Hello and welcome to my podcast show Tech Talk. In the April I had a chance to go to AWS Summit Health in London. It was first of my kind of experiences. I mostly work in Azure, but I wanted to explore what kind of services they are providing and what are new things they are demonstrating there.
They even start at 8:00 AM. But your keynote starts at 10:00 AM. But before that two overs, I had a good chance to explore different kind of areas, what they are offering different kind of camps. Enjoy free coffee and breakfast as well.
It was good to see those things that most interesting thing, which I want to cover in today's podcast is one of their demos was around amplifying how they can transform and create a end to end application using just a Gen. AI. What it does like it hosting your data authentication and even give you an instant previews when you're working in AWS. Simplify is a kind of tool which allows you to build your end to end applications from start to finish.
It tells you're mostly in React and then it connects your back end and your middleware as well. So it's a, it's a good way to get into the market if you don't have, if you don't want to spend much time in building these components from scratch. What it does provide use ready to use components, which you can utilize it from the GUI and then it can help you out and build this end to end application. It's a TypeScript first approach where you can focus on application code, node
infrastructure, for example. And then you can, you can have your sandbox environment set up hopefully. And then it's easy for developers to work on on a product in their own sandbox environment and have an isolation environment where they can test it.
It's a quick way of building an application where you still have an opportunity to work on the code side, but it does all by itself using the chain AI. Then another thing which I attended was like a WSQ code transform which helps you transform your legacy code into the new code and what it does like it analyze and creates the plan for you. So for example, you have an application in.net or Java which is outdated and you want to transform into that upgraded
framework. So it does it by solve by creating a plan for you. The good thing is like whatever the changes, it's such as you, it actually gives you a manual human intervention. So for example, if the plan doesn't work or if you have some kind of limitation, it does let you manually intervene those kind of process to actually make
like informed decisions. But it's a good way of like doing the manual rather than doing the manual work, it just automate it and just deploys the full application into a new Facebook and then it it generates the. The good thing is like if you have like multiple depositories, let's say report 1234 sitting in GitHub, you can actually do the interaction with it give you a kind of understanding where you can transform several repositories at once.
And it can create a plan for each repositories according to whatever the code is present in those repositories, either Java or in a similar kind of approach, Microsoft got like a GitHub Copilot app modernization, which is actually in the early stage of testing. But Microsoft does have Azure micro application and code assessment for upgrading technic application. What I found it is like this tool is quite impressive. It can handle the things very
well. And in, in terms of maturity, this tool, Amazon Q Core transform is, is better than what I found it with as compared to GitHub Copilot, which is again in the early stage of modernization and the existing tool, which is Microsoft micro application. I did tried Amazon Q together per visual core to see like how does it work? And I'm very impressed by how it actually works. In reality, it's not about the
demo, which I've seen it there. But in reality, if you want to give it a go up with Amazon Q code transform to test like any legacy code to migrate to the new framework. Or you can use the intelligent Gen. EI agent to actually give you suggestions on your, how you actually works in there. Another thing which I've really looked at is like how they're using AI to, to, to automate
some of the task. So one of the thing which I had a demo about like how you can choose AI to do kind of like changes in your complaint system in financial institution. So they showed us like a bit good kind of like an agent application which actually works on by automating your complaint system. So for example, they had five agents. So one is customer advocate agent, which actually speaks on the behalf of the customer. So if you receive a complaint from the customer into your
complaints management. So this customer advocate teacher actually assess the complaint from the customer point of view. Then you have a business agent which actually looks at what your current business is and gathers all the business policies around it that you have Internet policy agent, which actually looks like what's your policy in terms of like resolving one of these complaints and what are the action could be taken.
And then there was like FCA compliance agent which actually looks at the FCA documentation and gives you suggestions from from that point of view. And lastly, we have a judge agent which actually get us all the results from all these four regions and then compile them and give you the suggestion. So they outwork automatically. So each agent collects their job data in on their own behalf and compile the record. And it takes like a few minutes to actually get to this.
And at the end of the day, the judge agent actually used those records to create a case and give you what should be done for that specific complete again the customer. And before we sent this thing to the customer, that human intervention can be done to actually feed more data or maybe change the responses before we actually sent to the customer.
So that's was a good way of demonstrating how AI can automate your task, especially in the complaints handling management and how it can speed up the process of like resolving customer queries and basically using the agents model in and, and, and helping you out with quick resolving those customers to most of the conference was around AI, how the AI can be utilized to speed up the work, automate some of the manual work and how you can build these agents to actually help you out
to be more productive. So I think it was a good flavor of AWS. If I compare it with Azure, they both have like identical services. They both are doing good in their cloud platforms and they have both are providing like hundreds of services which can help us transform your business, help you build ancient capability in your applications. And they also in WS they are building everything is similar to what you are building in
Azure as well. And no code probably in terms of like putting those agents, you just need to to train those agents your models and then you are good to go and use them into your application. Overall, it was a good experience at AWS London conference. Thank you for listening me to Nick in today. I will come back soon with another actually. So tell them see you.