🦄 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 - From vibe to live in minutes with Heroku AI PaaS (AIM250)
In this video, Julián Duque, Principal Developer Advocate at Heroku, presents their AI platform offerings including Managed Inference and Agents with one-click provisioning of models like Claude 3.5 Sonnet, GPT-4o, and Amazon Nova. He demonstrates a solar energy dashboard using Heroku AI agents with Model Context Protocol (MCP) for secure database access and code execution tools. The presentation showcases Heroku Vibes, a tool for building web applications through natural language prompts, demonstrating an AWS re:Invent agenda builder deployed directly to Heroku.
; 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
Heroku's Vision: Building the Platform as a Service for AI Applications
Hello, hello you all. Welcome to this presentation. I'm going to be talking about the AI offering that we have at Heroku. Before we start, I'm going to introduce myself. My name is Julián Duque. I'm the principal developer advocate for Heroku, which is a Salesforce company.
And being a Salesforce company, we are a publicly traded company, so please don't make any purchase decisions based on things that are not yet publicly available. I might be mentioning things that are not yet fully GA. So Heroku is a platform as a service. We have been in the business since 2010, 2011. We were the first platform as a service for Ruby on Rails applications, and now we support more than nine programming languages and some other managed services.
We are renowned for offering a great developer experience, and our developer experience is so good that a lot of companies and open source products have created the Heroku of X. They try to mimic our experience and create something out of what we do. So a couple of years ago we asked ourselves this question: Who is going to build the Heroku of AI? Who is going to bring the developer experience of building AI applications that Heroku offers?
And of course the answer was ourselves. We are going to be building the Heroku of AI. So basically, building AI applications and agents is challenging. You will need to make a lot of decisions and take care of things that are not usually obvious. For example, we need to select the right models, the large language models we are going to be using for our application, if it is like a text to text model, image generation model, if we are going to do embeddings. We need to make sure that we are using the right model for our app.
Also, how are we going to integrate with the other applications and services? How are we going to allow the LLM or the model to access data securely? Because right now one of the risks about building AI is data leakage. We are giving access to our data to a third party that can access it and it might be vulnerable to certain security issues. And also, how are we going to operate the infrastructure behind AI? There are a lot of hidden things that we don't know, like managing GPUs, being able to maintain the models running. There is a lot of complexity behind.
Also, it's hard to make things easy for developers, easy for the company to operate and manage. Heroku has been working on a platform for a while, so we already have an integrated platform where you can use and deploy your applications and agents. We have great developer experience and operational experience. We already selected a list of curated AI models that we know are used in the industry and that are working for these new types of applications, and we also added extensibility through the Model Context Protocol, which is this protocol that allows the LLMs to have access to more context through prompt resources and tools.
And getting live, getting to production is hard. We need to make a lot of decisions that are complex. For example, when we want to take an application or an agent to production, we need to choose where are we going to deploy this application, what is going to be the underlying operating system and the network configuration that we will use for our app. How is the CPU and memory going to be distributed for our application? What is going to be the data storage, the logging, the observability? So there is a lot of moving pieces that are related to deploying an application to production.
With Heroku, we simplify all of this choice and we are giving you an opinionated platform. So you can focus on building the application, using our developer tools to deploy, and then operating your application by using the tools we are giving you to scale your app, to monitor your app, to do the observability, and we take care of the rest. We take care of the infrastructure. We take care of the metrics, we take care of the support, and we give you the tools for you to scale and maintain the application.
And this is increasing developer productivity. This is reducing the money that you are spending on DevOps and infrastructure operation, and it is increasing the return of investment of your application.
Heroku Managed Inference and Agents: Live Demo of a Solar Energy Dashboard with AI-Powered Tools
So let me tell you about the different AI offerings that we announced and released this year, and this is why we became the AI Platform as a Service. First, we have Managed Inference and Agents. We allow you to provision AI models to an app just with one click or with one command. You can select from a list of curated AI models that allows you to do text generation, image generation, or embeddings with just one click. This is something that is available right now.
