Remove solutions ai-data-solutions data-collection-services
article thumbnail

Improve LLM performance with human and AI feedback on Amazon SageMaker for Amazon Engineering

AWS Machine Learning

The Amazon D&C team implemented the solution in a pilot for Amazon engineers and collected user feedback. In this post, we share how we analyzed the feedback data and identified limitations of accuracy and hallucinations RAG provided, and used the human evaluation score to train the model through reinforcement learning.

article thumbnail

Guest Post: 7 Ways Improved Customer Journey Results in Business Growth

ShepHyken

This week, we feature an article by Sage , an international company that helps organizations of all sizes with accounting, payroll, and payment solutions. Enhanced customer satisfaction Stockouts, inaccurate forecasting, delays, silos, poor customer service: all of the weaknesses within your customer journey threaten to ruin experiences.

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

article thumbnail

Slack delivers native and secure generative AI powered by Amazon SageMaker JumpStart

AWS Machine Learning

This post is co-authored by Jackie Rocca, VP of Product, AI at Slack Slack is where work happens. It’s the AI-powered platform for work that connects people, conversations, apps, and systems together in one place. None of your data is used to train the underlying models. None of your data is used to train the underlying models.

article thumbnail

AI-Automated Fiber Customer Installation: A Seamless Self-Service Solution

TechSee

Over the last 12 months, our new AI-powered streamlined fiber customer installation solution has helped leading telecoms across North America automate millions of self-installs. By popular demand, we are now offering this AI-automated guided flow as a packaged solution.

article thumbnail

Build a contextual text and image search engine for product recommendations using Amazon Bedrock and Amazon OpenSearch Serverless

AWS Machine Learning

Search engines and recommendation systems powered by generative AI can improve the product search experience exponentially by understanding natural language queries and returning more accurate results. Amazon OpenSearch Service now supports the cosine similarity metric for k-NN indexes. Review and prepare the dataset.

article thumbnail

Knowledge Bases for Amazon Bedrock now supports metadata filtering to improve retrieval accuracy

AWS Machine Learning

With Knowledge Bases for Amazon Bedrock, you can securely connect foundation models (FMs) in Amazon Bedrock to your company data using a fully managed Retrieval Augmented Generation (RAG) model. For instructions, see Sync to ingest your data sources into the knowledge base. Metadata can be string, number, or Boolean.

APIs 101
article thumbnail

How BigBasket improved AI-enabled checkout at their physical stores using Amazon SageMaker

AWS Machine Learning

Customers often lose the weight sticker and have to go back to the weighing counters to collect one again before proceeding with the checkout process. Self-checkout process BigBasket introduced an AI-powered checkout system in their physical stores that uses cameras to distinguish items uniquely.