> Markdown version of [/videos/2010-conversational-ai-meets-ms-data-agents-to-improve-customer-experience?t=244](https://www.wearedevelopers.com/videos/2010-conversational-ai-meets-ms-data-agents-to-improve-customer-experience?t=244). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Conversational AI meets MS data agents to improve customer experience

Stop losing subscribers to ignored emails. Learn how combining Microsoft data agents with conversational AI transforms passive analytics into proactive, intelligent voice calls that reduce churn.

- **Speakers:** [Alexandra Mihai](https://www.wearedevelopers.com/@alexandra-mihai), [Marina Stefan](https://www.wearedevelopers.com/@marina-stefan), [Tomasz Kacala](https://www.wearedevelopers.com/@tomasz-kacala)
- **Event:** World Congress 2026 Europe - Virtual Stage
- **Published:** July 2, 2026
- **Duration:** 23:36
- **URL:** https://www.wearedevelopers.com/videos/2010-conversational-ai-meets-ms-data-agents-to-improve-customer-experience

## Summary

Subscription-based businesses often struggle with revenue loss and churn due to passive renewal notifications via email or SMS. Because traditional communication is "reactive but not intelligent," organizations need a proactive, automated approach to customer engagement. By combining Microsoft data agents with conversational AI, businesses can transform passive analytics into real-time, dynamic voice interactions. In this closed-loop architecture, subscription data acts as the signal, AI serves as the decision layer, and voice becomes the primary customer experience channel. This solution leverages a powerful stack to build an end-to-end intelligent workflow. Microsoft Fabric provides a centralized lakehouse foundation, while the Fabric Data Agent abstracts complex queries, allowing systems to retrieve structured contextual data using natural language intents. Azure AI Foundry acts as the orchestration brain, evaluating business conditions and deciding the next action path. Once a trigger condition like an expiring subscription is met, Azure Logic Apps executes the workflow and securely passes the context to ElevenLabs. Using its expressive V3 model, ElevenLabs conducts a natural, context-aware phone call to negotiate renewals or offer dynamic discounts. The system operates as a seamless loop: after the AI negotiates a renewal, Logic Apps automatically posts the conversation summary, sentiment analysis, and updated subscription details back to the Fabric lakehouse for visualization in Power BI. This scalable pattern drastically reduces churn risk and increases operational efficiency by engaging users directly rather than waiting for them to react to a static reminder. Ultimately, this architecture proves that "every data set can become a conversation," establishing conversational AI as a highly effective, production-ready layer for modern customer experience.

**Keywords:** subscription renewal automation, conversational AI customer experience, microsoft fabric lakehouse, fabric data agent, azure AI foundry orchestration, azure logic apps integration, elevenlabs voice AI, churn risk reduction, closed-loop data architecture, automated outbound voice calls, real-time customer engagement, enterprise data orchestration, REST API tool integration, dynamic context-aware interactions

## Chapters

1. **Overcoming reactive customer engagement with conversational AI** (00:02) — Proactive voice interactions replace passive email or SMS notifications for subscription renewals.
1. **End-to-end architecture for data-driven voice agents** (02:06) — An orchestration of Microsoft Fabric, Azure AI Foundry, Logic Apps, and ElevenLabs enables intelligent interactions.
1. **Structuring data access with Fabric Data Agent** (04:04) — Abstraction layers simplify how AI systems interact with structured lakehouse data using natural language intent.
1. **Orchestrating decisions using Azure AI Foundry** (04:56) — The central intelligence layer interprets customer context and evaluates business conditions to determine action paths.
1. **Executing reliable actions with Azure Logic Apps** (05:36) — The action layer seamlessly triggers workflows to connect systems and initiate the voice interaction.
1. **Delivering dynamic voice interactions via ElevenLabs** (06:34) — Context-aware conversational AI turns automated reminders into responsive, natural voice engagements.
1. **Understanding the closed-loop architecture for proactive engagement** (07:17) — Data updates trigger condition detection, retrieving context, calling APIs, and capturing conversation outcomes.
1. **Live demonstration of automated subscription renewal calls** (08:01) — A real-time system queries expiring subscriptions and initiates interactive AI phone calls to test customers.
1. **Exploring the Microsoft Fabric workspace foundation** (14:13) — Engineers can analyze conversation results and stored outputs directly through the Fabric Data Agent interface.
1. **Configuring AI Foundry instructions and Logic App triggers** (17:03) — System prompts instruct the orchestrator to call the Fabric agent and pass variables via HTTP POST requests.
1. **Capturing conversation outcomes with ElevenLabs tool webhooks** (18:54) — An automated post-call tool sends collected customer intent and sentiment data back into the lakehouse.
1. **Evaluating the business impact of proactive conversational AI** (21:23) — Automated voice engagements increase renewal rates and transform static enterprise datasets into interactive channels.

## Related Moments

- [Introduction to Microsoft Fabric and data agents](https://www.wearedevelopers.com/videos/1547-data-analytics-with-microsoft-fabric-end-to-end-use-case-with-data-agents) (from "Data Analytics with Microsoft Fabric: End-to-End Use Case with Data Agents")
- [Modernizing customer support with AI and multi-channel handoffs](https://www.wearedevelopers.com/videos/1801-api-first-how-twilio-designs-for-developers-justin-kitagawa-twilio) (from "API‑First: How Twilio Designs for Developers - Justin Kitagawa (Twilio)")
- [Summarizing developer experience and artificial intelligence companions](https://www.wearedevelopers.com/videos/884-forget-developer-platforms-think-developer-productivity) (from "Forget Developer Platforms, Think Developer Productivity!")
- [Applying context engineering across the full software lifecycle](https://www.wearedevelopers.com/videos/100256-can-this-elephant-dance-ibm-bob-and-the-future-of-ai-first-software-development) (from "Can This Elephant Dance? IBM Bob and the Future of AI-First Software Development")
- [Modernizing edge experiences for agentic AI architectures](https://www.wearedevelopers.com/videos/100234-20-billion-requests-a-week-upgrading-twilio-s-api-gateway-at-scale) (from "20 billion requests a week: Upgrading Twilio's API gateway at scale")
- [Building autonomous functions with conversational agent frameworks](https://www.wearedevelopers.com/videos/1624-30-powerful-aws-hacks-in-just-30-minutes-boost-your-developer-productivity) (from "30 powerful AWS hacks in just 30 minutes: Boost your developer productivity")

## Related Articles

- [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)
- [Exploring AI: Opportunities and Risks for Developers](https://www.wearedevelopers.com/magazine/522-exploring-ai-opportunities-and-risks-for-developers)
- [Dev Digest 132 - Binging WADFlix?](https://www.wearedevelopers.com/magazine/473-dev-digest-132-binging-wadflix)

## Related Jobs

- [Principal Field Architect - AI Agents](https://www.wearedevelopers.com/jobs/ext/1442858-principal-field-architect-ai-agents) at **Twilio**
- [Twilio's next Senior Principal Field Architect - AI Agents](https://www.wearedevelopers.com/jobs/ext/1487390-twilio-s-next-senior-principal-field-architect-ai-agents) at **Twilio**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/588393-machine-learning-engineer) at **Twilio**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/2023929-machine-learning-engineer) at **TWILIO**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1355348-machine-learning-engineer) at **TWILIO**