We recently launched support for Claude 4.5 Sonnet, for Claude 4.5 Haiku, Amazon Nova Lite, Amazon Nova Pro, and GPT-4o. We also added support for MCP, the Model Context Protocol, and this support is in two ways. We have a Heroku MCP server that allows developers and DevOps people to use our MCP that knows how to manage Heroku resources. So this is for builders, but we also have a platform for you to securely deploy MCP servers that you are building. You can deploy and host your MCP on Heroku and access that MCP remotely through an HTTP interface or directly from within the agent endpoint that we give you with the Managed Inference and Agents.
We also have support for vector database through pgvector, which is an extension of PostgreSQL to create vector databases to perform similarity search and create retrieval augmented generation pipelines. Back in October, we released the pilot of Heroku Vibes, which is a tool that allows you to build web applications using natural language from the web. This tool lets you build the app and deploy the app automatically to Heroku, so you don't even need to worry about the infrastructure behind. We are taking care of everything, and just with one prompt and a couple of adjustments if you want to iterate over it, you can have an application from an idea to production in minutes.
Let me show you a couple of demos that I have here that show you first the Heroku Managed Inference and Agents and how I built an application that uses Heroku AI to get access to data and to be able to perform smart actions within an application, and another example of Heroku Vibes which can let you build applications using natural language. I built this application, which is a dashboard for a solar energy company. Let's say you have a solar installation in your house or in your business and you want to monitor how much energy you are producing, how much energy you are consuming, what are going to be your savings, and get some insights about the application.
This dashboard already goes and accesses my PostgreSQL database that is deployed on Heroku and creates the dashboard, but this is your typical web application. I want to also ask questions using AI to get access to insights from my data. So how can I do this? Usually people build retrieval augmented generation pipelines, so you get data from the database, you pass that data to the inference model, and then you perform some inference on top of that data.
What we did here is that we are using agents. We have an agent using the Heroku endpoint and tools, tools that we maintain which are pretty much MCPs that are hosted and running on Heroku to give my agent access to the database. I am not giving my database credentials. I am just giving a read-only access to a follower of my database so I can safely retrieve data and analyze that data. Let me open the agent here. I already have two queries that I did, but I'm going to be doing something here live.
The first one, I asked about what was my lowest production day this month. So I want to know from all this month, what was the day that I had the lowest production. So it is performing a tool execution which is the database query. It's generating this query, so my agent already knows the shape of my database, but we also have tools to retrieve the schema of the database so it doesn't hallucinate the shape of your data. It's generating the query, it's running the query and giving me the response, and then the inference is taking care of the answer.
Essentially, we are feeding the context of my prompt with tools. For the next question, I want to chart or create an image of the hourly production data of today. The process is pretty much the same. I need to go to the database, but then how can I create that image? For that, I'm using another tool which is code execution. In this case, I'm using Python and Python dependencies to generate images like matplotlib, pandas, NumPy, and others to create the image on the fly. I'm uploading this image to Amazon S3 and then returning a pre-signed URL.
So we can see here that we have the database query. This is fetching the data hour by hour of the day. Then it's passing that data to a Python execution tool. Since you can run any application on Heroku, what we are doing here is generating this code. The LLM is generating this code, spinning up a dyno on Heroku, which is a virtual machine, running the code sandbox safely on Heroku, and getting the return. You are only consuming the seconds that the application was running. I get the return, which is the pre-signed URL on Amazon S3, and now I have the answer, which is the report and the analysis.
Let me trigger another prompt here. What was the peak production in the past seven days? Again, I need to use a tool to get this data. In this case, I am expecting that my agent, which I configured, is going to perform a database query, getting that data from the database and then doing an analysis over the data. So this is the query. It failed. Amazing. Now it is trying another query. Now it got the response, so you saw that it has a self-healing capability. This is not scripted, this is a live demo. It failed and now it got the data and created the report that I just asked on the fly.
