Back to Details

llm-council

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

LLM Council

LLM Council

You ask one AI a question, you get one answer. That answer might be great. It might be mid. You have no way to tell because you only saw one perspective.
The council fixes this. It runs your question through 5 independent advisors, each thinking from a fundamentally different angle. Then they review each other's work. Then a chairman synthesizes everything into a final recommendation that tells you where the advisors agree, where they clash, and what you should actually do.
This is adapted from Andrej Karpathy's LLM Council. He dispatches queries to multiple models, has them peer-review each other anonymously, then a chairman produces the final answer. We do the same thing inside Claude using sub-agents with different thinking lenses instead of different models.
你向一个AI提问，只会得到一个答案。这个答案可能很棒，也可能表现一般，你无从判断好坏，因为你只看到了一个视角。
委员会机制解决了这个问题：它会将你的问题提交给5名独立顾问，每名顾问都会从完全不同的角度思考问题，之后他们会互相评审彼此的输出，最后由主席将所有内容综合为最终建议，告诉你顾问们的共识点、分歧点，以及你实际应该怎么做。
本方案改编自Andrej Karpathy的LLM Council方法论：他会将查询发送给多个模型，让它们匿名互相评审，再由主席输出最终答案。我们在Claude内部实现了相同的逻辑，只不过使用持有不同思考视角的sub-agent而非不同模型来实现。

when to run the council

何时运行委员会

The council is for questions where being wrong is expensive.
Good council questions:
  • "Should I launch a $97 workshop or a $497 course?"
  • "Which of these 3 positioning angles is strongest?"
  • "I'm thinking of pivoting from X to Y. Am I crazy?"
  • "Here's my landing page copy. What's weak?"
  • "Should I hire a VA or build an automation first?"
Bad council questions:
  • "What's the capital of France?" (one right answer, no need for perspectives)
  • "Write me a tweet" (creation task, not a decision)
  • "Summarize this article" (processing task, not judgment)
The council shines when there's genuine uncertainty and the cost of a bad call is high. If you already know the answer and just want validation, the council will likely tell you things you don't want to hear. That's the point.
委员会适用于出错代价高昂的问题。
适合提交给委员会的问题：
  • "我应该推出97美元的工作坊还是497美元的课程？"
  • "这3个定位角度中哪个最有竞争力？"
  • "我在考虑从X方向转向Y方向，这个想法是不是太疯狂了？"
  • "这是我的落地页文案，有什么薄弱的地方？"
  • "我应该先招聘虚拟助理还是先搭建自动化流程？"
不适合提交给委员会的问题：
  • "法国的首都是什么？"（只有一个正确答案，不需要多视角）
  • "帮我写一条推文"（创作任务，不是决策类问题）
  • "总结这篇文章"（处理任务，不需要判断）
委员会的价值在存在真实不确定性、错误决策成本高的场景下最突出。如果你已经知道答案只是想要验证，委员会大概率会告诉你一些你不想听的内容，这正是它的意义所在。

the five advisors

五名顾问介绍

Each advisor thinks from a different angle. They're not job titles or personas. They're thinking styles that naturally create tension with each other.
每名顾问都从不同角度思考，他们不是职位或人设，而是天然会产生冲突的思考风格。

1. The Contrarian

1. 唱反调者（The Contrarian）

Actively looks for what's wrong, what's missing, what will fail. Assumes the idea has a fatal flaw and tries to find it. If everything looks solid, digs deeper. The Contrarian is not a pessimist. They're the friend who saves you from a bad deal by asking the questions you're avoiding.
主动寻找问题、缺失点、可能失败的环节，默认想法存在致命缺陷并努力找出漏洞，如果一切看起来都没问题就会挖得更深。唱反调者不是悲观主义者，他们是那种会问出你一直在回避的问题、帮你避开糟糕交易的朋友。

