Back to Details

company-research

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Company Research

企业调研

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.
仅可使用
web_search_advanced_exa
。禁止使用
web_search_exa
或其他任何Exa工具。

Token Isolation (Critical)

令牌隔离（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
切勿在主上下文环境中运行Exa搜索，务必生成任务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内容（简洁JSON或简短markdown格式）
  • 无论搜索量多少，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 companies would you like?"
不要硬编码numResults参数，需根据用户需求调整：
  • 用户说"一些" → 10-20条结果
  • 用户说"全面的" → 50-100条结果
  • 用户指定数量 → 匹配该数量
  • 需求不明确时？询问："您需要查找多少家企业？"

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返回不同的结果。为确保覆盖全面：
  • 生成2-3种查询变体
  • 并行运行查询
  • 合并结果并去重

Categories

分类

Use appropriate Exa 
category
depending on what you need:
  • company
    → homepages, rich metadata (headcount, location, funding, revenue)
  • news
    → press coverage, announcements
  • tweet
    → social presence, public commentary
  • people
    → LinkedIn profiles (public data)
  • No category (
    type: "auto"
    ) → general web results, deep dives, broader context
Start with 
category: "company"
for discovery, then use other categories or no category with 
livecrawl: "fallback"
for deeper research.
根据需求选择合适的Exa 
category
参数：
  • company
    → 企业官网、丰富元数据（员工数量、地理位置、融资情况、营收）
  • news
    → 媒体报道、公告
  • tweet
    → 社交动态、公众评论
  • people
    → LinkedIn档案（公开数据）
  • 不设置分类（
    type: "auto"
    ）→ 通用网页结果、深度调研、更广泛的上下文信息
初始调研时使用
category: "company"
，后续如需深度调研，可使用其他分类或不设置分类并搭配
livecrawl: "fallback"
参数。

Category-Specific Filter Restrictions

分类专属过滤限制

When using 
category: "company"
, these parameters cause 400 errors:
  • includeDomains
    / 
    excludeDomains
  • startPublishedDate
    / 
    endPublishedDate
  • startCrawlDate
    / 
    endCrawlDate
When searching without a category (or with 
news
), domain and date filters work fine.
Universal restriction: 
includeText
and 
excludeText
only support single-item arrays. Multi-item arrays cause 400 errors across all categories.
当使用
category: "company"
时，以下参数会导致400错误：
  • includeDomains
    / 
    excludeDomains
  • startPublishedDate
    / 
    endPublishedDate
  • startCrawlDate
    / 
    endCrawlDate
不设置分类（或使用
news
分类）时，域名和日期过滤可正常使用。
通用限制：
includeText
和
excludeText
仅支持单元素数组。多元素数组会在所有分类下导致400错误。

LinkedIn

LinkedIn数据获取

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数据：使用
category: "people"
，不添加其他过滤条件。 如需获取需授权的LinkedIn内容→ 退而使用Chrome浏览器中的Claude。

Browser Fallback

浏览器Fallback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切换为Chrome浏览器中的Claude：
  • Exa返回的结果不足
  • 内容需要授权访问
  • 动态页面需要JavaScript支持

Examples

示例

Discovery: find companies in a space

发现：查找某领域的企业

web_search_advanced_exa {
  "query": "AI infrastructure startups San Francisco",
  "category": "company",
  "numResults": 20,
  "type": "auto"
}
web_search_advanced_exa {
  "query": "AI infrastructure startups San Francisco",
  "category": "company",
  "numResults": 20,
  "type": "auto"
}

Deep dive: research a specific company

深度调研：研究特定企业

web_search_advanced_exa {
  "query": "Anthropic funding rounds valuation 2024",
  "type": "deep",
  "livecrawl": "fallback",
  "numResults": 10,
  "includeDomains": ["techcrunch.com", "crunchbase.com", "bloomberg.com"]
}
web_search_advanced_exa {
  "query": "Anthropic funding rounds valuation 2024",
  "type": "deep",
  "livecrawl": "fallback",
  "numResults": 10,
  "includeDomains": ["techcrunch.com", "crunchbase.com", "bloomberg.com"]
}

News coverage

新闻报道调研

web_search_advanced_exa {
  "query": "Anthropic AI safety",
  "category": "news",
  "numResults": 15,
  "startPublishedDate": "2024-01-01"
}
web_search_advanced_exa {
  "query": "Anthropic AI safety",
  "category": "news",
  "numResults": 15,
  "startPublishedDate": "2024-01-01"
}

LinkedIn profiles

LinkedIn档案查找

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

Output Format

输出格式

Return:
  1. Results (structured list; one company per row)
  2. Sources (URLs; 1-line relevance each)
  3. Notes (uncertainty/conflicts)
返回内容要求：
  1. 结果（结构化列表；每行一家企业）
  2. 来源（URL；每条来源配一行相关性说明）
  3. 备注（不确定性/冲突信息）