investor-call-prep

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Investor Call Prep

投资者会议筹备

Setup

设置

Read your credentials from ~/.gooseworks/credentials.json:

bash

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run:

npx gooseworks login

All endpoints use Bearer auth:

-H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Pull investor meetings from Google Calendar, deep-research each firm (scrape their website, analyze portfolio, extract thesis), and output an honest prep sheet that says which investors are a real fit and which aren't.

Read-only calendar access. Never creates, modifies, or deletes events.

从~/.gooseworks/credentials.json读取您的凭证：

bash

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

如果~/.gooseworks/credentials.json不存在，请告知用户运行：

npx gooseworks login

所有端点均使用Bearer认证：

-H "Authorization: Bearer $GOOSEWORKS_API_KEY"

从Google Calendar提取投资者会议，深入研究每家机构（爬取其网站、分析投资组合、提取投资理念），并输出一份真实的筹备清单，说明哪些投资者是真正合适的，哪些不是。

仅读取日历权限。绝不会创建、修改或删除活动。

Input

输入

domain (required) — user's company website (provided in the prompt, e.g. "prep my investor calls for orthogonal.com")
competitors (optional) — auto-detected if not provided

Always export to Google Sheets at the end — it's free and takes seconds.

domain（必填）—— 用户公司的网站（在提示中提供，例如"为orthogonal.com筹备我的投资者会议"）
competitors（可选）—— 如果未提供则自动检测

最后务必导出到Google Sheets中——这是免费的，只需几秒钟。

Step 1: Pull Investor Meetings

步骤1：提取投资者会议

Pull from today through Demo Day (March 24, 2026). All W26 companies are fundraising now through Demo Day. Make multiple calls if needed to avoid truncation — e.g. split into week 1 and week 2.

bash

undefined

提取从今天到演示日（2026年3月24日）的会议。所有W26公司目前正通过演示日进行融资。如有需要可进行多次调用以避免截断——例如分为第1周和第2周。

bash

undefined

Adjust timeMin to today's date

将timeMin调整为今天的日期

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"google-calendar","path":"/list-events"}' "calendarId": "primary", "timeMin": "{today}T00:00:00Z", "timeMax": "{midpoint}T23:59:59Z", "maxResults": 100, "singleEvents": true, "orderBy": "startTime" }'

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"google-calendar","path":"/list-events"}' "calendarId": "primary", "timeMin": "{midpoint+1}T00:00:00Z", "timeMax": "2026-03-24T23:59:59Z", "maxResults": 100, "singleEvents": true, "orderBy": "startTime" }'

undefined

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"google-calendar","path":"/list-events"}' "calendarId": "primary", "timeMin": "{midpoint+1}T00:00:00Z", "timeMax": "2026-03-24T23:59:59Z", "maxResults": 100, "singleEvents": true, "orderBy": "startTime" }'

undefined

Filtering — be precise, not greedy

筛选——精准而非贪多

The keyword approach catches false positives (personal meetings, mock pitches, etc.). Use this priority order:

Strong signal (auto-include): Title starts with "Investors between" — this is the standard Cal.com booking format for investor meetings.
Medium signal (auto-include): Attendee email domain is a known VC domain (e.g.
```
@moonfire.com
```
,
```
@a16z.com
```
,
```
@accel.com
```
) OR the event description contains VC firm names.
Weak signal (requires confirmation): Title contains keywords like
```
invest
```
,
```
vc
```
,
```
fund
```
,
```
capital
```
,
```
ventures
```
,
```
angel
```
,
```
seed
```
,
```
series
```
— BUT does NOT match pattern #1. These need manual review.
Exclude: Events with "mock" or "practice" in title/description (these are rehearsals, not real meetings). Also exclude batch/group events with no attendees (e.g. "Fundraising Open Mic", "Demo Day") — these are YC events, not 1:1 investor calls.

Extract: title, date/time, attendee emails (non-company = investor contacts), description (often has investor names/emails even when attendee list doesn't).

Present filtered list to user for confirmation before proceeding.

