Crunchbase Startup Analysis and Comparison Report Generator using Bright Data and Gemini AI - n8n Workflow

Market Researchers and Analysts needing rapid competitor intelligence.
Venture Capitalists and Investors looking for recent, high-potential startups in specific sectors.
Automation Specialists seeking advanced n8n templates that combine scraping, custom code, and generative AI.
Users who require a reliable n8n trigger to start complex, data-heavy tasks via a simple web form.

Conducting deep competitive analysis usually involves manual data scraping, cleansing, and expert review. This sophisticated n8n workflow streamlines the entire process. By utilizing the When User Completes Form n8n trigger, users input a target keyword (e.g., "AI in healthtech"). The n8n automation then communicates with Bright Data to pull recent startup data from Crunchbase. Crucially, the data is cleaned and sorted by a custom Python Code n8n node before being fed into the Gemini LLM for expert comparative analysis. Finally, the raw data and the AI-generated report are consolidated and automatically logged into a Google Sheet. This powerful integration demonstrates the capability of advanced n8n templates for transforming raw data into actionable business intelligence.

The entire process is initiated by the When User Completes Form n8n trigger, which captures the user-provided 'Keyword'.

1. Data Extraction: The keyword is immediately passed to the HTTP Request- Post API call to Bright Data n8n node, initiating a Crunchbase discovery job for relevant companies.


2. Polling Loop: The n8n workflow enters a polling loop using the Wait - Polling Bright Data node (set to 15 seconds) and the Snapshot Progress request. The If - Checking status of Snapshot n8n node continuously checks the job status. If the status is 'running', the loop continues. Once complete, the n8n flow proceeds to the next step.


3. Data Retrieval & Cleaning: The HTTP Request - Getting data from Bright Data n8n node downloads the full snapshot. The subsequent Code - Parse and Clean JSON Data node (written in Python) filters this data, sorts companies by the newest founded date, extracts specific fields (e.g., funding, founders, descriptions), and selects the top 10 recent companies for analysis. This custom n8n node is vital for preparing high-quality input.


4. AI Analysis: The cleaned data for the top 10 companies is passed to the Google Gemini - Comparative Analisys n8n node. This chain uses the Google Gemini Chat Model to generate a detailed competitive summary based on the initial search keyword.


5. Output Generation: A Merge n8n node combines the structured company data with the text generated by the AI. The final Code - Combining JSON and AI outputs node integrates the comprehensive AI analysis text into the first company record's ai_analysis field.


6. Export: The structured, analyzed dataset is appended to the designated Google Sheet using the Google Sheets - Export Results n8n node, completing the automated research report via this complex n8n workflow.

To deploy this powerful n8n workflow, follow these steps:

1. Import: Copy the provided JSON code and import it into your n8n instance as a new workflow.


2. Bright Data Credentials: Configure the Bright Data API key in all HTTP Request n8n nodes (HTTP Request- Post API call to Bright Data, Snapshot Progress, HTTP Request - Getting data from Bright Data). Replace Bearer YOURAPIKEY with your actual token.


3. Google Gemini Credentials: Ensure your LangChain integration for the Google Gemini Chat Model n8n node is correctly set up with the required API key.


4. Google Sheets Setup: Configure the Google Sheets - Export Results n8n node. Select the correct Google Sheet document and specify the sheet name where the startup data should be exported. Ensure the service account has write permissions to this document.


5. Activation: Activate the When User Completes Form n8n trigger and use the generated public URL to run the n8n workflow.

When User Completes Form (n8n trigger): Initiates the entire n8n workflow upon form submission, capturing the 'Keyword' required for the search.
HTTP Request- Post API call to Bright Data (n8n node): Triggers the scraping/data discovery process on Bright Data's Crunchbase dataset using the user-supplied keyword.
If - Checking status of Snapshot (n8n node): Controls the polling loop, ensuring the n8n workflow waits until the Bright Data job status is no longer 'running'.
Code - Parse and Clean JSON Data (n8n node): Uses Python code to filter, sort, and select the top 10 most recently founded companies, standardizing the data structure for the AI component.
Google Gemini - Comparative Analisys (n8n node): Leverages the Gemini model via LangChain integration to perform a deep comparative assessment of the company data based on the provided prompt.
Code - Combining JSON and AI outputs (n8n node): Merges the AI-generated text report back into the structured company data array, making the final output cohesive.

• Google Sheets - Export Results (n8n node): The final action, which appends the complete, analyzed data set, including the AI summary, to the specified Google Sheet document.