AWS re:Invent 2025 - Build an Agentic SaaS App in 5 Steps: From Idea to Revenue (AIM104)

🦄 Making great presentations more accessible.
This project aims to enhances multilingual accessibility and discoverability while maintaining the integrity of original content. Detailed transcriptions and keyframes preserve the nuances and technical insights that make each session compelling.

Overview

📖 AWS re:Invent 2025 - Build an Agentic SaaS App in 5 Steps: From Idea to Revenue (AIM104)

In this video, John Huehn and Steve Bixby from Pega Systems demonstrate building an enterprise-grade agentic SaaS application using Launchpad in five steps. They showcase creating a mortgage pre-approval application for a fictional fintech called HomeLend that sells to banks. The demo illustrates using Gen AI-powered blueprints to design workflows, deploying on AWS infrastructure, adding enterprise capabilities like human approval rules for loans over $5 million, making it available to multiple bank subscribers, and showing live customer usage through a conversational interface that reduces processing time from days to seconds for customers like Sarah seeking home loan pre-approval.

; This article is entirely auto-generated while preserving the original presentation content as much as possible. Please note that there may be typos or inaccuracies.

Main Part

Introduction: Building an Enterprise-Grade Agentic SaaS Application with Launchpad

All right, hey everyone, I'm John Huehn. I'm the Chief of Launchpad for Pega Systems, and with me today is Steve Bixby, who is our Senior Vice President of Product Engineering. We are delighted to be spending the next 20 minutes with you building an enterprise-grade agentic SaaS application that can run a complex and regulated process and be sold to thousands of B2B clients in just five easy steps.

Those steps include making the design with a Gen AI-powered blueprint, making it real here on AWS, making it work with enterprise capabilities, making it available to your subscribers, and making it rain with real live customer usage. We're going to demonstrate how a fintech that we're going to call HomeLend can build and sell to banks an agentic application that will dramatically accelerate processing and deliver a great customer experience for a scenario that many of us may have gone through ourselves or may one day go through in our lives, which is mortgage pre-approvals.

Of course, banks are super excited to see their work get automated, but they also can't afford to have AI introduce variability into important decisions like creditworthiness. That's where a lot of agentic applications struggle. They have armies of agents trying to manage other armies of agents to deliver an outcome, and of course that just naturally breeds all kinds of variability, which can't exist in financial decisions.

So today we're going to use workflows to manage our AI agents to deliver a controlled, deterministic, predictable outcome, the kind of outcomes that regulated industries like banking actually love. To build our application, we're going to use Launchpad, the AI-powered low-code app development platform from Pega. If you've never used Launchpad before, what you should know is whether you're looking to build a new application or enhance maybe a legacy application with workflow or Gen AI into it, or you're looking to replace or re-platform a tech debt-laden old application with something new and modern that you can innovate on faster, then Launchpad will dramatically accelerate your speed to market, reduce your development time, and reduce your costs.

It provides a vibe development experience that helps get your app started with a managed database and secure, scalable cloud powered by AWS, with industry-leading workflow, integration, and UX and reporting capabilities, and with pre-built subscriber management, administration, and configurability, all with a usage-based pricing model that scales with your business. Ultimately, Launchpad gives you everything that you need to build and sell an enterprise-grade application without the cost and complexity of managing your cloud, your security, and of course code.

So we're going to get started. Here's our scenario. HomeLend, our make-believe fintech that builds and sells apps to banks, has identified a gap in the mortgage pre-approvals process that impacts people like Sarah. Sarah's dream house just came on the market, and she is super excited. She very quickly booked a showing of the house, contacted her bank, and provided all of her documentation to get a mortgage pre-approval and the corresponding letter.

But unfortunately, her bank took two days to process her application and get back to her with that letter. Sadly, during that time, somebody else bought Sarah's dream house. Imagine how disappointing that is, and HomeLend understands that pain. So they are going to build an agentic SaaS application for banks to reduce the processing time from days to seconds and deliver a great experience for folks like Sarah.

Something that actually looks like this, an agentic SaaS application with a conversational interface. So Steve, I'm hoping I can count on you now to play the role of HomeLend, and I want to build an app that manages the mortgage pre-approvals process and other loan origination stuff. All right, well, that's a challenge. We're going to do it. Hopefully the Wi-Fi holds up. We're going to build this real quick. Last session of the day, thank you all for being here.

Okay, John, could you actually just maybe say that one more time? Okay, Steve, I want to build an app that manages the mortgage pre-approvals process and other loan origination stuff. We got it. All right, brilliant. That's enough to get started with this process. So here we go.