2. The First Principles Thinker

2. 第一性原理思考者（The First Principles Thinker）

Ignores the surface-level question and asks "what are we actually trying to solve here?" Strips away assumptions. Rebuilds the problem from the ground up. Sometimes the most valuable council output is the First Principles Thinker saying "you're asking the wrong question entirely."
忽略表面问题，追问“我们真正要解决的问题是什么？”，剥离所有假设，从零开始重构问题。有时候委员会最有价值的输出就是第一性原理思考者告诉你“你问的问题从根本上就错了”。

3. The Expansionist

3. 扩张主义者（The Expansionist）

Looks for upside everyone else is missing. What could be bigger? What adjacent opportunity is hiding? What's being undervalued? The Expansionist doesn't care about risk (that's the Contrarian's job). They care about what happens if this works even better than expected.
寻找所有人都忽略的上行空间：什么可以做得更大？隐藏的相邻机会是什么？什么被低估了？扩张主义者不关心风险（那是唱反调者的工作），他们关心的是如果效果远超预期能带来什么收益。

4. The Outsider

4. 局外人（The Outsider）

Has zero context about you, your field, or your history. Responds purely to what's in front of them. This is the most underrated advisor. Experts develop blind spots. The Outsider catches the curse of knowledge: things that are obvious to you but confusing to everyone else.
对你、你的领域、你的过往经历完全不了解，只基于眼前的内容给出反馈。这是最被低估的顾问：专家会有盲点，局外人能发现知识的诅咒——那些对你来说显而易见，但对其他人来说非常困惑的内容。

5. The Executor

5. 执行者（The Executor）

Only cares about one thing: can this actually be done, and what's the fastest path to doing it? Ignores theory, strategy, and big-picture thinking. The Executor looks at every idea through the lens of "OK but what do you do Monday morning?" If an idea sounds brilliant but has no clear first step, the Executor will say so.
Why these five: They create three natural tensions. Contrarian vs Expansionist (downside vs upside). First Principles vs Executor (rethink everything vs just do it). The Outsider sits in the middle keeping everyone honest by seeing what fresh eyes see.
只关心一件事：这件事到底能不能落地，最快的落地路径是什么？忽略理论、战略和宏观思考，执行者看待所有想法的视角都是“好的，但你周一早上要做什么？”如果一个想法听起来很绝妙但没有清晰的第一步，执行者会直接指出来。
为什么选这五个角色： 他们天然形成三组张力：唱反调者vs扩张主义者（下行风险vs上行收益）、第一性原理思考者vs执行者（全盘重思vs直接落地），局外人坐在中间，用全新视角观察，保证所有人的输出都足够客观。

how a council session works

委员会会议运行流程

step 1: frame the question (with context enrichment)

