BT Group’s digital unit has launched an internal platform to help the company tap into large language models (LLMs) from providers such as Anthropic, Meta, Claude, Cohere, and Amazon.
The GenAI Gateway, built in collaboration with AWS and using Amazon Bedrock, Amazon SageMaker and AWS Professional Services capabilities, provides secure, private access to a range of natural-language processing and LLMs, a critical tool BT Group will use as it embeds AI into the way it runs the business.
Ad-hoc use of LLMs, while appropriate for test and development work, is not well suited to large scale use; cost control, security and privacy need more careful management. LLM performance also needs to be monitored, for unexpected errors and model decay over time. The GenAI Gateway also gives BT Group protection against ‘lock-in’ to any given LLM if any other issues emerge. The use of GenAI Gateway platform will encourage BT Group engineers to use the right model for the right use case.
A consolidated platform reduces duplication of effort and resources, as BT Group scales the adoption of generative AI. APIs, security configuration and infrastructure management can all be managed centrally, reducing the risk of error and the cost of maintaining separate LLMs for every use case.GenAI Gateway, deployed on AWS, is accessed via secure APIs, like all the components of BT Group’s modular digital architecture.
GenAI Gateway uses Amazon Bedrock, a fully managed service that offers a choice of high-performing foundation models from AI companies such as AI21 Labs, Anthropic, Cohere, Meta, Mistral AI, Stability AI and Amazon through a single API; as well Amazon SageMaker, a fully managed service that brings together a broad set of tools to enable high-performance, low-cost machine learning for any use case.
The platform supports prompt security, chat history, FinOps billing per use case, enterprise search, as well as use of multiple corporate data sources. Central privacy controls include separate tenants for each use case, the use of personal identifiable information filters, the location of the data within the UK and the isolation of trained models from each other, protecting data in line with group policies and relevant regulation. Guardrails are built into the GenAI Gateway, limiting the risk of jailbreaks or toxic interactions, filtering out queries that go beyond the remit of specific applications – ensuring both performance and ethical guardrails are built-in by design.
Fabio Cerone, GM EMEA telco at AWS, said, “The BT Group GenAI Gateway is showcasing how enterprises can effectively deploy generative AI at scale and speed. It’s been a brilliant, pioneering opportunity to collaborate and work backwards from the customer to provide a way to accelerate deployment of generative AI use cases into production with embedded security and compliance. The GenAI Gateway will trigger the flywheel effect in the adoption of generative AI, delivering quicker results for BT Group and its customers.”
Deepika Adusumilli, managing director, data and AI, BT Group’s digital unit, said, “AI is helping us reimagine the future of our company. We believe that where our data is a constant, we need flexibility with our LLMs. GenAI Gateway allows us to tap into this powerful new set of technologies at scale, in a way that is safe, responsible, flexible and scalable, delivering the ambition we have for AI to unlock the human potential within BT Group, today and in the future.”