关键词方法会误判（个人会议、模拟路演等）。请按照以下优先级顺序筛选：

强信号（自动纳入）：标题以"Investors between"开头——这是Cal.com投资者会议的标准预订格式。
中等信号（自动纳入）：参会者邮箱域名是已知的VC域名（例如
```
@moonfire.com
```
、
```
@a16z.com
```
、
```
@accel.com
```
），或者活动描述中包含VC机构名称。
弱信号（需确认）：标题包含
```
invest
```
、
```
vc
```
、
```
fund
```
、
```
capital
```
、
```
ventures
```
、
```
angel
```
、
```
seed
```
、
```
series
```
等关键词——但不符合模式#1。这些需要人工审核。
排除：标题/描述中包含"mock"或"practice"的活动（这些是彩排，不是真实会议）。同时排除没有参会者的批量/群组活动（例如"Fundraising Open Mic"、"Demo Day"）——这些是YC活动，不是一对一投资者会议。

提取：标题、日期/时间、参会者邮箱（非公司邮箱 = 投资者联系人）、描述（即使参会者列表中没有，描述中通常也会有投资者姓名/邮箱）。

在继续之前，请将筛选后的列表呈现给用户确认。

Create the Google Sheet immediately after confirmation

确认后立即创建Google Sheet

Before starting any research, create the spreadsheet and populate it with all confirmed investor rows (date/time, firm name, investor name, firm website — leave research columns blank). Share the link with the user so they can watch results fill in live as each investor is researched. This is much better UX than waiting for all research to complete.

在开始任何研究之前，创建电子表格并填入所有已确认的投资者行（日期/时间、机构名称、投资者姓名、机构网站——研究列留空）。将链接分享给用户，以便他们可以实时查看每个投资者的研究结果填充情况。这比等待所有研究完成后再交付的用户体验要好得多。

Step 2: Research the User's Company

步骤2：研究用户的公司

Ask the user to describe their company in 1-2 sentences rather than relying on Perplexity, which often confuses companies with similar names (e.g. orthogonal.com vs orthogonal.io). The user's own description is always more accurate than a web search for early-stage startups.

Then auto-detect competitors:

bash

undefined

请用户用1-2句话描述他们的公司，而不是依赖Perplexity，因为它经常混淆名称相似的公司（例如orthogonal.com和orthogonal.io）。对于早期初创公司，用户自己的描述总是比网络搜索更准确。

然后自动检测竞争对手：

bash

undefined

Auto-detect competitors (skip if user provided)

自动检测竞争对手（如果用户已提供则跳过）

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"perplexity","path":"/chat/completions"}' "model": "sonar", "messages": [{"role": "user", "content": "Top 5-10 competitors of {company_name} ({domain})? {user_provided_description}. Company names and domains only."}] }'


**Verify the competitor list with the user** before proceeding. Perplexity often returns enterprise incumbents (MuleSoft, Workato) rather than actual startup competitors. The user knows their competitive landscape better.

Save the company description and confirmed competitor list — use them for every investor assessment.


**在继续之前，请与用户核实竞争对手列表**。Perplexity经常返回企业巨头（MuleSoft、Workato），而不是实际的初创公司竞争对手。用户更了解他们的竞争格局。

保存公司描述和已确认的竞争对手列表——将它们用于每一项投资者评估。

Step 2b: Reverse-lookup competitor investors (one-time, cheap)

步骤2b：反向查找竞争对手的投资者（一次性操作，成本低）

Instead of asking each investor "have you invested in X?" (unreliable), do a single reverse lookup for each competitor. This is 1 Perplexity call per competitor — not per investor.

bash

undefined

不要向每位投资者询问"你们是否投资了X？"（不可靠），而是为每个竞争对手进行一次反向查找。每个竞争对手只需调用一次Perplexity——而非每个投资者。

bash

undefined

Run one call per competitor (e.g. 5 competitors = 5 calls total)

为每个竞争对手运行一次调用（例如5个竞争对手 = 总共5次调用）

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"perplexity","path":"/chat/completions"}' "model": "sonar", "messages": [{"role": "user", "content": "Who are the investors in {competitor_name} ({competitor_domain})? List all known venture capital firms and angel investors who have invested in them, with round details if available."}] }'


Build a lookup table: `{investor_firm -> [competitors they backed]}`. Cross-reference this against the meeting list. This catches conflicts that per-investor Perplexity queries miss, at a fraction of the cost.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"perplexity","path":"/chat/completions"}' "model": "sonar", "messages": [{"role": "user", "content": "Who are the investors in {competitor_name} ({competitor_domain})? List all known venture capital firms and angel investors who have invested in them, with round details if available."}] }'


构建一个查找表：`{investor_firm -> [competitors they backed]}`。将此与会议列表进行交叉引用。这能以极低的成本发现针对单个投资者的Perplexity查询所遗漏的冲突。

Step 3: Research Each Investor

步骤3：研究每位投资者

Run ALL of these in parallel per investor. Every source adds unique data.