步骤1：梳理问题（补充上下文）

When the user says "council this" (or any trigger phrase), do two things before framing:
A. Scan the workspace for context. The user's question is often just the tip of the iceberg. Their Claude setup likely contains files that would dramatically improve the council's output. Before framing, quickly scan for and read any relevant context files:
  • CLAUDE.md
    or 
    claude.md
    in the project root or workspace (business context, preferences, constraints)
  • Any 
    memory/
    folder (audience profiles, voice docs, business details, past decisions)
  • Any files the user explicitly referenced or attached
  • Recent council transcripts in this folder (to avoid re-counciling the same ground)
  • Any other context files that seem relevant to the specific question (e.g., if they're asking about pricing, look for revenue data, past launch results, audience research)
Use 
Glob
and quick 
Read
calls to find these. Don't spend more than 30 seconds on this. You're looking for the 2-3 files that would give advisors the context they need to give specific, grounded advice instead of generic takes.
B. Frame the question. Take the user's raw question AND the enriched context and reframe it as a clear, neutral prompt that all five advisors will receive. The framed question should include:
  1. The core decision or question
  2. Key context from the user's message
  3. Key context from workspace files (business stage, audience, constraints, past results, relevant numbers)
  4. What's at stake (why this decision matters)
Don't add your own opinion. Don't steer it. But DO make sure each advisor has enough context to give a specific, grounded answer rather than generic advice.
If the question is too vague ("council this: my business"), ask one clarifying question. Just one. Then proceed.
Save the framed question for the transcript.
当用户说出“council this”（或任何触发词）时，梳理问题前先做两件事：
A. 扫描工作区获取上下文 用户的问题通常只是冰山一角，他们的Claude设置里很可能有能大幅提升委员会输出质量的文件。梳理问题前，快速扫描并读取所有相关上下文文件：
  • 项目根目录或工作区中的
    CLAUDE.md
    或
    claude.md
    （业务上下文、偏好、约束条件）
  • 任意
    memory/
    文件夹（受众画像、语气文档、业务细节、过往决策）
  • 用户明确引用或附加的所有文件
  • 本文件夹内近期的委员会记录（避免重复讨论相同内容）
  • 其他和具体问题相关的上下文文件（例如如果用户问定价相关问题，查找收入数据、过往上线结果、受众调研）
使用
Glob
和快速
Read
调用查找这些文件，这一步耗时不要超过30秒，你只需要找到2-3个能给顾问提供足够上下文的文件，让他们能给出具体、落地的建议而非泛泛之谈即可。
B. 梳理问题 将用户的原始问题+补充到的上下文重构成清晰、中立的提示词，提供给所有五名顾问。梳理后的问题应该包含：
  1. 核心决策或问题
  2. 用户消息里的关键上下文
  3. 工作区文件里的关键上下文（业务阶段、受众、约束、过往结果、相关数字）
  4. 利害关系（为什么这个决策很重要）
不要添加你自己的观点，不要引导方向，但要确保每个顾问都有足够的上下文给出具体、落地的答案，而不是泛泛的建议。
如果问题太模糊（比如“council this: 我的业务”），只问一个澄清问题，之后继续推进。
将梳理好的问题保存到记录中。

step 2: convene the council (5 sub-agents in parallel)

步骤2：召集委员会（并行运行5个sub-agent）

Spawn all 5 advisors simultaneously as sub-agents. Each gets:
  1. Their advisor identity and thinking style (from the descriptions above)
  2. The framed question
  3. A clear instruction: respond independently. Do not hedge. Do not try to be balanced. Lean fully into your assigned perspective. If you see a fatal flaw, say it. If you see massive upside, say it. Your job is to represent your angle as strongly as possible. The synthesis comes later.
Each advisor should produce a response of 150-300 words. Long enough to be substantive, short enough to be scannable.
Sub-agent prompt template:

You are [Advisor Name] on an LLM Council.


Your thinking style: [advisor description from above]


A user has brought this question to the council:


---

[framed question]

---


Respond from your perspective. Be direct and specific. Don't hedge or try to be balanced. Lean fully into your assigned angle. The other advisors will cover the angles you're not covering.


Keep your response between 150-300 words. No preamble. Go straight into your analysis.
同时生成全部5名顾问作为sub-agent，每个顾问都会收到：
  1. 他们的顾问身份和思考风格（来自上面的描述）
  2. 梳理好的问题
  3. 清晰的指令：独立回应，不要模棱两可，不要试图保持平衡，完全站在你分配到的视角输出。如果你看到致命缺陷就直接说，如果你看到巨大的上行空间也直接说，你的工作是尽可能有力地代表你的角度，后续会做综合。
每个顾问的回复长度控制在150-300词，足够有实质内容，同时足够简短方便浏览。
Sub-agent提示词模板：

You are [Advisor Name] on an LLM Council.


Your thinking style: [advisor description from above]


A user has brought this question to the council:


---

[framed question]

---


Respond from your perspective. Be direct and specific. Don't hedge or try to be balanced. Lean fully into your assigned angle. The other advisors will cover the angles you're not covering.


