📚 Convert email leads to CRM entries with AI

Reading Time: 5 minutes

Hello AI Enthusiast,

Today we're sharing how we use AI and an automation platform to streamline how we handle incoming leads at AI Academy. We'll show you how we convert unstructured emails into organized CRM entries.

The Problem

Imagine receiving numerous partnership requests weekly. Manually entering each detail into your CRM is time-consuming and error-prone. At AI Academy, we faced this challenge with incoming collaboration emails. We needed a way to efficiently process these leads without sacrificing accuracy. This is where our AI-powered automation comes in, streamlining the process and reducing manual data entry.

How We Do It: A Step-by-Step Guide

Before building our automation, we always test our prompt in ChatGPT, or other models. Only when satisfied with the outputs do we create the workflow.

1) Set up ChatGPT with a clear, specific prompt.

Our prompt extracts key information from emails:

• Sender details

• Company information

• Main request

The example in our prompt looks like this for a specific reason: it's formatted as JSON. We'll explain later what JSON is and why we use it.

2) Build the automation workflow using Make.com or similar

Our workflow uses four main modules:

a. Gmail Module: Monitors a specific email folder

Example email:

• Subject: Partnership Opportunity with OpenAI

• From: Sam Altman [[email protected]]

• To: [email protected]

• Date: Jul 9, 2024, 02:35 AM

"Dear AI Academy Team,

My name is Sam Altman, the OpenAI CEO. We are a leading AI research and deployment company with over 1,000 employees. We are impressed with your training programs and would like to explore a partnership to educate users on maximizing the benefits of our AI technologies. Could we schedule a meeting to discuss this further? Looking forward to your response.

Best regards,

Sam Altman CEO"

b. OpenAI Module: ChatGPT analyzes the email and returns structured data in JSON format.

c. JSON Module: Parses the structured data.

JSON (JavaScript Object Notation) is a simple way to organize data in a format that's easy for both humans and machines to read. In our case, it helps by:

• Structuring the information consistently

• Making it easy to transfer data between different systems (like from ChatGPT to our spreadsheet)

This structured format acts as a bridge between ChatGPT's analysis and our spreadsheet, ensuring each piece of information finds its proper place.

d. Google Sheets Module: Adds parsed data (image below) to our spreadsheet.

Note: We use Google Sheets instead of a CRM to simplify things for this example.

Here is the data extracted from the email into our spreadsheet:

By using this method, we transform a potentially time-consuming manual task into an efficient, automated process that maintains accuracy and consistency in our lead management.

Your Turn

While our full automation might be complex, you can start small:

1. Manual Extraction: Choose an important email you've received recently. Without AI, identify and list the key information (like sender, company, main request). This helps you understand what data is most relevant to you.

2. AI-Assisted Analysis: Now, use ChatGPT to analyze the same email. Give it a simple prompt like "Summarize the key points of this email." Compare its output to your manual extraction. What did it catch that you missed, or vice versa?

3. Spreadsheet Organization: Create a basic spreadsheet with columns for the key information you identified. Manually fill it out for 5-10 emails. This exercise helps you visualize how automated data extraction could streamline your workflow.

Even these simple steps can help you think about your workflow differently.

Want to get even more practical? Explore hands-on AI learning with AI Academy:

• Generative AI Project Bootcamp: Create AI prototypes to solve real business problems.

• Corporate Training: Tailored AI training for your team.

• Practical Introduction to ChatGPT: Free course on effectively using ChatGPT.

We'll be back with more AI tips soon!