Running AI you can control - Sovereign AI for networks, data and decisions

Chair: Sanjay Mewada, Analyst & Chief Research Officer, Recon Analytics

From 1.1 million weekly conversations to actionable insights: How AT&T built an enterprise-scale transcript intelligence platform 

• Enterprise AI at scale requires purpose-built architecture—AT&T replaced vendor platforms with an internal solution processing 1.1M+ weekly interactions with significant cost savings 
• Multi-model AI architecture dramatically reduces token costs while maintaining quality at massive scale 
• Cross-functional collaboration accelerates delivery—6-month timeline vs typical enterprise cycles 

Bo Gu, Director of Data Science, AT&T 

Fireside chat: Beyond the chatbot: What agentic CX actually delivered for operators 

Every operator has deployed a bot. Most have created a new silo. This panel deals in results, not roadmaps: what changes when agents share context across discovery, commerce and service instead of operating as disconnected "AI islands." Operators share deployment reality — the guardrails, the grounding in CRM/billing data, and the KPIs that moved.  

• Proof points on the table: 40% increase in sales through agent-productivity tooling and over $2.3M in annual savings from transformed self-service 
• Why context continuity from search to service — not bot quality — is the actual differentiator 
• Deploying production agents in days via low-code studios and pre-built templates, without handing your customer relationship to a third party 
• Governance, data sovereignty and the compliance floor for regulated CX 

Niaz Tadayyon, Customer Experience Lead, Google Cloud
Jeff Dixon VP, Digital CX, AT&T