aggregateContacts

Analyze and summarize contact statistics using numerical data. Count and calculate percentages for specific queries like job titles, companies, or locations without revealing individual details. Ideal for insights such as 'how many contacts work at Google?' or 'what % are engineers?'.

Instructions

Get numerical statistics and counts ONLY. Returns numbers and percentages, never specific contacts. For counting questions like "how many work at Google?" or "what % are engineers?". Use search endpoint instead for any "who" questions or to get actual contact details.

Input Schema

Name	Required	Description
`company_name`	No	If the query refers to a company or acronym of companies, list company names as they would on a LinkedIn profile.
`job_title`	No	If the query refers to a job title, position, or industry, list relevant job titles as they would be on a LinkedIn profile. Examples: Developer should return positions such as 'Software Engineer', 'Full Stack Developer', 'Data Scientist', etc. Banker should return positions such as 'Financial Analyst', 'Investment Banker', 'Credit Analyst', etc. Healthcare industry should return positions such as 'Registered Nurse', 'Physician', 'Medical Director', etc. Legal industry should return positions such as 'Attorney', 'Legal Counsel', 'Paralegal', etc.
`location`	No	If the query refers to a location (city, state, country, region) where people are located or based, list the locations as they would appear on a LinkedIn profile. For example, if someone asks about "people in New York", return "New York City Metropolitan Area" or if they ask about "contacts in California", return "San Francisco Bay Area", "Greater Los Angeles Area", etc.
`query`	Yes	The raw search query from the user. This field is required and should contain all the key details extracted from the user's prompt to enable effective database searching and aggregation. For example, if the user asks 'how many people work at Google', preserve both the company filter 'Google' and the fact that they want a count. If they ask 'what are the most common job titles in my network', preserve that they want job titles aggregated and ranked by frequency. The query should maintain any conditions (OR, AND) and aggregation needs to properly build the elasticsearch query.

Input Schema (JSON Schema)

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "additionalProperties": false,
  "properties": {
    "company_name": {
      "default": [],
      "description": "If the query refers to a company or acronym of companies, list company names as they would on a LinkedIn profile.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "job_title": {
      "default": [],
      "description": "If the query refers to a job title, position, or industry, list relevant job titles as they would be on a LinkedIn profile. Examples: Developer should return positions such as 'Software Engineer', 'Full Stack Developer', 'Data Scientist', etc. Banker should return positions such as 'Financial Analyst', 'Investment Banker', 'Credit Analyst', etc. Healthcare industry should return positions such as 'Registered Nurse', 'Physician', 'Medical Director', etc. Legal industry should return positions such as 'Attorney', 'Legal Counsel', 'Paralegal', etc.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "location": {
      "default": [],
      "description": "If the query refers to a location (city, state, country, region) where people are located or based, list the locations as they would appear on a LinkedIn profile. For example, if someone asks about \"people in New York\", return \"New York City Metropolitan Area\" or if they ask about \"contacts in California\", return \"San Francisco Bay Area\", \"Greater Los Angeles Area\", etc.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "query": {
      "description": "The raw search query from the user. This field is required and should contain all the key details extracted from the user's prompt to enable effective database searching and aggregation. For example, if the user asks 'how many people work at Google', preserve both the company filter 'Google' and the fact that they want a count. If they ask 'what are the most common job titles in my network', preserve that they want job titles aggregated and ranked by frequency. The query should maintain any conditions (OR, AND) and aggregation needs to properly build the elasticsearch query.",
      "type": "string"
    }
  },
  "required": [
    "query"
  ],
  "type": "object"
}

Clay