Ericsson demo: Stopping silent degradation with autonomous multi-agent AI
By James Pearce
Nov 9, 2026
To embed our video on your website copy and paste the code below:
<iframe src="https://www.youtube.com/embed/WrRKMZQ00AI?modestbranding=1&rel=0" width="970" height="546" frameborder="0" scrolling="auto" allowfullscreen></iframe>
James Pearce, TelecomTV (00:05):
Hello, and welcome to TelecomTV. I'm James Pearce, and I'm delighted to be joined today by Hemant Patil from Ericsson. Thank you so much for joining us today. So telecom customers can experience service degradation before traditional network alarms start firing. When contributing issues can span RAN, core, cloud, finding and prioritizing the right fix can feel like finding a needle in a haystack. How does this catalyst tackle this challenge as part of Autonomous Networks Level 4 operations?
Hemant Patil, Ericsson (00:33):
Yeah. This catalyst leverages five AI agents on top of a digital graph of RAN, core, and cloud to execute on a zero-touch closed loop. The detective agent is what detects the problem. The engineer agent is what prioritizes what needs to be fixed based on business value. The executor agent then translates it into a healing intent, which is given to Ericsson Service Orchestration and Assurance, which configures it into the network. And the reflection agent validates if the performance is restored. This is how the whole loop works and closes a lot of issues, like silent degradation.
James Pearce, TelecomTV (01:10):
Brilliant. Thank you.
Hemant Patil, Ericsson (01:12):
Thank you.
Hello, and welcome to TelecomTV. I'm James Pearce, and I'm delighted to be joined today by Hemant Patil from Ericsson. Thank you so much for joining us today. So telecom customers can experience service degradation before traditional network alarms start firing. When contributing issues can span RAN, core, cloud, finding and prioritizing the right fix can feel like finding a needle in a haystack. How does this catalyst tackle this challenge as part of Autonomous Networks Level 4 operations?
Hemant Patil, Ericsson (00:33):
Yeah. This catalyst leverages five AI agents on top of a digital graph of RAN, core, and cloud to execute on a zero-touch closed loop. The detective agent is what detects the problem. The engineer agent is what prioritizes what needs to be fixed based on business value. The executor agent then translates it into a healing intent, which is given to Ericsson Service Orchestration and Assurance, which configures it into the network. And the reflection agent validates if the performance is restored. This is how the whole loop works and closes a lot of issues, like silent degradation.
James Pearce, TelecomTV (01:10):
Brilliant. Thank you.
Hemant Patil, Ericsson (01:12):
Thank you.
Please note that video transcripts are provided for reference only – content may vary from the published video or contain inaccuracies.
Hemant Patil, Service and 5G Slicing Orchestration - Global Sales, Ericsson
Ericsson’s Hemant Patil explains how a collaborative ecosystem of specialised AI agents enables Level 4 Autonomous Networks to resolve issues before alarms can even fire. He reveals how zero-touch closed loops dynamically detect, prioritise, heal and validate network performance across the radio access network, core and cloud.
Recorded October 2026
Email Newsletters
Sign up to receive TelecomTV's top news and videos, plus exclusive subscriber-only content direct to your inbox.