为每位投资者并行运行所有这些操作。每个来源都能提供独特的数据。

3a. Apollo — investor profile from email

3a. Apollo — 通过邮箱获取投资者资料

bash

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"apollo","path":"/api/v1/people/match"}'
  "email": "{investor_email}",
  "reveal_personal_emails": true
}'

No attendee email? Don't stop. Parse firm name from event title, then:

bash

undefined

bash

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"apollo","path":"/api/v1/people/match"}'
  "email": "{investor_email}",
  "reveal_personal_emails": true
}'

没有参会者邮箱？不要停止。 从活动标题中解析机构名称，然后：

bash

undefined

Firm enrichment

机构信息补充

Find key people

查找关键人员

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"apollo","path":"/api/v1/mixed_people/search"}' "q_organization_domains": "{firm_domain}", "person_titles": ["Partner", "Principal", "Managing Director", "GP", "General Partner", "Investor"], "page": 1, "per_page": 10 }'

undefined

undefined

3b. Scrape the firm's website (most reliable source)

3b. 爬取机构网站（最可靠的来源）

VC websites are the ground truth. Perplexity and Apollo often have gaps for smaller firms.

bash

undefined

VC网站是真实依据。对于较小的机构，Perplexity和Apollo经常存在信息缺口。

bash

undefined

Main page — thesis, overview, portfolio

主页——投资理念、概述、投资组合

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"scrapegraph","path":"/v1/smartscraper"}' "website_url": "https://{firm_website}", "user_prompt": "Extract ALL information: investment thesis, fund size, check size, stage focus, sector focus, geographic focus, every portfolio company listed, team members with titles and LinkedIn URLs, contact info." }'

Portfolio page (try /portfolio, /companies, /investments — skip on 404)

投资组合页面（尝试/portfolio、/companies、/investments——404则跳过）

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"scrapegraph","path":"/v1/smartscraper"}' "website_url": "https://{firm_website}/portfolio", "user_prompt": "Extract every portfolio company: name, sector, funding stage, description, website URL." }'

Team page (try /team, /people, /about — skip on 404)

团队页面（尝试/team、/people、/about——404则跳过）

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"scrapegraph","path":"/v1/smartscraper"}' "website_url": "https://{firm_website}/team", "user_prompt": "Extract every team member: full name, title, LinkedIn URL, bio summary, background." }'

undefined

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run
-H "Authorization: Bearer $GOOSEWORKS_API_KEY"
-H "Content-Type: application/json"
-d '{"api":"scrapegraph","path":"/v1/smartscraper"}' "website_url": "https://{firm_website}/team", "user_prompt": "Extract every team member: full name, title, LinkedIn URL, bio summary, background." }'

undefined

3c. Perplexity — thesis, portfolio, competitor check

3c. Perplexity — 投资理念、投资组合、竞争对手检查

Critical: use context-rich prompts. Include location, GP names, aliases. "Tell me about e2vc" gets nothing. "Tell me about e2vc, formerly 500 Emerging Europe, based in Turkey" gets rich results.

bash

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"perplexity","path":"/chat/completions"}'
  "model": "sonar",
  "messages": [{"role": "user", "content": "Tell me about {firm_name}, a venture capital firm{location_context}{gp_context}{alias_context}. I am raising for {company_name}, {company_description}. Answer:
1. Investment thesis and typical check size?
2. Notable portfolio companies in {company_sectors}?
3. Have they invested in any of these competitors: {competitor_list}?
4. What stage?
5. Recent investments or news?
6. Key partners and backgrounds?
7. Would {company_name} be a good fit for them? Why or why not?"}]
}'

关键：使用富含上下文的提示词。包含地点、普通合伙人姓名、别名。"Tell me about e2vc"得不到有效结果。"Tell me about e2vc, formerly 500 Emerging Europe, based in Turkey"能得到丰富的结果。

bash

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"perplexity","path":"/chat/completions"}'
  "model": "sonar",
  "messages": [{"role": "user", "content": "Tell me about {firm_name}, a venture capital firm{location_context}{gp_context}{alias_context}. I am raising for {company_name}, {company_description}. Answer:
1. Investment thesis and typical check size?
2. Notable portfolio companies in {company_sectors}?
3. Have they invested in any of these competitors: {competitor_list}?
4. What stage?
5. Recent investments or news?
6. Key partners and backgrounds?
7. Would {company_name} be a good fit for them? Why or why not?"}]
}'

