Heroku Blog
- News
- Last Updated: May 29, 2025
- Anush DSouza
Anthropic’s Claude 4 Sonnet, part of the next generation of Claude models, is now available on Heroku Managed Inference and Agents. This gives developers immediate access to a model designed for coding, advanced reasoning, and the support of capable AI agents. Heroku Managed Inference and Agents expands your AI choices, offering the freedom to build transformative applications with the developer and operational ease Heroku is known for. Claude 4 Sonnet extends what’s possible with AI systems by improving task planning, tool use, and overall agent experience within the Heroku ecosystem.
Claude 4 Sonnet offers a significant leap in performance, …
- Engineering
- Last Updated: May 27, 2025
- Alex Arnell
Heroku recently made the next generation platform – Fir – generally available. Fir builds on the strengths of the Cedar generation while introducing a new modern era of developer experience. Fir leverages modern cloud-native technologies to provide a seamless and performant platform.
One of the goals we set out to achieve with Fir is to modernize our platform’s observability architecture. Applications being written today are becoming increasingly more distributed and complex in nature. With this increase in complexity, the need for good observability becomes critical. With solid observability practices in place, it becomes possible to gain deep insights into the …
- Engineering
- Last Updated: May 22, 2025
- Ken W. Alger
The speed and efficiency of the Go programming language make it popular for backend development. Combine Go with the Gin framework—which offers a fast and minimalistic approach to building web applications—and developers can easily create high-performance APIs and web services. Whether you’re working on a personal project or building a production-ready application, Go and Gin make for an attractive stack perfectly suited for lightweight, scalable web development.
Creating a Go/Gin application might seem straightforward: You write a few routes, connect a database, and spin up a local server. But when it comes to deploying your app, things can get …
- Engineering
- Last Updated: May 21, 2025
- Andrew Fawcett
SignalR makes it easy to add real-time functionality to .NET web applications—things like live chat, instant notifications, or interactive dashboards. But what happens when your app starts to grow? A single server can only take you so far. At some point, you’ll need to take advantage of SignalR scaling features to scale out your app.
In this post, we’ll walk through what it takes to scale a SignalR app to run across multiple servers. We’ll start with the basics, then show you how to use Redis as a SignalR backplane and enable sticky sessions to keep WebSocket connections stable. And …
- News
- Last Updated: May 15, 2025
- Anush DSouza, Rand Arete
Many of the most exciting experiences we’re beginning to rely on every day are powered by AI; whether it’s conversational assistants, personalized recommendations or code generation, these experiences are powered by inference systems and intelligent agents. Behind the scenes, developers offload complex decisions, automate tasks, and compose intelligent applications using large language models and tool execution flows. Together, these AI-powered primitives are becoming a key complement to traditional application development, enabling a new wave of developer capabilities.
At Salesforce, we are helping our customers bring their agentic strategy to life with Heroku, Agentforce, and Data Cloud. These powerful …
- News
- Last Updated: May 15, 2025
- Gautam Rangarajan, Anush DSouza
Agents hold immense power, but their true potential shines when they connect to the real world, fetching data, triggering actions, or leveraging external tools. The Model Context Protocol (MCP) offers a standardized way for AI agents to do this.
MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI applications. Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools.
Subscribe to the full-text feed.