.head,o),s(e,_,t),s(e,C,t),s(e,S,t),u(d,e,t),s(e,T,t),u(f,e,t),s(e,q,t),s(e,g,t),s(e,M,t),u(x,e,t),s(e,P,t),u(h,e,t),s(e,z,t),u(b,e,t),s(e,F,t),u($,e,t),s(e,A,t),u(w,e,t),s(e,E,t),u(y,e,t),s(e,L,t),s(e,k,t),O=!0},p:I,i(e){O||(m(d.$$.fragment,e),m(f.$$.fragment,e),m(x.$$.fragment,e),m(h.$$.fragment,e),m(b.$$.fragment,e),m($.$$.fragment,e),m(w.$$.fragment,e),m(y.$$.fragment,e),O=!0)},o(e){p(d.$$.fragment,e),p(f.$$.fragment,e),p(x.$$.fragment,e),p(h.$$.fragment,e),p(b.$$.fragment,e),p($.$$.fragment,e),p(w.$$.fragment,e),p(y.$$.fragment,e),O=!1},d(e){e&&(a(_),a(C),a(S),a(T),a(q),a(g),a(M),a(P),a(z),a(F),a(A),a(E),a(L),a(k)),a(o),c(d,e),c(f,e),c(x,e),c(h,e),c(b,e),c($,e),c(w,e),c(y,e)}}}const te='{"title":"Quiz 2: Multi-Agent Workflows","local":"quiz-2-multi-agent-workflows","sections":[],"depth":1}';function ae(Q){return R(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class ie extends D{constructor(o){super(),H(this,o,ae,ee,G,{})}}export{ie as component};