Step 4: Classify Before Compiling

步骤4：编译前分类

Before writing up the prep sheet, classify each meeting into one of these categories based on research:

VC Fund — traditional venture capital firm (GP, Partner, Principal, Associate)
Angel — individual investor (current/former founder, operator, or executive investing personally)
NOT an investor — flag prominently. This includes:
- Founders of other startups (potential BD/partnership, not fundraise)
- Researchers/academics with no investing track record
- Operators at companies (not investing personally)
- Mock pitch / practice sessions

For non-investors, still include them in the sheet but mark the Compatibility column as "NOT AN INVESTOR" and explain what the meeting likely is (BD, partnership, mock pitch, etc.). This prevents the user from wasting prep time on a fundraise pitch when the meeting is something else.

在撰写筹备清单之前，根据研究结果将每个会议分为以下类别之一：

VC基金 — 传统风险投资机构（普通合伙人、合伙人、负责人、助理）
天使投资者 — 个人投资者（现任/前任创始人、经营者或高管个人投资）
非投资者 — 突出标记。包括：
- 其他初创公司的创始人（潜在商务拓展/合作伙伴，而非融资对象）
- 无投资记录的研究人员/学者
- 企业经营者（不进行个人投资）
- 模拟路演/练习环节

对于非投资者，仍需将其列入清单，但在适配性列标记为"NOT AN INVESTOR"并说明会议可能的性质（商务拓展、合作伙伴、模拟路演等）。这可以避免用户在会议并非融资路演时浪费筹备时间。

Surface ecosystem investments, not just competitor conflicts

展示生态投资，而非仅竞争对手冲突

When an investor has portfolio companies that are adjacent to the user's space (not direct competitors but in the same ecosystem), surface these as Ecosystem Signals rather than ignoring them. These are actually positive — they show the investor understands the space.

Examples:

An investor backed CrewAI (AI agent framework) → they understand agents need API access → good hook for Orthogonal
An investor backed Arcade.dev (AI tooling) → adjacent, not a conflict → shows thesis alignment
An investor backed Langbase (AI agents) → ecosystem overlap → talking point

Only flag as Competitor Conflict if the portfolio company is a direct competitor (same product, same customer, same use case). Adjacent/ecosystem companies go in the Talking Points column as conversation hooks.

当投资者的投资组合公司与用户所在领域相邻（不是直接竞争对手但处于同一生态系统）时，将其作为生态信号展示，而非忽略。这些实际上是积极信号——表明投资者了解该领域。

示例：

某投资者投资了CrewAI（AI Agent框架）→ 他们了解Agent需要API访问权限→ 这是与Orthogonal沟通的良好切入点
某投资者投资了Arcade.dev（AI工具）→ 相邻领域，无冲突→ 表明投资理念一致
某投资者投资了Langbase（AI Agents）→ 生态重叠→ 可作为讨论话题

只有当投资组合公司是直接竞争对手（相同产品、相同客户、相同用例）时，才标记为竞争对手冲突。相邻/生态系统公司列入讨论要点列作为对话切入点。

Step 5: Compile Prep Sheet

步骤5：编译筹备清单

Cross-reference all sources. When they conflict, prefer: website > Apollo > Perplexity.

交叉引用所有来源。当信息冲突时，优先顺序为：网站 > Apollo > Perplexity。

Output format per meeting:

每个会议的输出格式：

undefined

undefined

{Firm Name} — {Date/Time}

{机构名称} — {日期/时间}

Investor: {Name}, {Title} LinkedIn: {linkedin_url} Firm: {firm_name} | {firm_linkedin_url} | {firm_website}

Thesis: {specific, not generic} Stage: {seed, Series A, etc.} | Check Size: {range} | Fund Size: {if known} Geographic Focus: {regions}

Portfolio ({count}): {most relevant to user's space} Competitor Conflicts: {names} or None found

Compatibility: {verdict} {honest, company-specific assessment}

Talking Points:

{angle from portfolio overlap}
{angle from partner's background}
{angle from thesis alignment}

undefined

投资者： {姓名}, {职位} LinkedIn： {linkedin_url} 机构： {机构名称} | {机构LinkedIn链接} | {机构网站}

投资理念： {具体内容，而非泛泛之谈} 阶段： {种子轮、A轮等} | 投资额度： {范围} | 基金规模： {若已知} 地域聚焦： {地区}

投资组合（{数量}家）： {与用户领域最相关的公司} 竞争对手冲突： {名称} 或未发现

适配性：{结论} {真实、针对公司的评估}

讨论要点：

{来自投资组合重叠的角度}
{来自合伙人背景的角度}
{来自投资理念契合的角度}

undefined

Compatibility — Be Honest and Specific

适配性——真实且具体

Every rating must reference the user's specific company, product, and sector. Generic assessments are useless.

