Using AI to Qualify and Sort Sales Leads

Not all leads are equal and AI is perfect for doing background research on each one to ensure you're focusing on the most viable leads first.

January 19th 2024 Max Brodeur-Urbas
Max Brodeur-Urbas
Co-Founder/CEO
Using AI to Qualify and Sort Sales Leads

Let’s have AI qualify your leads in a hyper-custom way so you can focus on the work that matters.

I'm going to show you how AI can loop through each of your prospective leads, scrape their company website for more info and then assign them a score based on how closely they match your ideal customer profile. You’ll be able to quickly narrow down 10,000 leads to a few 100 strong ones in minutes.

How do we do it

This automation is a 5 step process. You input a list of all the companies you want to target (ex: https://www.agenthub.dev/, https://zapier.com/ etc.), we load more info about their organization (country, size, revenue), scrape their websites, summarize what they’re about and have AI score them from 0-100 based on your custom needs.

This data then goes back into the Sheet/CRM/database from which it came and you can start focusing on selling to your best leads first.

Step 1. Intake Your Leads

We’ll start off by ingesting your leads from wherever you store them. For the sake of this demo I’m going to be reading leads from a Google Sheet.

Each lead contains information like the person’s name, their company URL, their email etc. We’re going to extract only the company URL column from

Step 2. Enrich Your Leads

It’s quite possible that you don’t have all the info about this company that you’d want. Perhaps you’d want to know their company size, annual revenue, country etc.

Let’s use the ‘Enrich Company Info’ node on AgentHub to get that information. Using this node you can pass in company URLs and select the info you want about them.

This will be useful in step 4 because one of our criteria is company size. We only want to sell to extremely large businesses so their size will play a key role in the score we assign them.

Step 3. Scrape their websites and Summarize what they’re about

Now that we’ve loaded in these leads, we need to find out what the company is about. What they do, what their product is, what market they’re targeting etc.

Most of this information is located on their website so we’ll scrape that with a Web Scraping node on AgentHub.

The output of this node will be all of the text on their website. This is way too much information for our next step to handle so let’s boil it down a bit.

We’re going to summarize the content from their website so we can have an overview of their company in a nicely packaged, digestible paragraph.

Step 4. Assign them a score

Scoring is one of my favorite steps as it was almost completely impossible before the recent AI developments. We can now describe our criteria for the perfect candidate with simple language and have the AI apply those criteria to each of the leads during the grading process.

The output of this step is a score from 0-100 and a justification for that score. If they meet all of our criteria they’ll have a great score, if they miss some the AI will be able to reason about what score they merit and why. Similar to a human carefully reading through thousands of leads and spending time considering how highly to rank them given a grading rubric.

You'll notice in this image that I've inputted criteria for the AI to use during scoring. This is where you can get creative and customize the automation based on your needs! If you need a

Step 5. Output those results

Now we have an enriched and scored sales lead ready to put back into the tracking system we’ve been using. Like I mentioned before, we’re using a Google Sheet for the sake of this demo so we’ll be adding a row to our sheet for each enriched lead.

Here is a link to the automation I’ve described building in this blog post. It is infinitely customizable to your needs with no code.

Reach Out!

If you want to chat more about how AgentHub can automate parts of your business send me an email at max@agenthub.dev and we can book some time to chat!

We're always interested in building new features based on user needs so even if the platform doesn't do what you want yet, send us an email and give us 24 hours. We'll try and make it happen.

Related Posts

Here is some more content related to AgentHub, LLMs and automation. Enjoy!

Ready to Automate?

Start using AgentHub today.

Automate your complex business processes without writing a single line of code. No credit card required.