Keep your response between 150-300 words. No preamble. Go straight into your analysis.

step 3: peer review (5 sub-agents in parallel)

步骤3：同行评审（并行运行5个sub-agent）

This is the step that makes the council more than just "ask 5 times." It's the core of Karpathy's insight.
Collect all 5 advisor responses. Anonymize them as Response A through E (randomize which advisor maps to which letter so there's no positional bias).
Spawn 5 new sub-agents, one for each advisor. Each reviewer sees all 5 anonymized responses and answers three questions:
  1. Which response is the strongest and why? (pick one)
  2. Which response has the biggest blind spot and what is it?
  3. What did ALL responses miss that the council should consider?
Reviewer prompt template:

You are reviewing the outputs of an LLM Council. Five advisors independently answered this question:


---

[framed question]

---


Here are their anonymized responses:


**Response A:**

[response]


**Response B:**

[response]


**Response C:**

[response]


**Response D:**

[response]


**Response E:**

[response]


Answer these three questions. Be specific. Reference responses by letter.


1. Which response is the strongest? Why?

2. Which response has the biggest blind spot? What is it missing?

3. What did ALL five responses miss that the council should consider?


Keep your review under 200 words. Be direct.
这一步让委员会不再是“问5次AI”，是Karpathy核心洞见的体现。
收集所有5名顾问的回复，匿名化为回复A到E（随机打乱顾问和字母的映射，避免位置偏见）。
生成5个新的sub-agent，每个对应一名顾问。每个评审者会看到所有5个匿名回复，回答三个问题：
  1. 哪个回复最有力？为什么？（选一个）
  2. 哪个回复的盲点最大？缺失了什么内容？
  3. 所有回复都漏掉了什么委员会应该考虑的内容？
评审者提示词模板：

You are reviewing the outputs of an LLM Council. Five advisors independently answered this question:


---

[framed question]

---


Here are their anonymized responses:


**Response A:**

[response]


**Response B:**

[response]


**Response C:**

[response]


**Response D:**

[response]


**Response E:**

[response]


Answer these three questions. Be specific. Reference responses by letter.


1. Which response is the strongest? Why?

2. Which response has the biggest blind spot? What is it missing?

3. What did ALL five responses miss that the council should consider?


Keep your review under 200 words. Be direct.

step 4: chairman synthesis

步骤4：主席综合

This is the final step. One agent gets everything: the original question, all 5 advisor responses (now de-anonymized so you can see which advisor said what), and all 5 peer reviews.
The chairman's job is to produce the final council output. It follows this structure:
COUNCIL VERDICT
  1. Where the council agrees — the points that multiple advisors converged on independently. These are high-confidence signals.
  2. Where the council clashes — the genuine disagreements. Don't smooth these over. Present both sides and explain why reasonable advisors disagree.
  3. Blind spots the council caught — things that only emerged through the peer review round. Things individual advisors missed that other advisors flagged.
  4. The recommendation — a clear, actionable recommendation. Not "it depends." Not "consider both sides." A real answer. The chairman can disagree with the majority if the reasoning supports it.
  5. The one thing you should do first — a single concrete next step. Not a list of 10 things. One thing.
Chairman prompt template:

You are the Chairman of an LLM Council. Your job is to synthesize the work of 5 advisors and their peer reviews into a final verdict.


The question brought to the council:

---

[framed question]

---


ADVISOR RESPONSES:


**The Contrarian:**

[response]


**The First Principles Thinker:**

[response]


**The Expansionist:**

[response]


**The Outsider:**

[response]


**The Executor:**

[response]


PEER REVIEWS:

[all 5 peer reviews]


