Overview#
Namedropping a prospect's clients in your emails is a proven way to boost conversion rates. This template shows you how to use Firecrawl and Cargo to scrape client names from a prospect’s homepage, enrich the data, and map it to your CRM for effective prospecting.
All integrations mentioned in this template require an associated connector to be set up in your Cargo workspace. Some integrations are eligible for use with Cargo credits. See the documentation for instructions on setting up connectors and using Cargo credits.
Personalize outreach by extracting social proof from a webpage inside a Cargo workflow#
Step 1 - Set variables#
Set up your input variables to the workflow
Inputs used in the workflow are set up in the variables node at the beginning of the workflow. This node is used to define the parameters that will be passed through the rest of workflow as inputs to the rest of the nodes.
To power this workflow, the following variables are needed:
- domain: The domain name of the company whose homepage you want to scrape for client logos
- companyHubspotID: The ID of the company in your CRM
Step 2 - Scrape webpage#
Scrape the homepage with Firecrawl
For web scraping, we recommend using Firecrawl to crawl through different prospects’ homepages, which often display logos and names of their top clients.
Firecrawl excels at normalizing various data formats into plain markdown, making it easier to analyze the content. Another advantage is its ability to crawl multiple website layers using the crawl action, allowing users to combine information from multiple pages into a single output.
Step 3 - AI analysis#
Extract client names using OpenAI
Once you have the markdown content from Firecrawl, use an OpenAI node to extract client names, which are often found in logos or plain text. The markdown should include both formats. Below is a prompt we've seen work well for this example.
Based on this company website including markdown from different pages, find the clients of this company, they might be showcased in a images or logo, in usecases, in plain text etc...
The key is to strictly define the analysis rules in the system prompt of the OpenAI integration, setting guardrails for output quality. Ideally, you’ll receive a structured object of client names that can be looped through later in the workflow. Use the response format section to structure the JSON schema of the desired output. Below is an example of a system prompt you could use.
Your output should contain a maximum of 3 client names separated by a comma. Don't add anything else to your answer. Prioritize clients where you have 100% confidence. If you dont have any results, output "nothing".
Step 4 - Find domain names#
Find domains for client names inside a group node
Once the OpenAI analysis is complete, push the contents of the produced object to a group node in Cargo, which will loop through each identified client name.
Inside the group node, use the Serper node to find the associated domain for each identified client name. A Google search should typically surface their domain names. If not, add keywords extracted from the Firecrawl output to refine the search query, ensuring accurate domain information for further enrichment.
Step 5 - Enrich CRM#
Enrich and map client information to the CRM
Still within the group, use an enrichment action on the companies object of an enrichment integration to retrieve details such as company size and other relevant attributes. This step provides valuable data for your prospecting efforts.
Next, use a variables node to gather the information collected so far, such as the client's name, domain, and size. Map these details to the relevant fields in your CRM or outreach tool. This data can be used to personalize and enhance your email marketing campaigns.
By following these steps, you can leverage the names of a prospect's clients to boost your email marketing conversion rates.
