They reduced service design from weeks to minutes by embedding AI-driven automation in operational workflows – more use cases will follow for dynamic, intent‑based services
Telefónica Deutschland and Blue Planet, a division of Ciena, completed a joint proof of concept (PoC) exploring the use of AI agents to accelerate the design and fulfilment of 5G network slicing services.
As part of Telefónica Deutschland’s ongoing transformation of its OSS and its strategy of higher levels of network autonomy, the company is focused on industrialising service and network deployment through its Service & Network Factory.
A key enabler of this transformation is Telefónica Deutschland’s Multi‑Domain Service Orchestration (MDSO) programme, which provides end‑to‑end orchestration across network domains and underpins the introduction of new, complex services, including 5G network slicing.
This is a high‑value B2B service, characterised by complex specifications, evolving standards and strong dependence on expert knowledge. Designing and deploying slicing services efficiently gets servcies to market faster while maintaining quality and consistency across domains.
Intent-based design
To address these challenges, Telefónica Deutschland collaborated with Blue Planet to test how AI agents could support engineers throughout the service lifecycle – from intent‑based design to catalogue creation and fulfilment.
The PoC leveraged Blue Planet AI Studio, an OSS‑native platform for building and running AI agents, integrated directly with Telefónica Deutschland’s MDSO environment. AI‑driven automation was embedded in real operational workflows rather than running as a standalone experiment.
The results
Tasks that previously required specialised expertise and manual effort – such as defining slice specifications and generating standards‑compliant service payloads – were completed in minutes instead of weeks. By abstracting complex standards and parameters into AI agents and reusing catalogue elements managed through MDSO, the solution improved design speed, consistency, and quality, while reducing errors through guided, repeatable processes.
Eva Ulicevic (pictured), Director of Architecture, Strategy and Technology Enablement at Telefónica Deutschland, commented, “This proof of concept has shown that AI agents, when integrated with our MDSO framework, can meaningfully simplify service design, reduce lead times, and help democratize expert knowledge. It is an important validation of how intent‑based, AI‑driven approaches can support our evolution toward more autonomous operations, allowing us to provide additional and enhanced customer services.”
For his part, Joe Cumello, Senior Vice President and General Manager, Blue Planet said, “By building AI agents directly into their orchestration workflows using Blue Planet AI Studio, this PoC demonstrates how service providers can accelerate innovation while maintaining control, standards compliance, and operational rigor.”
Beyond the PoC
Beyond the immediate outcomes, the PoC provides valuable insight into how AI‑driven automation can complement multi‑domain orchestration to support the future evolution of network and service operations. By validating the role of AI agents within the MDSO framework, Telefónica Deutschland and Blue Planet have established a foundation for scaling this approach to additional use cases and enabling more dynamic, intent‑based services.
Javier García, Head of Core IT at Telefónica Global CTIO, added, “This proof of concept supports Telefónica’s ambition to advance towards higher levels of network autonomy, reinforcing the role of AI in transforming service and network operations. Moving beyond traditional automation requires evolving operational systems into AI-native platforms that can progressively increase autonomy.”
