Can AI Face Your (Potential) Customers?
summary
Built an on‑premises contact‑center pipeline that turns audio into action: speech‑to‑text, text cleaning, classification, data extraction and validation, then pushes insights to PowerBI/Teams and fills forms in real time. Claims matched Azure STT in two weeks and beat AWS in two months and now serves Baltic/Nordic customers handling ~25,000 calls/day signals. Uses custom models (no ChatGPT or Whisper), freelancer‑annotated accents, domain and client‑specific jargons, on‑premises, no internet required, and exposes 100+ custom datapoints for alerts and upsell.
AI-written summary · about
chapters (10)
- 0:00AI in contact centers
- 1:04IBM Watson to East Lucid AI
- 3:31AI for sales and support
- 5:56Call center pain points
- 12:29AI solution architecture
- 16:30Speech-to-text for Baltic languages
- 24:23Call conversation insights
- 34:02Live AI form-filling demo
- 47:26GDPR and data protection
- 50:59Q&A
related talks
51mCan AI Face Your (Potential) Customers?
31mBuild AI-assisted communication workflows for customer engagement
39mPotencie su centro de contacto con la inteligencia artificial
46mBuilding Copilots - key lessons and best practices
43mAgentic AI with Amazon Connect
11mMedia Interview
30mAI Driven Transformation in Contact Centers: Enhancing Customer Experience
49mHow to be an AI First company