Customer Service Automation
AT&T needed to route customers more accurately, increase autonomous issue containment, and make virtual assistants feel more personal instead of forcing users through repetitive phone trees and stateless support interactions.
Reported impact
AT&T increased autonomous containment and made virtual-assistant interactions more continuous and helpful, reducing the friction customers feel when seeking support or sales help.
AT&T combined BigQuery with Gemini Enterprise for Customer Experience to build a more contextual support stack across voice and chat channels. BigQuery analyzes customer history so the contact center can route each person to the right path without relying on rigid menus, improving front-end containment before a conversation even begins. Once the interaction starts, Gemini Enterprise for Customer Experience handles more complex issues naturally and retains up to sixty days of conversational memory, which means customers do not have to restate context every time they return or move between support scenarios. This memory layer also helps AT&T use the same conversational foundation for sales, service, and troubleshooting. The result is a support experience that resolves more calls autonomously, routes customers faster, and feels more continuous and personalized than traditional telecom-service flows.
Customer history and intent signals are analyzed in BigQuery, which improves initial routing. Gemini Enterprise for Customer Experience then handles the conversation, retains memory across interactions, and returns more personalized resolutions in voice and chat channels.
AT&T uses BigQuery and Gemini Enterprise for Customer Experience to deploy highly contextual AI agents, resolving 20% more calls autonomously.
BigQuery provides the intelligence AT&T needs to bypass rigid menus and direct users to the right solution
Gemini Enterprise for Customer Experience allows us to keep 60 days worth of memory.
the conversation ... handles complex issues naturally
we're about 20% better containment at the front end of the call.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Google Cloud Sample Archived · Aug 29, 2026 Bell Canada Bell needed to move beyond rigid support decision trees and fragmented agent tooling so it could resolve more customer inquiries autonomously while still personalizing interactions across chat, voice, and human-assisted… Handled 16M+ chat interactions, with over half resolved by AI Agent Assist · BigQuery · Gemini for customer experience Google Cloud Sample Archived · Aug 5, 2026 Cox Cox needed to move beyond traditional IVR flows so customers could explain issues naturally, resolve more requests at first contact, and shift routine support into digital channels without losing context when a live… 10% improvement in customer resolution within its first week Gemini Enterprise for Customer Experience Google Cloud Sample Archived · Jul 23, 2026 TELUS TELUS needed to unify siloed customer and network data so teams could trust the same foundation for generative AI, launch new services faster, and scale agentic platforms without each business unit building its own… 90% of AI model traffic runs through Gemini Enterprise Agent Platform BigQuery · BigQuery Analytics Hub · Cloud SQL 