Company Intelligence Engine

In this tutorial, you’ll learn how to build a real-time company intelligence system that automatically gathers and structures information about any company. This system is perfect for sales teams, market researchers, and anyone needing up-to-date company information.

Prerequisites

Before starting, ensure you have:

Python 3.7 or newer installed
Basic familiarity with Python programming
A Linkup API key (required for making requests)

Get your API key

Create a Linkup account for free to get your API key.

Project setup

Let’s start by creating a new project and installing the necessary dependencies:

shell

# Create a new project directory
mkdir company-intel
cd company-intel

# Install required packages
pip install linkup-sdk pydantic fastapi uvicorn

Implementation guide

1. Define your data structure

First, we’ll create a data model that specifies exactly what company information we want to collect. Create a new file called schema.py:

python

from pydantic import BaseModel
from typing import List, Optional

class CompanyInfo(BaseModel):
    # Basic company information
    name: str = ""              # Company name
    website: str = ""           # Official website URL
    description: str = ""       # Brief company description

    # Detailed information
    latest_funding: str = ""    # Most recent funding information
    recent_news: List[str] = [] # Latest company news
    leadership_team: List[str] = [] # Key executives and leaders
    tech_stack: List[str] = []  # Technologies used by the company

This schema ensures our data is consistently structured and validated.

2. Build the intelligence engine

Next, create company_intel.py to handle the core functionality:

python

from linkup import LinkupClient
from schema import CompanyInfo

class CompanyIntelligence:
    def __init__(self, api_key: str):
        """Initialize the intelligence engine with your API key."""
        self.client = LinkupClient(api_key=api_key)

    def research_company(self, company_name: str) -> CompanyInfo:
        """
        Gather comprehensive information about a company.

        Args:
            company_name (str): Name of the company to research

        Returns:
            CompanyInfo: Structured company information
        """
        query = f"""
        Research {company_name} and provide:
        - Company name, website, and brief description
        - Most recent funding round or financial announcement
        - Current leadership team members
        - Technologies and tools they use
        - Recent news from the last 3 months

        Focus on current, verified information.
        """

        # Make the API request with structured output
        response = self.client.search(
            query=query,
            depth="deep",           # Get comprehensive results
            output_type="structured",
            structured_output_schema=CompanyInfo
        )

        return response

3. Create the API layer

Now let’s make our intelligence engine accessible via HTTP. Create api.py:

python

from fastapi import FastAPI, HTTPException
from company_intel import CompanyIntelligence

# Initialize FastAPI with metadata
app = FastAPI(
    title="Company Intelligence API",
    description="Real-time company research and intelligence",
    version="1.0.0"
)

# Create intelligence engine instance
intel = CompanyIntelligence(api_key="your-linkup-api-key")

@app.get("/company/{name}", tags=["Company Research"])
async def get_company_info(name: str):
    """
    Retrieve detailed information about a company.

    Parameters:
        name (str): Company name to research

    Returns:
        CompanyInfo: Structured company information
    """
    try:
        return intel.research_company(name)
    except Exception as e:
        raise HTTPException(
            status_code=500,
            detail=f"Error researching company: {str(e)}"
        )

Using the system

Basic usage example

At first, let’s use the intelligence engine directly in Python. We will create a new file called main.py and add the following code to it:

python

from company_intel import CompanyIntelligence

# Initialize the intelligence engine
intel = CompanyIntelligence(api_key="your-api-key")

# Research a company
company = intel.research_company("Vercel")

# Access the information
print(f"Company: {company.name}")
print(f"Website: {company.website}")
print(f"Description: {company.description}")
print(f"Latest Funding: {company.latest_funding}")
print(f"Recent News: {', '.join(company.recent_news)}")
print(f"Leadership Team: {', '.join(company.leadership_team)}")
print(f"Technologies: {', '.join(company.tech_stack)}")

Get your API key

Create a Linkup account for free to get your API key.

You can run the code by executing the following command:

shell

python main.py

Running the API server

Let’s now try our API server.

shell

# Start the server with auto-reload enabled
uvicorn api:app --reload

You can now access the API at http://localhost:8000/docs.

Step 1

Click on the endpoint GET /company/{name}, and click on the Try it out button.

Step 2

Now, enter the company name, for example Vercel, and click on the Execute button.

Step 3

Step 4

You should see the response in JSON format.

