OVERVIEW

Sybill identified an opportunity to help sales reps speed up one of the most repetitive parts of their workflow — writing follow-up emails after meetings.

Although reps were already using tools like ChatGPT and Claude to draft emails, the experience was fragmented and disconnected from their workflow. We saw an opportunity to turn AI email generation into a dedicated workflow directly integrated with meeting and CRM context.

I led the end-to-end design of this new AI-powered email experience, helping expand Sybill from an AI meeting notetaker into a more embedded AI assistant for sales workflows.

• My role
• Team
• Duration

IMPACT

<aside> 🎉 27% increase in workflow adoption Increased daily usage compared to the previous AI chat-based workflow

</aside>

<aside> 🎉 Over half of the emails sent with minimal or no edits AI-generated emails became more context-rich and production-ready within reps’ existing workflow

</aside>

<aside> 🎉

Increased AE workflow efficiency

Reduced time taken on writing emails from 15-20min → 2-5 min

</aside>

DISCOVERY

Understand user needs around AI-powered email workflows

To learn about how reps write follow-up emails today, I conducted research across multiple channels:

• 10 one-on-one interviews with sales reps
• 30+ Sybill AI chats contained email drafting
• Understanding market and needs from customer success and sales team

From user research, I identified not only what was breaking in the current flow but also the broader email tasks AEs wanted AI to support. After syncing with the PM, we prioritized fixing the most immediate drop-off issues first—improving the UI/UX and refining AI output—before exploring additional email types and workflows once we had stronger validation.

Other themes & problems discovered from research

Key research findings:

<aside> 💡 Reps write different emails across the sales cycle Follow-ups, re-engagements, replies, scheduling, and deal updates.

</aside>

<aside> 💡 Sending emails is high-stakes Reps wanted control over editing, formatting, and delivery in Gmail/Outlook.

</aside>

<aside> 💡 Generic AI chat wasn’t the right interaction model

Users could generate emails through AI chat, but most didn’t think to use it that way.

</aside>