In Docker Desktop 4.44, we’ve focused on delivering enhanced reliability, tighter AI modeling controls, and simplified tool integrations so you can build on your terms.

Docker Model Runner Enhancements 

Inspectable Model Runner Workflows

Now you can inspect AI inference requests and responses directly from Docker Model Runner (DMR), helping you troubleshoot and debug model behavior quickly.This feature brings transparency and debugging capabilities to AI workflows and provides a major

Just published by Docker: Read more

This is Part 3 of our MCP Horror Stories series, where we examine real-world security incidents that validate the critical vulnerabilities threatening AI infrastructure and demonstrate how Docker MCP Toolkit provides enterprise-grade protection.
The Model Context Protocol (MCP) promised to revolutionize how AI agents interact with developer tools, making GitHub repositories, Slack channels, and databases as accessible as files on your local machine.But as our Part 1 and Part 2 of this series demonstrated, this seamless integration has created unprecedented attack surfaces that

Just published by Docker: Read more

What That Means for Devs and AI App Companies

When GPT-5 dropped, OpenAI killed off a bunch of older APIs without much warning.A whole lot of apps face-planted overnight.If your app hard-codes itself to one provider, one API shape, or one model, this is the nightmare scenario.This is also different from losing a service because most AI applications are not just the AI but also stacks of prompts, training, and other customizations on top.Remove or modify the primary AI service and the Jenga tower

Just published by Docker: Read more

Building AI agents can be a complex task.But it also can be a fairly simple combination of answers to the following questions: 

What is the AI backend that powers my intelligent fuzzy computation? What tools do you need to give to the AI to access external systems or execute predefined software commands? What is the application that wraps these together and provides the business logic for the agent (like when you’re building a marketing agent, what makes it know more about marketing

Just published by Docker: Read more

There’s a weird contradiction in modern AI development.We have better tools than ever.We’re building smarter systems with cleaner abstractions.And yet, every time you try to swap out a component in your stack, things fall apart.Again. This isn’t just an inconvenience.It’s become the norm. You’d think with all the frameworks and libraries out there (LangChain, Hugging Face, MLflow, Airflow) we’d be past this by now.These tools were supposed to make our workflows modular and composable.Swap an embedding model?No problem.

Just published by Docker: Read more