Response examples

Successful response

A typical successful request to /company/Vercel returns:

{
    "name": "Vercel",
    "website": "https://vercel.com",
    "description": "Vercel is a cloud platform for static sites and Serverless Functions that fits perfectly with your workflow. It enables developers to host websites and web services that deploy instantly and scale automatically.",
    "latest_funding": "Series D - $150M (December 2023)",
    "recent_news": [
        "Vercel announces Edge Functions improvements with streaming support",
        "New Next.js 14 release brings major performance improvements",
        "Vercel launches new Enterprise Security features"
    ],
    "leadership_team": [
        "Guillermo Rauch - CEO",
        "Malte Ubl - CTO"
    ],
    "tech_stack": [
        "Next.js",
        "React",
        "Node.js",
        "TypeScript",
        "PostgreSQL",
        "Redis",
        "AWS"
    ]
}

Error responses

The API returns appropriate error responses in these situations:

Company not found

{
    "status_code": 404,
    "detail": "Unable to find information for the specified company",
    "timestamp": "2024-12-16T10:30:45Z"
}

Invalid API key

{
    "status_code": 401,
    "detail": "Invalid or missing API key",
    "timestamp": "2024-12-16T10:30:45Z"
}

Rate limit exceeded

{
    "status_code": 429,
    "detail": "Rate limit exceeded. Please try again in 60 seconds",
    "timestamp": "2024-12-16T10:30:45Z"
}

Engine response fields

Field	Type	Description	Example
name	string	Company name	”Vercel”
website	string	Company website URL	”https://vercel.com”
description	string	Brief company description	”Vercel is a cloud platform…“
latest_funding	string	Most recent funding information	”Series D - $150M (December 2023)“
recent_news	array	List of recent news headlines	[“Vercel announces…”, “New Next.js 14…“]
leadership_team	array	List of key leadership members	[“Guillermo Rauch - CEO”, …]
tech_stack	array	List of technologies used	[“Next.js”, “React”, …]
news_sentiment	float	Optional sentiment score	0.8
company_size	string	Optional size estimation	”Large Enterprise”

Best practices

For production use, consider implementing these best practices:

Error handling
- Implement comprehensive error handling for API calls
- Log errors appropriately
- Provide meaningful error messages to users
Rate limiting
- Implement rate limiting to avoid API quota issues
- Consider using a queue for batch processing
- Add retry logic for failed requests
Caching
- Cache frequently requested company data
- Use appropriate TTL values based on data freshness requirements
- Implement cache invalidation strategies
Data validation
- Validate all input data
- Use Pydantic’s validation features
- Implement data cleaning where necessary

Common applications

This system can be used for:

Pre-sales research automation
CRM data enrichment
Competitor monitoring
Market intelligence gathering
Investment research
Due diligence automation

Conclusion

You now have a company intelligence engine that provides:

Real-time company information
Structured, consistent data
Easy API access
Extensible architecture

Remember to:

Keep your API key secure
Respect API rate limits
Implement appropriate caching for your use case
Add error handling for production use

Need help? Email support@linkup.so, ping us on Discord, or talk to us.

Get Started

Endpoints

Platform

Guides

Tutorials

FAQ

Prerequisites

Get your API key

Project setup

Implementation guide

1. Define your data structure

2. Build the intelligence engine

3. Create the API layer

Using the system

Basic usage example

Get your API key

Running the API server

Step 1

Step 2

Step 3

Step 4

Response examples

Successful response

Error responses

Company not found

Invalid API key

Rate limit exceeded

Engine response fields

Best practices

Common applications

Conclusion

Get Started

Endpoints

Platform

Guides

Tutorials

FAQ

Documentation Index

​Prerequisites

Get your API key

​Project setup

​Implementation guide

​1. Define your data structure

​2. Build the intelligence engine

​3. Create the API layer

​Using the system

​Basic usage example

Get your API key

​Running the API server

​Step 1

​Step 2

​Step 3

​Step 4

​Response examples

​Successful response

​Error responses

​Company not found

​Invalid API key

​Rate limit exceeded

​Engine response fields

​Best practices

​Common applications

​Conclusion

Prerequisites

Project setup

Implementation guide

1. Define your data structure

2. Build the intelligence engine

3. Create the API layer

Using the system

Basic usage example

Running the API server

Step 1

Step 2

Step 3

Step 4

Response examples

Successful response

Error responses

Company not found

Invalid API key

Rate limit exceeded

Engine response fields

Best practices

Common applications

Conclusion