AWS Machine Learning Blog

Category: HAQM Lex

architecture diagram

Enhance your customer’s omnichannel experience with HAQM Bedrock and HAQM Lex

In this post, we show you how to set up HAQM Lex for an omnichannel chatbot experience and HAQM Bedrock to be your secondary validation layer. This allows your customers to potentially provide out-of-band responses both at the intent and slot collection levels without having to be re-prompted, allowing for a seamless customer experience.

Using transcription confidence scores to improve slot filling in HAQM Lex

When building voice-enabled chatbots with HAQM Lex, one of the biggest challenges is accurately capturing user speech input for slot values. Transcription confidence scores can help ensure reliable slot filling. This blog post outlines strategies like progressive confirmation, adaptive re-prompting, and branching logic to create more robust slot filling experiences.

Achieve multi-Region resiliency for your conversational AI chatbots with HAQM Lex

Global Resiliency is a new HAQM Lex capability that enables near real-time replication of your HAQM Lex V2 bots in a second AWS Region. When you activate this feature, all resources, versions, and aliases associated after activation will be synchronized across the chosen Regions. With Global Resiliency, the replicated bot resources and aliases in the […]

Create a next generation chat assistant with HAQM Bedrock, HAQM Connect, HAQM Lex, LangChain, and WhatsApp

Create a next generation chat assistant with HAQM Bedrock, HAQM Connect, HAQM Lex, LangChain, and WhatsApp

In this post, we demonstrate how to deploy a contextual AI assistant. We build a solution which provides users with a familiar and convenient interface using HAQM Bedrock Knowledge Bases, HAQM Lex, and HAQM Connect, with WhatsApp as the channel.

Evaluate conversational AI agents with HAQM Bedrock

As conversational artificial intelligence (AI) agents gain traction across industries, providing reliability and consistency is crucial for delivering seamless and trustworthy user experiences. However, the dynamic and conversational nature of these interactions makes traditional testing and evaluation methods challenging. Conversational AI agents also encompass multiple layers, from Retrieval Augmented Generation (RAG) to function-calling mechanisms that […]

Detect and protect sensitive data with HAQM Lex and HAQM CloudWatch Logs

In today’s digital landscape, the protection of personally identifiable information (PII) is not just a regulatory requirement, but a cornerstone of consumer trust and business integrity. Organizations use advanced natural language detection services like HAQM Lex for building conversational interfaces and HAQM CloudWatch for monitoring and analyzing operational data. One risk many organizations face is […]

Build a self-service digital assistant using HAQM Lex and HAQM Bedrock Knowledge Bases

Organizations strive to implement efficient, scalable, cost-effective, and automated customer support solutions without compromising the customer experience. Generative artificial intelligence (AI)-powered chatbots play a crucial role in delivering human-like interactions by providing responses from a knowledge base without the involvement of live agents. These chatbots can be efficiently utilized for handling generic inquiries, freeing up […]

Implement exact match with HAQM Lex QnAIntent

This post is a continuation of Creating Natural Conversations with HAQM Lex QnAIntent and HAQM Bedrock Knowledge Base. In summary, we explored new capabilities available through HAQM Lex QnAIntent, powered by HAQM Bedrock, that enable you to harness natural language understanding and your own knowledge repositories to provide real-time, conversational experiences. In many cases, HAQM […]

Create natural conversations with HAQM Lex QnAIntent and HAQM Bedrock Knowledge Bases

Customer service organizations today face an immense opportunity. As customer expectations grow, brands have a chance to creatively apply new innovations to transform the customer experience. Although meeting rising customer demands poses challenges, the latest breakthroughs in conversational artificial intelligence (AI) empowers companies to meet these expectations. Customers today expect timely responses to their questions […]