Strong Fit — Thesis covers user's sector AND stage. Adjacent portfolio companies (not competitors). Partner has relevant domain expertise.

"Strong fit — Revo invests in B2B SaaS + AI from Turkey/CEE at seed-Series A ($500K-$5M). Their marketplace portfolio companies are adjacent. Melis's M&A background means she gets platform economics."

Moderate Fit — Partial overlap. Be specific about what's missing.

"Moderate fit — right stage but portfolio leans fintech/industrial tech, no developer tools. You'll need to educate them on the API marketplace space."

Weak Fit — Wrong thesis, stage, geography, or has funded a competitor. Don't sugarcoat.

"Weak fit — consumer apps focus, Series B+ checks. No dev tools portfolio. May not be worth your limited pre-demo-day time."

Competitor Conflict — Flag prominently.

"They backed Composio — a direct competitor. Ask early whether this creates a conflict."

每个评级必须参考用户的具体公司、产品和领域。泛泛的评估毫无用处。

强适配 — 投资理念涵盖用户的领域和阶段。有相邻的投资组合公司（非竞争对手）。合伙人具备相关领域专业知识。

"强适配——Revo专注于土耳其/中东欧地区的B2B SaaS+AI领域，投资阶段为种子轮到A轮（50万美元至500万美元）。他们的 marketplace投资组合公司与您的领域相邻。Melis的并购背景意味着她理解平台经济。"

中等适配 — 部分重叠。具体说明缺失的部分。

"中等适配——阶段匹配，但投资组合倾向于金融科技/工业科技，无开发者工具相关布局。您需要向他们介绍API marketplace领域。"

弱适配 — 投资理念、阶段、地域不符，或投资了竞争对手。不要粉饰。

"弱适配——专注于消费应用，投资阶段为B轮及以后。无开发者工具投资组合。可能不值得您在演示日前投入有限的时间。"

竞争对手冲突 — 突出标记。

"他们投资了Composio——您的直接竞争对手。请尽早询问这是否会造成冲突。"

Step 6: Google Sheets Export

步骤6：导出到Google Sheets

The spreadsheet was already created in Step 1. Update each row as research completes — use

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \   -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \   -H "Content-Type: application/json" \   -d '{"api":"google-sheets","path":"/update-values

"}'

Important: Always use

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \   -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \   -H "Content-Type: application/json" \   -d '{"api":"google-sheets

","path":"for"}'

电子表格已在步骤1中创建。完成研究后更新每一行——使用

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \   -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \   -H "Content-Type: application/json" \   -d '{"api":"google-sheets","path":"/update-values

"}'

重要提示： 务必使用

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \   -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \   -H "Content-Type: application/json" \   -d '{"api":"google-sheets

","path":"for"}'

Tips

提示

Parallelize everything: Apollo, Scrapegraph, Perplexity, Fiber are independent — run all in parallel per investor, and process investors simultaneously.
Website > all other sources: Firm websites are ground truth. Always scrape.
No email? Parse the firm name from the event title → derive domain → Apollo org enrich + people search + website scrape.
Context in Perplexity prompts: Include location, GP names, "formerly known as" — massively improves results for smaller firms.
Be brutal on fit: User has limited time. Say which meetings to prioritize and which to skip.
Firm domain from email:
```
investor@somefirm.com
```
→ domain is
```
somefirm.com
```
.
Multiple attendees: Run Apollo on each. Most senior person = decision-maker.

并行处理所有操作：Apollo、Scrapegraph、Perplexity、Fiber相互独立——为每位投资者并行运行所有操作，同时处理多位投资者。
网站 > 所有其他来源：机构网站是真实依据。务必爬取。
没有邮箱？解析机构名称 从活动标题中提取→推导域名→Apollo机构信息补充+人员搜索+网站爬取。
Perplexity提示词中加入上下文：包含地点、普通合伙人姓名、"曾用名"——大幅提升小型机构的搜索结果质量。
对适配性严格判断：用户时间有限。说明哪些会议需要优先处理，哪些可以跳过。
从邮箱获取机构域名：
```
investor@somefirm.com
```
→域名是
```
somefirm.com
```
。
多位参会者：为每位参会者运行Apollo。职位最高的人是决策者。