MicrosoftLive sourceProductionEvidence: High75/100

MasOrange streamlines telecom customer service with AI-powered chatbot

MasOrange, a major Spanish telecommunications operator, faced mounting customer service challenges due to high call volumes and lengthy invoice-related queries. In response, PwC Spain and MasOrange developed a sophisticated AI-powered conversational agent using Microsoft Azure OpenAI services, deployed via WhatsApp. The solution automated invoice explanations leveraging Azure AI Search for Retrieval-Augmented Generation and Form Recognizer for invoice parsing, greatly reducing manual intervention. The chatbot continuously learned from interactions, optimizing responses while integrating seamlessly with existing customer service workflows. This innovative project was executed in multiple phases: knowledge base creation, invoice data extraction, prompt engineering, and iterative optimization. By improving response speed and accuracy, MasOrange could alleviate pressure on call centers, focus staff on complex issues, and enhance customer loyalty through a superior service experience.

Organization
MasOrange
Industry
Tech & Comms
Location
Spain
Published
January 2024
Why do we believe this?Outcome claims, sources, and evidence checks

Normalized claim

Quantified impact: 30%

pwc.esJan 1, 2024Case studyInferred claimHigh evidence strength

Avoided over 30% of unnecessary call center queries.

Last evidence check: Jun 1, 2026

Why do we believe this deployment?Customer identity, provider attribution, maturity, and source checks
Customer
MasOrange
Provider
Microsoft
Maturity
Production
Linked source
pwc.es

In response, PwC Spain and MasOrange developed a sophisticated AI-powered conversational agent using Microsoft Azure OpenAI services, deployed via WhatsApp

Customer identity supportedSource describes one deploymentMaturity supported

Primary read

Use case focus

Showing 2 of 2

  • 1Automated Invoice Query Resolution via Conversational AI
  • 2Chatbot-Driven Customer Self-Service
  • Developed a WhatsApp-integrated conversational chatbot using Microsoft Azure OpenAI.
  • Azure Form Recognizer processed and extracted data from invoices.
  • Azure AI Search and Retrieval-Augmented Generation techniques enabled high accuracy in information retrieval.
  • Iterative chatbot improvement based on real user interactions.
Architecture

Customer queries on WhatsApp trigger the Azure OpenAI chatbot. The bot retrieves invoice-related information via Azure AI Search, uses Azure Form Recognizer to extract invoice data, generates explanations using Retrieval-Augmented Generation, and adapts over time through iterative learning.

Implementation partners1
Sources & evidence1
Evidence: High75/100Evidence strength
  • Customer explicitly identified
  • Deployment status explicitly supported
  • Primary source available
  • Quantified outcome available
  • Technical implementation details available
  • Recent evidence check available
  • Last evidence check: Jun 1, 2026.
Live sourceStill referenced

The case's original source is still reachable.

  • Cited source last checked Jun 1, 2026 — ok (0/1 broken).

Measures whether this deployment's public evidence persists — not whether the system is still in production.

Type: Case StudyPublished: Jan 1, 2024Publisher: pwc.esEvidence: PrimaryConfidence: High

AI-generated summary. Verify important details with the linked sources before relying on this case.

Explore related AI use cases

Was this useful?

Community

Comments

No published comments yet.

Similar cases