Back to Details

people-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

People Research

人物调研

Tool Restriction (Critical)

工具限制（重要）

ONLY use 
web_search_advanced_exa
. Do NOT use 
web_search_exa
or any other Exa tools.
仅使用
web_search_advanced_exa
。不得使用
web_search_exa
或其他任何Exa工具。

Token Isolation (Critical)

Token隔离（重要）

Never run Exa searches in main context. Always spawn Task agents:
  • Agent runs Exa search internally
  • Agent processes results using LLM intelligence
  • Agent returns only distilled output (compact JSON or brief markdown)
  • Main context stays clean regardless of search volume
绝不要在主上下文运行Exa搜索，始终生成Task Agent：
  • Agent在内部运行Exa搜索
  • Agent利用LLM智能处理结果
  • Agent仅返回提炼后的输出（简洁JSON或简短markdown）
  • 无论搜索量多大，主上下文始终保持整洁

Dynamic Tuning

动态调优

No hardcoded numResults. Tune to user intent:
  • User says "a few" → 10-20
  • User says "comprehensive" → 50-100
  • User specifies number → match it
  • Ambiguous? Ask: "How many profiles would you like?"
不要硬编码numResults参数，需根据用户意图调整：
  • 用户说“几个”→ 10-20条
  • 用户说“全面的”→ 50-100条
  • 用户指定数量→ 匹配该数量
  • 意图模糊时？询问：“您需要多少份资料？”

Query Variation

查询变体

Exa returns different results for different phrasings. For coverage:
  • Generate 2-3 query variations
  • Run in parallel
  • Merge and deduplicate
不同的措辞会让Exa返回不同结果。为保证覆盖范围：
  • 生成2-3个查询变体
  • 并行运行搜索
  • 合并并去重结果

Categories

分类选择

Use appropriate Exa 
category
depending on what you need:
  • people
    → LinkedIn profiles, public bios (primary for discovery)
  • personal site
    → personal blogs, portfolio sites, about pages
  • news
    → press mentions, interviews, speaker bios
  • No category (
    type: "auto"
    ) → general web results, broader context
Start with 
category: "people"
for profile discovery, then use other categories or no category with 
livecrawl: "fallback"
for deeper research on specific individuals.
根据需求选择合适的Exa 
category
参数：
  • people
    → LinkedIn资料、公开个人简介（用于人物发现的首选分类）
  • personal site
    → 个人博客、作品集网站、关于页面
  • news
    → 媒体报道、访谈、演讲者简介
  • 不指定分类（
    type: "auto"
    ）→ 通用网页结果、更广泛的背景信息
人物资料发现优先使用
category: "people"
，之后可针对特定人物使用其他分类或不指定分类并搭配
livecrawl: "fallback"
进行深度调研。

Category-Specific Filter Restrictions

分类专属过滤限制

When using 
category: "people"
, these parameters cause errors:
  • startPublishedDate
    / 
    endPublishedDate
  • startCrawlDate
    / 
    endCrawlDate
  • includeText
    / 
    excludeText
  • excludeDomains
  • includeDomains
    — LinkedIn domains only (e.g., "linkedin.com")
When searching without a category, all parameters are available (but 
includeText
/
excludeText
still only support single-item arrays).
使用
category: "people"
时，以下参数会导致错误：
  • startPublishedDate
    / 
    endPublishedDate
  • startCrawlDate
    / 
    endCrawlDate
  • includeText
    / 
    excludeText
  • excludeDomains
  • includeDomains
    — 仅支持LinkedIn域名（例如："linkedin.com"）
不指定分类时，所有参数均可使用（但
includeText
/
excludeText
仍仅支持单元素数组）。

LinkedIn

LinkedIn搜索

Public LinkedIn via Exa: 
category: "people"
, no other filters. Auth-required LinkedIn → use Claude in Chrome browser fallback.
通过Exa获取公开LinkedIn资料：使用
category: "people"
，不添加其他筛选条件。 需要权限的LinkedIn内容→ 回退使用Chrome浏览器中的Claude。

Browser Fallback

浏览器回退方案

Auto-fallback to Claude in Chrome when:
  • Exa returns insufficient results
  • Content is auth-gated
  • Dynamic pages need JavaScript
出现以下情况时自动回退到Chrome浏览器中的Claude：
  • Exa返回结果不足
  • 内容需要权限访问
  • 动态页面需要JavaScript支持

Examples

示例

Discovery: find people by role

人物发现：按职位查找

web_search_advanced_exa {
  "query": "VP Engineering AI infrastructure",
  "category": "people",
  "numResults": 20,
  "type": "auto"
}
web_search_advanced_exa {
  "query": "VP Engineering AI infrastructure",
  "category": "people",
  "numResults": 20,
  "type": "auto"
}

With query variations

使用查询变体

web_search_advanced_exa {
  "query": "machine learning engineer San Francisco",
  "category": "people",
  "additionalQueries": ["ML engineer SF", "AI engineer Bay Area"],
  "numResults": 25,
  "type": "deep"
}
web_search_advanced_exa {
  "query": "machine learning engineer San Francisco",
  "category": "people",
  "additionalQueries": ["ML engineer SF", "AI engineer Bay Area"],
  "numResults": 25,
  "type": "deep"
}

Deep dive: research a specific person

深度调研：特定人物研究

web_search_advanced_exa {
  "query": "Dario Amodei Anthropic CEO background",
  "type": "auto",
  "livecrawl": "fallback",
  "numResults": 15
}
web_search_advanced_exa {
  "query": "Dario Amodei Anthropic CEO background",
  "type": "auto",
  "livecrawl": "fallback",
  "numResults": 15
}

News mentions

媒体报道查询

web_search_advanced_exa {
  "query": "Dario Amodei interview",
  "category": "news",
  "numResults": 10,
  "startPublishedDate": "2024-01-01"
}
web_search_advanced_exa {
  "query": "Dario Amodei interview",
  "category": "news",
  "numResults": 10,
  "startPublishedDate": "2024-01-01"
}

Output Format

输出格式

Return:
  1. Results (name, title, company, location if available)
  2. Sources (Profile URLs)
  3. Notes (profile completeness, verification status)
返回内容需包含：
  1. 结果（姓名、职位、公司、所在地，如有）
  2. 来源（资料链接）
  3. 备注（资料完整性、验证状态）