SmartMail AI helps sales reps create personalized emails in seconds using D&B data. As UX Lead, I led the feature from concept to launch.
Sales reps were spending more time gathering context than reaching out to prospects.
D&B Hoovers had the data, but reps still had to piece together context across multiple tools before writing an email. Preparing a single message could take up to 20 minutes, slowing outreach and reducing how often D&B data was used.
Used 4+ tools to prepare one email
Reps moved between Hoovers, LinkedIn, news sites, and CRM tools to gather the context they needed.
Up to 20 minutes of prep per email
Gathering and copying company and contact information manually made outreach slow.
D&B contact data was underused
Without an easy way to bring D&B data into the workflow, reps often defaulted to generic outreach.
Email personalization was just as important to reps as the AI writing the email.
What I found
Sales reps wanted control over how each email sounded and what it focused on. Tone, length, email type, and product positioning changed with every opportunity.
They also needed the message to reflect their own context, not just the data already available in Hoovers.
The constraint
The AI model knew the account and contact data, but not what the rep wanted to sell or emphasize in that moment. Without that context, the output could feel generic.
I needed to give the model enough context to create a useful draft while keeping the experience simple and giving reps control over the final message.
"I don't want the same email for every company. Sometimes I want to keep it light and generic, sometimes I need to be specific about what we're offering."
Sales rep, interview participant
"I have my own way of writing. I want to decide the tone and how I ask for the next step. I don't want the AI deciding that for me."
Sales rep, interview participant
Sales reps needed control over tone and style.
Research made one thing clear: reps wanted control over how each email sounded. Introduction or follow-up. Formal or conversational.
I introduced controls for tone, length, email type, and language so the AI could handle the draft while the rep shaped the message.
Giving the AI context made every email more relevant.
Three inputs gave the AI the business context it needed: what the rep's company does, what they were selling, and how they wanted to close.
That context helped the AI generate drafts that better matched the opportunity.
Giving reps more control also introduced risk.
Open text inputs could send inappropriate or overly long content to the model. I designed two safeguards to keep inputs within clear boundaries.
Content filtering
Inappropriate content is detected and blocked before it reaches the model.
Character limit
Input is capped at 1,000 characters.
Creating an AI identity that felt familiar.
Because SmartMail was one of Hoovers' first generative AI experiences, I worked with branding and legal to establish a recognizable AI identity that could scale across future AI features.
Final Designs
Providing context to the model
AI guardrails triggered to prevent misuse
Character limit to prevent the model from being overloaded
Enabling users to customize the AI generated email to match their preferred style
Press Coverage
"JACKSONVILLE, Fla. (BUSINESS WIRE) Dun & Bradstreet (NYSE: DNB), a leading global provider of business decisioning data and analytics, today announced SmartMail AI."
Dun & Bradstreet · Business Wire via Nasdaq, 2024
Read press release ↗Takeaways
AI features work best when they live inside the user's workflow.
SmartMail worked because it met reps where they already worked. The email generator wasn't a separate destination. It appeared at the moment they needed it.
That placement was as important as the feature itself.
Designing for misuse early makes the experience better for everyone.
Thinking through misuse before launch helped us design guardrails that protected the experience without adding friction for everyone else.
SmartMail shaped how I think about AI experiences: meet users in their workflow, give them meaningful control, and design the boundaries early.