How We Built an Engagement Scoring System Using Census AI Columns

Find out how to build an automation that assigns an engagement score, highlights areas of interest for that account, and generates talking points for reps to access right from Salesforce. Bonus: We'll also discuss which model worked best for this and why. Learn more about how the LLMs measure up here.

So What Are We Actually Trying to Solve Here?

Let's be real about what understanding customer engagement usually involves:

• Manually tracking multiple engagement touchpoints
• Figuring out which activities actually matter
• Creating engagement scores that make sense
• Writing summaries that sales will actually read
• Getting all of this into Salesforce in a usable format
• And probably maintaining yet another spreadsheet

But here's where it gets interesting - we built an automated engagement scoring system using Census AI columns that your sales team can start using today. Let's dive into how!

The Solution: Census AI Columns

See it in action: If you're more of a video person than a reader, take a look at this quick guide on creating engagement scores using LLM. 👇

For the readers, here's how to set it up:

Step 1: Initial Setup

Before diving in, make sure you have:

1. Connected your data warehouse as a source
2. Connected Salesforce as a destination
3. Set up your AI integration

Step 2: Create Your Dataset

Navigate to Datasets in Census and create a query that pulls:

• Account information
• Engagement activities (ebook downloads, pricing page views, free trials)
• Asset names for each activity
• Lightweight engagement scores for each activity

Pro tip: While you can bring in all historical data, we recommend limiting to the last 90 days to keep insights relevant for your sales team.

Here's the SQL we used to pull this dataset:

Step 3: Create Your AI Column

This is where the magic happens! Click 'AI Enrich and Enhance' in the right corner, then 'GPT' to create your prompt. We've broken our prompt into three key parts:

1. Basic Instructions

• • Create a total engagement score (1-10)
  • Review all engagement data
  • Generate a summary
  • Set clear guidelines (e.g., scores 6-10 indicate high engagement)

2. Output Structure

• • Specify exactly how you want the data formatted
  • Request top 3 assets with highest engagement scores
  • Include color coding for visual clarity

3. Sample Output

• • Show GPT what "good" looks like
  • Demonstrate the desired format
  • Make it easily readable for the sales team

Pro tip: Set your output type to 'string' for the full summary, or 'number' if you just want the engagement score. You can also add default values for accounts with no data.

Here's the prompt we used:

Step 4: Set Up the Sync

Now let's get this data into Salesforce:

1. Go to Syncs and create a new sync
2. Select your source (engagement dataset) and destination (Salesforce Account)
3. Choose "Update Only" sync behavior
4. Map your engagement score and summary fields
5. Set your sync schedule

Real Results at Census

When we sync this to Salesforce, our sales team gets:

• Clear engagement scores
• Explanation of why each account got its score
• Highlighted pages/assets the company engaged with
• Specific talking points for hyper personalized outreach

Which Model do we prefer?

Census offers connections to GPT, Claude and Gemini. And while we tested this across all of them, our verdict is that GPT makes the most sense for this use case.

• Both GPT and Claude produced excellent results - Claude was slightly stronger in its writing
• However, at about 7x the cost, we can't justify using Claude for this internally facing use case. We still love it for anything customer facing or fully automated though!

Ready to Get Started?

Whether you're trying to understand engagement patterns, prioritize accounts, or enable more personalized outreach, Census's AI Columns makes it happen in minutes.

Want to try it yourself? Check out our documentation at docs.getcensus.com for detailed setup instructions and our complete AI Columns recipe book for more use cases. Or reach out to us at support@getcensus.com - we'd love to help you supercharge your sales engagement!

Ready to implement engagement scoring in your organization? Check out our documentation or reach out to our team for personalized guidance.