Turning Vendor Chaos into Answers: How Xelix Built an AI Helpdesk

Guests

• Claire Smid — AI Engineer, Xelix
• Emilija Gransaull — Back-End Tech Lead, Xelix
• Talal A. — Product Manager, Xelix

Key Takeaways

• Start narrow to win: pick high-volume, high-cost requests (invoice status & reminders).
• Enrichment > magic: accurate replies come from great retrieval/matching, not just a bigger LLM.
• Design for adoption: familiar inbox view helps onboarding, but a ticket-first UI unlocks AI features.
• Measure outcomes, not vibes: track “messages sent from Helpdesk”, % auto-resolved.
• Confidence builds trust: show match quality and response confidence so humans know when to edit.

0:00 Meet the Team: Claire, Emilija, and Talal 00:36 Introduction to Xelix and Its Products 01:08 Understanding Accounts Payable Teams 01:37 Help Desk Product Overview 03:11 Challenges Faced by Accounts Payable Teams 04:03 AI Integration in Help Desk 05:47 Automating Reconciliation Requests 07:45 Development Methodology: Carpaccio 09:11 Prototyping and Beta Testing 12:00 Manual Tagging and Data Collection 16:39 Focusing on High-Impact Use Cases 18:55 User Experience and Interface Design 24:56 Pipeline Architecture and Email Processing 28:21 Data Enrichment Challenges 29:04 Handling Vendor Identification 33:33 Email Thread Management 36:15 Generating Accurate Responses 40:48 Evaluating System Performance 49:20 Future Developments and Goals