Produce the council verdict using this exact structure:
这是最后一步，一个代理会收到所有内容：原始问题、所有5名顾问的回复（现在解除匿名，你可以看到哪个内容是哪个顾问说的）、所有5份同行评审结果。
主席的工作是输出最终的委员会结论，遵循以下结构：
委员会结论
  1. 委员会共识 — 多名顾问独立达成一致的观点，这些是高置信度信号。
  2. 委员会分歧 — 真实的意见冲突，不要抹平这些分歧，展示双方的观点，解释为什么理性的顾问会产生分歧。
  3. 委员会发现的盲点 — 只有在同行评审环节才浮现的问题，单个顾问漏掉但其他顾问指出的内容。
  4. 建议 — 清晰、可落地的建议，不要说“看情况”，不要说“考虑双方观点”，给出真实的答案，如果推理支持的话主席可以不同意多数人的观点。
  5. 你首先要做的一件事 — 单一的具体下一步，不要列10件事，只给一件。
主席提示词模板：

You are the Chairman of an LLM Council. Your job is to synthesize the work of 5 advisors and their peer reviews into a final verdict.


The question brought to the council:

---

[framed question]

---


ADVISOR RESPONSES:


**The Contrarian:**

[response]


**The First Principles Thinker:**

[response]


**The Expansionist:**

[response]


**The Outsider:**

[response]


**The Executor:**

[response]


PEER REVIEWS:

[all 5 peer reviews]


Produce the council verdict using this exact structure:

Where the Council Agrees

Where the Council Agrees

[Points multiple advisors converged on independently. These are high-confidence signals.]
[Points multiple advisors converged on independently. These are high-confidence signals.]

Where the Council Clashes

Where the Council Clashes

[Genuine disagreements. Present both sides. Explain why reasonable advisors disagree.]
[Genuine disagreements. Present both sides. Explain why reasonable advisors disagree.]

Blind Spots the Council Caught

Blind Spots the Council Caught

[Things that only emerged through peer review. Things individual advisors missed that others flagged.]
[Things that only emerged through peer review. Things individual advisors missed that others flagged.]

The Recommendation

The Recommendation

[A clear, direct recommendation. Not "it depends." A real answer with reasoning.]
[A clear, direct recommendation. Not "it depends." A real answer with reasoning.]

The One Thing to Do First

The One Thing to Do First

[A single concrete next step. Not a list. One thing.]
Be direct. Don't hedge. The whole point of the council is to give the user clarity they couldn't get from a single perspective.
undefined
[A single concrete next step. Not a list. One thing.]
Be direct. Don't hedge. The whole point of the council is to give the user clarity they couldn't get from a single perspective.
undefined

step 5: generate the council report

步骤5：生成委员会报告

After the chairman synthesis is complete, generate a visual HTML report and save it to the user's workspace.
File: 
council-report-[timestamp].html
The report should be a single self-contained HTML file with inline CSS. Clean design, easy to scan. It should contain:
  1. The question at the top
  2. The chairman's verdict prominently displayed (this is what most people will read)
  3. An agreement/disagreement visual — a simple visual showing which advisors aligned and which diverged. This could be a grid, a spectrum, or a simple breakdown showing advisor positions. Keep it clean and scannable.
  4. Collapsible sections for each advisor's full response (collapsed by default so the page isn't overwhelming, but available if the user wants to dig in)
  5. Collapsible section for the peer review highlights
  6. A footer showing the timestamp and what was counciled
Use clean styling: white background, subtle borders, readable sans-serif font (system font stack), soft accent colors to distinguish advisor sections. Nothing flashy. It should look like a professional briefing document.
Open the HTML file after generating it so the user can see it immediately.
主席综合完成后，生成可视化HTML报告并保存到用户的工作区。
文件： 
council-report-[timestamp].html
报告应该是单一的自包含HTML文件，使用内联CSS，设计简洁、便于浏览，应该包含：
  1. 顶部展示问题
  2. 突出展示主席的结论（这是大多数人会阅读的内容）
  3. 共识/分歧可视化 — 简单的可视化展示哪些顾问意见一致、哪些有分歧，可以是网格、频谱图或者简单的顾问立场拆分，保持简洁便于浏览。
  4. 每个顾问完整回复的折叠区块（默认折叠，避免页面内容过多，如果用户想深入了解可以展开查看）
  5. 同行评审亮点的折叠区块
  6. 页脚展示时间戳和本次委员会讨论的内容
使用简洁的样式：白色背景、细边框、易读的无衬线字体（系统字体栈）、柔和的强调色区分不同顾问的区块，不要花哨的设计，看起来应该像专业的简报文档。
生成后自动打开HTML文件，让用户可以立即查看。

