← Back to Italgas replaces its contact center IVR with a conversational AI agent built on Databricks

Source proof for Italgas replaces its contact center IVR with a conversational AI agent built on Databricks

Source-bound proof

Verified source excerpts for every supported field

Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.

11 fields supported

Title

Italgas replaces its contact center IVR with a conversational AI agent built on Databricks

derived · medium
…0 calls dropped during navigation and 10,000 calls resolved through automation. Thus, the IVR was replaced with a conversational AI agent built on Databricks. The AI Gateway provides the backbone for real-time agent serving, while MLFlow…
…r for GenAI and defined measurable KPIs Return to all sessions Session Speakers Delli, Serena / Head of Data&AI Architectures Bludigit, Italgas Nicola Giorcelli / Lead Data&AI Cluster Reply Follow Home Databricks.com Event…

Description

At Europe's largest gas distributor, the customer contact center handled approximately 120,000 calls per month using a traditional IVR system, with 22,000 calls dropped during navigation and 10,000 calls resolved through automation. The IVR was replaced with a conversational AI agent built on Databricks, which interacts with callers in natural language, gathers contextual information and routes users to the correct resolution path. The session abstract reports a 50% reduction in call drops during navigation and a 44% increase in automated resolution.

derived · high
…ks Apps, Lakebase Skill Level Intermediate At Europe’s largest gas distributor, the customer contact center handled approximately 120,000 calls per month using a traditional IVR system. This resulted in 22,000 calls dropped during navigation and 10,000 calls resolv…
…extual information, and accurately routes users to the correct resolution path. The solution reduced call drops during navigation by 50% and increased automated resolution by 44%. This session shares how we designed and operationalized a production-grade conv…

Company

Italgas

quote · medium
…r for GenAI and defined measurable KPIs Return to all sessions Session Speakers Delli, Serena / Head of Data&AI Architectures Bludigit, Italgas Nicola Giorcelli / Lead Data&AI Cluster Reply Follow Home Databricks.com Event…

Industry

Energy

classification · high
…rise Scale Overview Experience In Person Track Artificial Intelligence & Agents Industry Energy & Utilities, Communications, Media & Entertainment, Retail & Consumer Goods Technologies Unity Catalog, Databricks Apps, Lakebase Skill Level Intermediate…

Problem

At Europe's largest gas distributor, the customer contact center handled approximately 120,000 calls per month using a traditional IVR system, which resulted in 22,000 calls dropped during navigation and only 10,000 calls resolved through automation.

derived · high
…r handled approximately 120,000 calls per month using a traditional IVR system. This resulted in 22,000 calls dropped during navigation and 10,000 calls resolved through automation. Thus, the IVR was replaced with a conversational AI agent built on Databricks.…

Solution

The IVR was replaced with a conversational AI agent built on Databricks. The AI Gateway provides the backbone for real-time agent serving while MLFlow tracks performance, data is securely accessed from Unity Catalog, and the tools are served via MCP through a Databricks app. The agent interacts with callers in natural language, gathers contextual information, and routes users to the correct resolution path.

derived · high
…Thus, the IVR was replaced with a conversational AI agent built on Databricks. The AI Gateway provides the backbone for real-time agent serving, while MLFlow tracks performance. Data is securely accessed from Unity Catalog, while the tools are served via MCP through a Databricks app. The agent interacts with callers in natural language, gathers contextual inform…
…rom Unity Catalog, while the tools are served via MCP through a Databricks app. The agent interacts with callers in natural language, gathers contextual information, and accurately routes users to the correct resolution path. The solution reduced call drops during navigation by 50% and increased automate…

Business value

According to the session abstract, the solution reduced call drops during navigation by 50% and increased automated resolution by 44%.

derived · high
…extual information, and accurately routes users to the correct resolution path. The solution reduced call drops during navigation by 50% and increased automated resolution by 44%. This session shares how we designed and operationalized a production-grade conv…

AI capabilities

Conversational AI, Agentic AI

classification · high
…rom Unity Catalog, while the tools are served via MCP through a Databricks app. The agent interacts with callers in natural language, gathers contextual information, and accurately routes users to the correct res…

Technology

AI Gateway, MLflow, Unity Catalog, Databricks Apps

classification · high
…rgy & Utilities, Communications, Media & Entertainment, Retail & Consumer Goods Technologies Unity Catalog, Databricks Apps, Lakebase Skill Level Intermediate At Europe’s largest gas distributor, the customer cont…
…Thus, the IVR was replaced with a conversational AI agent built on Databricks. The AI Gateway provides the backbone for real-time agent serving, while MLFlow tracks performance. Data is securely accessed from Unity Catalog, while the tools are served via MC…

Headline outcome

derived · high
…extual information, and accurately routes users to the correct resolution path. The solution reduced call drops during navigation by 50% and increased automated resolution by 44%. This session shares how we designed and operationalized a production-grade conv…

Use case type

Conversational assistant

classification · high
…n and 10,000 calls resolved through automation. Thus, the IVR was replaced with a conversational AI agent built on Databricks. The AI Gateway provides the backbone for real-time agent serving, while MLFlow…
Capture details
Captured
10 Oct 2026, 06:02 UTC
Extractor
fetch-strip@1
Snapshot hash
ed54915c48799f100e8203bb0181a8f27049b7b5cf3aadae37cefbefa22aa5a5