AI inference in practice: time is money

Inferencing is the real-time decision-making of AI in practice. In the telecoms industry, this could apply to the network, services, customer care or other corporate workloads. As AI adoption grows, inferencing will accelerate, raising the question of where workloads will be processed and how they translate into business benefits.

As outlined in “Distributed inference: how AI can turbocharge the edge”, published for GTC 2025, several factors support the case for AI at the edge: growing use of agentic AI, reducing compute latency, improving network resilience and energy efficiency, and ensuring data sovereignty. Goals include saving money, making money, reducing risk and helping customers.

To illustrate the impact of AI inference in practice, three Spotlights will focus on use cases, with each featuring an example provider from the telecoms AI ecosystem. The reports will be complemented by a plug-and-play calculator developed for network operators, their partners and enterprise buyers to simulate the potential impact of running inferencing workloads at various network locations. This analysis examines AI on the near edge in distributed telco data centres, with Kinetica highlighted as an example.