Live Demo: Creating HomeLend's Mortgage Pre-Approval Application from Blueprint to Deployment

We're in Launchpad. If you want to see Launchpad and try it yourself, we're at the Pega booth just over there. Everything I'm showing here you can do for yourself. Check it out at launchpad.io. All right, so it said perfect, what's your application name? This is HomeLend, so HomeLend. And here we go. I can now build your loan origination application, which will include a mortgage pre-approval process. It's identified the industry, the location, and all the things that are needed to build an application. Obviously, we haven't really provided enough context, but it's giving us the option to start building. So for the sake of time, let's just go for it. Let's build.

All right, so it now says I'm building your application. I'm starting with an industry template and customizing the workflows, connecting the channels, setting up the personas, and configuring the data and integrations. Boom. All right, awesome. So the chat is now pushed over to the right, and we're presented with the development environment for Launchpad here. You can see that our launch readiness is about a quarter of the way done. We can keep an eye on that as we walk through the process here.

So it's identified that we are this HomeLend corporation. We're in the US retail banking, and this is a loan origination application. Great. And if I click here in the middle of this diagram, this is going to show us the workflows that it created. So it created eight workflows, it looks like. Here they are, and mortgage pre-approval is in fact one of them. That's good. The rest of them are the other stuff. That's right, lots of other stuff. That's good. That's what we asked for.

Let's take a look at the mortgage pre-approval process. All right. So what Launchpad does for you is it takes that business process and breaks it into a series of stages and steps to organize the business process. I can now interact with this, add steps, add stages, drag them, drop them, move them around, and update this. But if we look at it, it looks like we've got a collect application data, verifying information, and then we go through financial assessment, pre-approval decision, and then ultimately finalization. So this actually looks pretty good in terms of delivering what Sarah's looking for in that scenario you described.

So let's make a few changes. Actually, before we do that, let me show you the data model over here. So it's also generated a data model for us. This thing's generated a full UI. It's all there. We're going to see it in a minute. Again, I can update this and make changes to it as needed. You see, we've got an applicant name, date of birth, W-2, annual income, all the things that we would need for that mortgage pre-approval process, all created with generative AI using the Bedrock models from AWS.

So let's go back to the lifecycle now. Let's make a change, John. What should we change? So I think Steve, maybe we want to get some human eyeballs if somebody's going to ask for a pre-approval maybe over five million dollars. Five million dollars would be good to have somebody actually take a look at. So in the pre-approval decision here, I could just type this over on the chat on the right, but I want to show you a cool feature here where I can actually do it inline, where I can just click on the area of the screen that I want to make the change to, and I can say configure the system so that any loan request over five million requires human approval, period. Boom. Nice.

So awesome. So this just inserted this human approval step, or it's a decision actually to determine if we need a human approval step. And if you want to know what did this actually do behind the scenes, I can open the left-hand panel here and it's going to show all of the assets that have been created that support this application. And here's that human approval down here at the bottom. It's a decisioning rule. It's private and it generated an expression for loan amount greater than five million dollars. So that's awesome. All right, let me just close this just to show you can work with the full screen here.

Let's make one more change. Let's add an agentic step, or at least a placeholder where we can insert one. So let me see. Let's integrate the AWS Nova agent to automate the verification of the employment through the approved third-party service. So you can add decision steps, you can add human steps, which would require a screen or some sort of interaction, whether it's through self-service or maybe through a contact center agentic conversation.

You can add agent calls, you can add decisions, automations, all of that here to build out this application. Now because we have such a short window, we're going to say, all right, this is probably what we need from here. Let's preview it. Let's see what does this application look like to a potential end user.

All right, so here we go. This is a, it even says right here, preview, Demo Bank. It's not real. That is not real. This is demo. This is how you test the application now, and I'm presented with this virtual assistant that says, Hi, I'm your virtual assistant. How can I help you today? I'm going to tell it, hi, I'd like to get pre-approved for a home loan. Says, sure, I'd be happy to help to get started. Could you please provide your full name and date of birth? Of course, my actual name, Steven Bixby, June 14th, 1983, not my actual birthday. I was gonna say I did not realize how much younger you are than me, Steve. Thank you. What loan amount would you like to be pre-approved for? I'm looking for $1 million. Got it to proceed.

So do you understand what this is doing? It's actually going through the first step of the process and trying to collect the information that's necessary. To visualize that further, in this preview portal here, we can say, okay, that's what it's gonna look like through this self-service chat, but what would it look like in like, in the bank back office in a desktop application. So this is the application that it's created for us, and you can see there's a dashboard, there's chat, there's all kinds of stuff that's going on here. And I can actually create any one of these workflows right from here or instance of the workflow, including that mortgage pre-approval.