step 6: save the full transcript

步骤6：保存完整记录

Save the complete council transcript as 
council-transcript-[timestamp].md
in the same location. This includes:
  • The original question
  • The framed question
  • All 5 advisor responses
  • All 5 peer reviews (with anonymization mapping revealed)
  • The chairman's full synthesis
This transcript is the artifact. If the user wants to run the council again on the same question after making changes, having the previous transcript lets them (or a future agent) see how the thinking evolved.
将完整的委员会记录保存为
council-transcript-[timestamp].md
，存在相同位置，包含：
  • 原始问题
  • 梳理后的问题
  • 所有5名顾问的回复
  • 所有5份同行评审（展示匿名映射关系）
  • 主席的完整综合内容
这份记录是存档文件，如果用户修改内容后想就同一个问题再次运行委员会，过往记录可以让他们（或未来的代理）看到思考过程的演变。

output format

输出格式

Every council session produces two files:

council-report-[timestamp].html    # visual report for scanning

council-transcript-[timestamp].md  # full transcript for reference
The user sees the HTML report. The transcript is there if they want to dig deeper or reference specific advisor arguments later.
每次委员会会议生成两个文件：

council-report-[timestamp].html    # 可视化报告，用于快速浏览

council-transcript-[timestamp].md  # 完整记录，用于参考
用户会看到HTML报告，如果他们想深入了解或者后续参考特定顾问的论点，可以查看记录。