How does this work? How do I provision this model to my application? This is an application that is deployed on Heroku. It's a Node.js application, an API that accesses the Heroku AI services. How can I provision these AI services as any other service on Heroku? I am on the Heroku dashboard. I'm on the resources tab, and I will search for Heroku Managed Inference and Agents. It will provide a list of the supporting models that we have. I can select the model. Let's say we want Claude 3.5 Haiku. I click on the order form provision.
Now I have the model available to my application. How can I access from my application to that model? Basically, this is giving me an API URL and an API key, and now I can use an SDK or directly perform an HTTP request to the inference endpoint and get the response. This is everything working on Heroku infrastructure, so your data is not going out to a third party. Everything is within the same infrastructure. It is staying safe and is trusted, getting access to the database.
If I go to the settings of my application and reveal the configuration variables, you might see here the different API keys and API URLs for the models I have provisioned. What I have to do in my app, I will show you the code. This is my agent. I have a system prompt. In the system prompt, I'm specifying this is what you do. You are a solar energy agent. This is the type of tools and libraries you have access to. As I mentioned, I'm giving access to the library to upload to S3, to do matplotlib and the charting in Python. I'm specifying everything here, being very, very specific.
After defining the prompt and the tools, you can see we have Heroku tools. These are tools that run on Heroku, not tools that I have to write. I'm giving access to the database to those tools.
And then what I'm doing is an HTTP request, just calling an API. I'm using the same OpenAI API shape, so if you are using an SDK that talks to that specific API, like for example, LangChain or the Vercel AI SDK or Pydantic LlamaIndex, depending on the technology of your choice for building agents, you can use Heroku AI for that.
Heroku Vibes: Building Applications from Natural Language Prompts
So now let me switch to the other AI tool that we are offering our people. This is more like pro development for developers, for builders that can use the services. This other one is more for business users, people that are not 100% technical, that they want to also build applications and deploy to Heroku, which is Heroku Vibes. So here on Heroku Vibes, I start from a prompt. I need to define the prompt of the application that I want this to build, so for this example, I'm going to be building an agenda builder for AWS re:Invent 2025. So I'm asking to create this agenda builder application so I want to track my sessions, store the information on local storage, but I can also store it on a PostgreSQL database on Heroku. It will take care of the backend, and I'm giving a data source, get the data from this CSV that lives on the internet.
And now I'm going to create that application. So there are a couple of things that are going to happen here. First, it's going to enter into plan mode. It's going to create a plan, a step-by-step plan of how the agent is going to build this application. You can approve the plan or suggest changes to that plan. And once you have that plan approved, it's going to start building. Since I just have two minutes in my presentation, I'm going to show you exactly this prompt and the whole process and a couple of iterations that I did changing this prompt and the final result.
So here you can see that I have a long conversation with the agent, but it started with the same exact prompt. I want my agenda builder, this is how I want it, this is where you are going to be storing the data, and this is where you are getting the data. It provides a plan, I approved the plan, and then it went and implemented the application. And since we are using Heroku here, it is deploying the application directly to Heroku.
So the application that I have here is the final result. It's living on Heroku, you can see the Heroku app domain, it is live, and I can just use it. I can just add sessions to my agenda. Go check the agenda, and that's exactly what I asked for. I then asked for some changes. For example, I want to have dark and light theme, or I want to change this color to be something different, or I want you to have a backend and store the information on a PostgreSQL database. And that's the iterative process that you are going to do with these AI tools to build an application and take it live just using a prompt and going to production.
So that's what Heroku has for you. One, which is the Heroku AI services for you to build custom agents and deploy them. And then we are giving you also a tool for building applications using AI that simplifies that process. That's pretty much it. Thank you so much. If you have any questions, we are located at booth 838 just right next by the Salesforce booth. You can go there, visit us, ask more about what we have for you to build AI applications and other types of applications. And also you can please complete the session survey on your mobile application, and thank you so much for coming.
; This article is entirely auto-generated using Amazon Bedrock.
Top comments (0)