Exclusive Content:

Haiper steps out of stealth mode, secures $13.8 million seed funding for video-generative AI

Haiper Emerges from Stealth Mode with $13.8 Million Seed...

Running Your ML Notebook on Databricks: A Step-by-Step Guide

A Step-by-Step Guide to Hosting Machine Learning Notebooks in...

“Revealing Weak Infosec Practices that Open the Door for Cyber Criminals in Your Organization” • The Register

Warning: Stolen ChatGPT Credentials a Hot Commodity on the...

Cisco achieves 50% reduction in latency with Amazon SageMaker’s faster autoscaling feature

Enhancing Contact Center Experiences with Generative AI and Amazon SageMaker Inference_SPEEDY AUTOSCALING RELEASE REFERENCE

Cisco’s Webex Collaboration AI team is at the forefront of leveraging AI-driven features to enhance its products and services. With a focus on generative AI and large language models (LLMs), the team has been able to improve productivity and user experiences, particularly in the realm of customer engagement solutions like Webex Contact Center. However, as the models grew in size and complexity, the team faced challenges in efficiently allocating resources and scaling applications.

To address these challenges, Cisco worked with Amazon SageMaker Inference to optimize its AI/ML infrastructure. By migrating LLMs to SageMaker, Cisco was able to improve speed, scalability, and price-performance. This architectural shift allowed for better resource utilization and streamlined development, testing, and deployment of new AI-powered features for the Webex portfolio.

One notable improvement came in the form of faster autoscaling with SageMaker’s new predefined metric types. By utilizing high-resolution metrics like SageMakerVariantConcurrentRequestsPerModelHighResolution, Cisco saw up to a 50% improvement in end-to-end inference latency. This enhancement enabled faster detection of scaling needs and more efficient allocation of resources, ultimately leading to improved performance and efficiency for their critical Generative AI applications.

Looking ahead, Cisco plans to continue working with SageMaker Inference to drive further improvements in variables that impact autoscaling latencies, such as model download and load times. With this new feature, Cisco looks forward to broadening its rollout in multiple regions and delivering even more impactful generative AI features to its customers.

The collaboration between Cisco and Amazon SageMaker highlights the power of AI-driven innovation in enhancing collaboration experiences and customer engagement solutions. With a focus on leveraging advanced technologies like LLMs and generative AI, Cisco is paving the way for more efficient and personalized customer interactions. As the partnership continues to evolve, we can expect to see even more exciting developments in the realm of AI-driven collaboration.

Latest

Creating Age-Responsive, Context-Aware AI Using Amazon Bedrock Guardrails

Ensuring Safe and Reliable AI Responses: A Guardrail-First Approach...

Sephora Introduces ChatGPT App to Enhance AI-Driven Beauty Shopping体验

Sephora Launches AI-Powered App in ChatGPT for Personalized Beauty...

European Robotics Forum Set for Birmingham in 2027

European Robotics Forum 2027: Shaping the Future of Robotics...

Google Launches Global AI Camera Assistant for Live Search

Google Unveils Search Live: Revolutionizing Visual AI and Conversational...

Don't miss

Haiper steps out of stealth mode, secures $13.8 million seed funding for video-generative AI

Haiper Emerges from Stealth Mode with $13.8 Million Seed...

Running Your ML Notebook on Databricks: A Step-by-Step Guide

A Step-by-Step Guide to Hosting Machine Learning Notebooks in...

VOXI UK Launches First AI Chatbot to Support Customers

VOXI Launches AI Chatbot to Revolutionize Customer Services in...

Investing in digital infrastructure key to realizing generative AI’s potential for driving economic growth | articles

Challenges Hindering the Widescale Deployment of Generative AI: Legal,...

Creating Age-Responsive, Context-Aware AI Using Amazon Bedrock Guardrails

Ensuring Safe and Reliable AI Responses: A Guardrail-First Approach for Diverse User Populations Introduction to AI Response Verification Addressing Content Safety and Reliability Challenges Solution Overview: Serverless...

Deploying Voice Agents Using Pipecat and Amazon Bedrock AgentCore Runtime –...

Leveraging AWS and Pipecat to Build Intelligent Voice Agents: A Comprehensive Guide Introduction to Intelligent Voice Agents This post is a collaboration between AWS and Pipecat....

Speeding Up Custom Entity Recognition Using the Claude Tool in Amazon...

Unlocking the Power of Claude Tool Use for Efficient Entity Extraction with Amazon Bedrock Streamlining Document Processing with Large Language Models Key Topics Covered: Understanding Claude Tool...