Breaking barriers: Harnessing generative AI in telecom (TLC207)
Breaking Barriers: Harnessing Generative AI for Telecom
Introduction
The session introduces the AWS for Telecom team and their work on breaking barriers and harnessing generative AI for digital inclusion.
The team consists of Robbie Bellson (Senior SA), Andrew Young (Software Developer), and Kenes Mii (Director of Technology for Telecom).
AWS for Telecom and Digital Inclusion
AWS for Telecom works with telecom operators, customers, and partners across 5 continents to transform telecom, reimagine customer experiences, and digitize industries.
One of the key leadership principles at AWS is "success and scale brings broad responsibility" - this includes responsibility to local communities, the planet, and future generations.
AWS is committed to digital inclusion through initiatives like the AWS Scholarship Program and the AWS Digital Equity Initiative.
Telecom is central to connecting communities and accessing inclusive technology, so AWS for Telecom sees an opportunity and obligation to shape the future of digitally inclusive tech.
Breaking Barriers Program
The Breaking Barriers program was born out of a challenge from a telecom customer to help with large-scale adoption of generative AI.
The team decided to address the broader societal problem of enabling everyone to effectively consume and monetize technology.
A hackathon was organized in partnership with Nvidia, Anthropic, and AT&T, which brought together multiple sectors to experiment and find solutions.
The Winning Application: Learn AI
The winning application from the hackathon was "Learn AI", developed by a student team.
Learn AI is a dynamic, personalized learning platform that can adapt to different learning styles (visual, auditory, kinesthetic) by generating tailored summaries and interactive games based on the content being learned.
The application can be used to learn a variety of content, from telecom specifications to textbooks, by ingesting the document and personalizing the learning experience.
Generative AI as the Foundation
Generative AI is seen as the inflection point for building digitally inclusive applications, as well as applications in general.
The assistant walks through a three-layer generative AI stack, comprising:
Tools for building and scaling generative AI applications (e.g., Amazon Bedrock)
Integrated digital assistants (e.g., Amazon CodeWhisperer)
Generative AI Gateway
To enable "any model, any data, anywhere", the team developed a Generative AI Gateway architecture using AWS services like API Gateway, Lambda, and Amazon Cognito.
This gateway provides features like model abstraction, identity management, content moderation, and a developer-friendly interface for discovering and accessing generative AI models.
Data Foundation with Amazon DataZone
Integrating internal company data is crucial for building retrieval-augmented generation (RAG) applications.
Amazon DataZone is a self-service analytics service that allows organizations to easily share, discover, access, and govern data at scale across boundaries.
The team demonstrates how the Learn AI application can leverage the Telecom Data Foundation powered by Amazon DataZone to personalize the learning experience.
Hands-on Demo
The team provides a hands-on demo to build the Generative AI Gateway, Data Foundation, and a sample Learn AI application using AWS services like API Gateway, Lambda, Amazon Bedrock, and Amazon DataZone.
The demo shows how developers can easily integrate these building blocks to create digitally inclusive applications.
Closing Remarks
Kenes emphasizes the importance of breaking social, economic, and technological barriers to create an equitable future for all.
The team encourages the audience to reach out if they are passionate about solving problems for humanity, creating digitally inclusive tech, or building solutions at a global scale.
These cookies are used to collect information about how you interact with this website and allow us to remember you. We use this information to improve and customize your browsing experience, as well as for analytics.
If you decline, your information won’t be tracked when you visit this website. A single cookie will be used in your browser to remember your preference.