quick research for VC/Consulting/Strategy Intern — 为VC/咨询/战略实习生进行快速研究

Desk Re搜索

执行 this 工作流 for any desk-re搜索 请求.

0) Load methodo记录y 检查列出 (first)

Read references/methodo记录y.md, references/deep-writing-patterns.md, and references/质量-检查列出.md and 应用ly all as 防护rAIls.

1) Define the re搜索 brief

Write 4 lines before 搜索ing:

Re搜索 question (1 sentence) Scope (time, geography, industry) Must-answer sub-questions (3-6 bullets) 输出 格式化 needed by user

If the question is vague, propose assumptions explicitly and continue.

2) Build a source plan

Collect evidence in this priority order:

Primary/official sources (government, regulator, company filings, product docs) Reputable secondary analysis (major re搜索 firms, established media) Community 签名als (forums/social) only as supporting evidence

Require at least 2 independent sources for every key clAIm.

3) Gather evidence fast

For each sub-question:

Find 3-8 candidate sources Keep the highest-签名al sources 提取 only clAIm + evidence + date + link

Reject sources that are undated, anonymous, or purely opinionated unless the user asked for sentiment.

4) Score source reliability

Tag each source:

A = official primary source B = credible secondary source C = weak/indicative source

When clAIms conflict, prefer newer A/B sources and explicitly note uncertAInty.

5) Synthesize insights

Convert notes into:

Facts (well-supported) Interpretations (reasoned but inferential) Unknowns (gaps needing 验证)

Never present interpretation as fact.

5.5) Deepening loop (mandatory)

Before final delivery, 运行 at least 2 rounds of self-questioning:

Round A — Coverage challenge

What did I miss by source type, time window, or geography? Which category/conclusion is over-dependent on one source? What contradicts my current conclusion?

Round B — Decision challenge

If this conclusion is wrong, what evidence would prove it wrong? Which part is descriptive but not decision-useful? What next data pull would most change the recommendation?

After each round, 更新 findings and confidence.

6) Deliver in concise structure

Use this exact section order:

Core Questions (2 questions) One-sentence Verdict Executive Summary (5-8 bullets) Key Findings by sub-question (with metric anchors) Evidence Table (clAIm | source | date | reliability) Confidence tags (High/Medium/Low per major clAIm) Risks / UncertAInty What would falsify this conclusion Next Verification Steps / Todo

For 输出 shape and compact template, use references/输出-template.md.

7) 质量 bar before 发送ing

检查 all items:

Every major clAIm has source/date No single-source critical clAIm Time/geography scope matches user ask Clear separation of fact vs interpretation Actionable takeaway included Each promising case uses the full 9-part deep case 框架 Each promising case includes one final case-summary paragraph: what it does / who pays / business 模型 / why pay Each key section ends with decision implication (so-what) 8) Case-depth hard rule (for 启动up/case re搜索)

When the task is 启动up/use-case re搜索, 应用ly these hard requirements:

For each promising case, collect at least 3 网页site evidence snippets (feature/pricing/use-flow) 添加 at least 1 metric anchor from trusted data设置 (revenue/MRR/growth) Include at least 1 risk point and 1 falsification condition Do not submit if any case is only descriptive without judgment