Revolutionizing Client Inquiry Management with Gen-AI
summary
Claims a lightweight, production-ready system that uses few-shot prompting and an LLM endpoint to tag inquiries by sentiment and high/medium/low urgency, deployed inside BlackRock’s Aladdin workflow. Reports a business impact: 35% fewer monthly escalations and regional drops from seven to two weekly escalations, with measured coverage above 95% for prioritized cases. Implementation emphasizes easy deployment, minimal labeled data, and iterative prompt tuning.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 1:03Gen-AI for client inquiries
- 2:10Client inquiry challenges
- 3:34Sentiment and urgency classification
- 4:58Design simplicity
- 6:43Detection nuances
- 8:28Business impact
- 9:35Q&A
- 10:19Model training
- 11:01Model performance
- 12:28Traditional model comparison
- 13:09Why Gen-AI won
- 14:11Handling urgency claims
- 14:54Ticket prioritization
- 17:01Closing remarks
related talks
16mMulti-Agent Intelligence for Next-Gen Insights
28mUnlocking the power of GenAI
36mAI Agents in Automation | 3 Real Production Cases with ROI
51mTransforming Banking with Advanced AI: GenAI, RAG, and Multi-Agent Systems
16mTransform customer experience with an array of AI agents
49mHow to be an AI First company
41mMaximize the Effectiveness of Your Customer Relationships
30mAI Sales Coaching | Agentic AI Replacing Manual Feedback