Leveraging Amazon Bedrock for Generative AI Applications with JP

Picture of Kane Simms
Kane Simms

More ways to listen and watch

About this episode

JP joins us as he talks about the biggest opportunities and considerations for brands seeking to use generative AI in customer experience.

JP is the Co-Founder and CTO of SmartBots, a platform that’s making the most of Amazon Bedrock Foundation Models and enabling developers and brands to build generative AI applications. Find out about the biggest opportunities and considerations for brands seeking to use generative AI in customer experience, as well as how you can use the SmartBots platform to accomplish just that.

In this episode

00:00 Introduction
03:56 Welcome JP
10:16 Where SmartBots is now
13:45 Whats missing on the application layer
17:59 The middle ground
20:30 Defining prompts and models
21:40 Clients concern with hallucination
31:19 Retrieval augmented generation
35:10 Approaching different tasks
39:10 Quality assurance
45:00 Models changing
48:34 Difference between FAQ & rag solution
55:00 Open AI capabilities
1:00:15 Using LLMs to speak in other languages
1:03:38 Using training data
1:08:25 Outro

Enter one of the worlds biggest AI awards – We’re proud to support the AI World Series Awards and Conference. An unrivaled celebration of the best use cases of AI

Make sure to check out – Smartbots.ai

Visit JP’s LinkedIn

Share

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Host

Kane Simms

A strategic AI advisor who, for the past decade, has helped business leaders and product owners transform customer experience using conversational and generative AI.

Share

✓   Link copied

Weekly newsletter

The latest in AI-powered customer experience. Make better strategic decisions with the help of our weekly newsletter.

Top articles and podcasts

Related content

Cobus Greyling: why intents, graphs and conversation design have come full circle
Cobus Greyling on where enterprise AI is really heading: data, security, forward-deployed engineers and conversation design.
From answers to actions: building better government AI
Pete Kowalczyk on knowledge graphs, goal detection and moving AI from answering questions to taking action.
What’s really breaking your AI agents?
Discover where conversational AI projects actually break: contradictory source data, manual process and weak testing.
How Simplyhealth scaled voice AI to resolve 30% of calls
Paul Atkins, Head of Business Optimisation at Simplyhealth, breaks down how they scaled voice AI to resolve almost a third of calls, and what it took to get there.