example: counciling a product decision

示例：产品决策评审

User: "Council this: I'm thinking of building a $297 course on Claude Code for beginners. My audience is mostly non-technical solopreneurs. Is this the right move?"
The Contrarian: "The market is flooded with Claude courses right now. At $297, you're competing with free YouTube content. Your audience is non-technical, which means high support burden and refund risk. The people who would pay $297 are likely already past beginner level..."
The First Principles Thinker: "What are you actually trying to achieve? If it's revenue, a course is one of the slowest paths. If it's authority, a free resource might do more. If it's building a customer base for higher-ticket offers, the price point and audience might be mismatched..."
The Expansionist: "Beginner Claude for solopreneurs is a massive underserved market. Everyone's teaching advanced stuff. If you nail the beginner angle, you own the entry point to this entire space. The $297 might be low. What if this became a $997 program with community access..."
The Outsider: "I don't know what Claude Code is. If I saw '$297 course on Claude Code for beginners,' I wouldn't know if this is for me. The name means nothing to someone outside your world. Your landing page needs to sell the outcome, not the tool..."
The Executor: "A full course takes 4-8 weeks to produce properly. Before building anything, run a live workshop at $97 to 50 people. You validate demand, generate testimonials, and create the raw material for the course. If 50 people don't buy the workshop, 500 won't buy the course..."
Chairman's Verdict:
Where the council agrees: The beginner solopreneur angle has real demand, but the current framing (Claude Code course) is too tool-specific and won't resonate with non-technical buyers.
Where the council clashes: Price. The Contrarian says $297 is too high given competition. The Expansionist says it's too low for the value. The resolution likely depends on how much support and community access is bundled.
Blind spots caught: The Outsider's point that "Claude Code" means nothing to the target buyer is the single most important insight. Every advisor except the Outsider assumed the audience already knows what this is.
Recommendation: Don't build the course yet. Validate with a lower-commitment offer first. But reframe entirely: sell the outcome (automate your business, get 10 hours back per week), not the tool.
One thing to do first: Run a $97 live workshop called "How to automate your first business task with AI" to 50 people. Don't mention Claude Code in the title.
用户： "Council this: 我在考虑做一门面向初学者的297美元的Claude Code课程，我的受众大多是非技术的独立创业者，这个决定对吗？"
唱反调者： "现在Claude相关课程的市场已经饱和了，297美元的定价要和免费的YouTube内容竞争，你的受众是非技术人群，意味着更高的支持负担和退款风险，愿意付297美元的人大概率已经过了初学者阶段..."
第一性原理思考者： "你真正想要达成的目标是什么？如果是赚收入，课程是最慢的路径之一；如果是打造权威，免费资源的效果可能更好；如果是为高客单价产品积累客户群，定价和受众可能不匹配..."
扩张主义者： 面向独立创业者的Claude入门内容是一个巨大的未被满足的市场，所有人都在教高级内容，如果你把入门角度做透，你就占领了整个领域的入口，297美元可能定价太低了，如果做成997美元的带社群的项目会怎么样..."
局外人： "我不知道Claude Code是什么，如果我看到'297美元的Claude Code初学者课程'，我不知道这个是不是适合我，这个名字对你圈子外的人来说没有任何意义，你的落地页应该卖结果，而不是卖工具..."
执行者： "一门完整的课程要花4-8周才能做好，在做任何内容之前，先开一个97美元的直播工作坊，招50个人，你可以验证需求、生成 testimonials，还能产出课程的原始素材，如果50个人都不愿意买工作坊，就不会有500个人买课程..."
主席结论：
委员会共识： 面向独立创业者的入门角度确实有真实需求，但当前的定位（Claude Code课程）太偏向工具，无法打动非技术买家。
委员会分歧： 定价问题。唱反调者认为考虑到竞争情况，297美元定价太高；扩张主义者认为相对于价值来说定价太低，最终的定价取决于捆绑的支持和社群权益多少。
发现的盲点： 局外人提出的“Claude Code”对目标买家没有任何意义是最重要的洞见，除了局外人之外的所有顾问都默认受众已经知道这个是什么。
建议： 暂时不要做课程，先用更低投入的产品验证需求，同时完全重构定位：卖结果（自动化你的业务，每周省10小时），而不是卖工具。
首先要做的一件事： 开一个97美元的直播工作坊，标题是“如何用AI自动化你的第一个业务任务”，招50个人，标题里不要提Claude Code。

important notes

重要注意事项

  • Always spawn all 5 advisors in parallel. Sequential spawning wastes time and lets earlier responses bleed into later ones.
  • Always anonymize for peer review. If reviewers know which advisor said what, they'll defer to certain thinking styles instead of evaluating on merit.
  • The chairman can disagree with the majority. If 4 out of 5 advisors say "do it" but the reasoning of the 1 dissenter is strongest, the chairman should side with the dissenter and explain why.
  • Don't council trivial questions. If the user asks something with one right answer, just answer it. The council is for genuine uncertainty where multiple perspectives add value.
  • The visual report matters. Most users will scan the report, not read the full transcript. Make the HTML output clean and scannable.
  • 始终并行生成所有5名顾问 顺序生成会浪费时间，还会让前面的回复影响后面的输出。
  • 同行评审环节始终匿名 如果评审者知道哪个回复是哪个顾问做的，他们会偏向特定的思考风格，而不是基于内容本身评估。
  • 主席可以不同意多数意见 如果5个顾问里4个说“可以做”，但剩下1个反对者的推理更有力，主席应该站在反对者一边并解释原因。
  • 不要评审 trivial 的问题 如果用户问的问题只有一个正确答案，直接回答即可，委员会适用于存在真实不确定性、多视角能带来价值的场景。
  • 可视化报告很重要 大多数用户只会浏览报告，不会读完整的记录，确保HTML输出简洁便于浏览。