And now I'm gonna see those fields that were prompted in that first step of the first stage, which included the applicant name, the date of birth, email, phone, annual income, and the W-2 file. So that's pretty cool because you just built the core logic of the app. And we're showing it in the conversational interface, but you can actually do the same thing on the employee desktop and it also would work on your website for self-service, mobile app, mobile app, you know, build that logic in the core in the center one time and it deploys across all of your channels. Exactly.

All right, so let's assume that this app is perfect. There's all kinds of things that we probably would want to go tweak to make this our own, make it actually serve the purpose that we need. But from here, I think we can, let's launch this thing. So what's unique about Launchpad is that it's built specifically for organizations that are building products, SaaS products that they are going to then go sell. So we're, this is, we're a provider here, and we're gonna go sell this to our subscribers.

So when you launch it, it's actually gonna take this blueprint of our application and make it real. So it's, doing the domain data modeling, the workflow, the UI screen generation, the integration setup, the security configuration, all of that to make sure that we have an app that we can actually deploy so that our subscribers can use it. So I'm presented now with my list of subscribers, like HomeLend subscribers, there's five banks here. I'm just gonna say, let's deploy it so that all of them have access to it. And let's deploy this application.

Real-World Application: Sarah's Success Story and Closing Remarks

All right. So now that I've done that, made this available to all my subscribers, I'm looking at my subscribers dashboard. So as a provider, I can now see what's happening with other apps that I've built and that have been deployed. I can see the usage, I can see even the revenue, things like that. And right here, I'm seeing those banks and seeing that the HomeLend subscription is active for all of them.

So now that we've built this application, I'm gonna do a little bit of fantasy here. We're going to flip to one of these banks' websites and assume that they've already deployed this virtual assistant on their website, so it's no longer the, you know, this is not real bank, it's actually the UBank or U+ Bank website. So here we are on their website. They've, they've deployed this assistant here, and I can click on it and it says, I'm your U+ Bank virtual assistant. How can I help you today? So very similar to what we saw in the preview in the development environment, we're now seeing live for a real subscriber.

And this time, I'm going to say I'm Sarah, right? So let's be Sarah in this use case. And hi, I'd like to get pre-approved for a home loan. All right. Sure, happy to help. Get started. Please provide your full name. So this is gonna take us through that same process again. I'm gonna say I'm Sarah this time.

Sarah Wilson, March 18th, 1974. Thank you. What loan amount would you like to be approved for? Let's do a million dollars again. All right, everybody, a million dollars for Steve, a million dollars for Sarah. Everybody a million dollars. And now it's asking for the W-2, same as we saw before. Let's actually do that this time. Let's upload the W-2. Submit that W-2s received securely. I'm now evaluating your finances to determine pre-approval amount. I'll have the decision for you shortly. Here we go. Fingers crossed. Let's hope Sarah gets approved. It's not over $5 million so that rule's not going to be in play that we added. Boom, congratulations. Awesome. You've been pre-approved. Would you like me to email? Yes, definitely. Check your inbox. Is there anything else I can help you with? Let's say that was it. Thanks for getting back to me so fast. Awesome.

All right, John, so I think I did it. I built the application. I think Sarah's going to be happy. So that flip back. That is awesome. Thanks so much for sharing all that with us. So I'm just going to quickly recap, going back to our five steps with what Steve has shown us. So the first thing, Steve, you did, you made the design, leveraging vibe development to get your, to create your Gen AI powered blueprint. And then you made it real, secure, scalable on a pre-built and already-built AWS architecture.

You made it work with enterprise grade capabilities and with workflows managing your AI agents. And you made it available to your subscribers like UBank to configure and deploy to their customers, and you made it rain with real live customer usage from folks like Sarah who are using the UBank deployment of the app. So in five simple steps you built an enterprise grade Agentic SaaS application that dramatically shortened processing time and delivered a great experience for Sarah, and you took a cumbersome bank workflow and you enabled that to be automated to deliver an experience. It's for Sarah, whose story can now finally have a happy ending.

So there's really not much more for Steve and I to share, except to say if you have any questions about anything that we have shared today or if you want to learn a little bit about the amazing companies that are already building Agentic SaaS applications like Steve just showed on Launchpad. Or if you want to learn about our security capabilities and how our full technical review can accelerate your path for building an application and getting it onto the AWS Marketplace, we would love to see you at the Pega booth, which is number 366 just over here. Or if you'd like to get started with Launchpad today, just go and get started on your own for free. You can just click that get started button and start with easy step number one, designing your app with your Gen AI powered blueprint.

So with that, we will say thank you all very much for spending this time with us today, and we hope you enjoy the rest of your time here at AWS re:Invent.

---

; This article is entirely auto-generated using Amazon Bedrock.