How Dropbox is moving from AI tools that assist engineers to agentic systems that can execute scoped tasks, and how we’re building platforms to support those workflows.
#agents
12 posts
28 May
19 May
Cloudflare has integrated with Anthropic's Claude Managed Agents to provide a fast, isolated execution environment for autonomous code delivery. This means builders can scale agent workflows globally while strictly controlling access to private backends and easily customizing their agent’s tools and runtimes.
18 May
In recent weeks, we pointed Mythos and other security-focused LLMs at live code across critical parts of our infrastructure. We share what we observed, the models’ strengths and weaknesses, and what the work around them needs to look like before any of it can scale.
6 May
Build durable AI agent workflows with the Microsoft Agent Framework. Start with in-process console apps, add durability with the Durable Task runtime, scale with parallel AI agents, and host on Azure Functions for serverless execution. The post Durable Workflows in the Microsoft Agent Framework appeared first on .NET Blog.
29 Apr
Learn how to govern MCP tool calls in .NET with the Agent Governance Toolkit—policy-based access control, security scanning, and response sanitization to reduce risk in AI agent systems. The post Governing MCP tool calls in .NET with the Agent Governance Toolkit appeared first on .NET Blog.
16 Apr
Last week, we launched Docker Sandboxes with a bold goal: to deliver the strongest agent isolation in the market. This post unpacks that claim, how microVMs enable it, and some of the architectural choices we made in this approach. The Problem With Every Other Approach Every sandboxing model asks you to give something up. We...
31 Mar
Agents have crossed a threshold. Over a quarter of all production code is now AI-authored, and developers who use agents are merging roughly 60% more pull requests. But these gains only come when you let agents run autonomously. And to unlock that, you have to get out of the way. That means letting agents run...
19 Mar
Learn how custom-built AI agents are dramatically improving the .NET MAUI contribution workflow, reducing issue resolution time by 50-70% while increasing test coverage and code quality. The post Accelerating .NET MAUI Development with AI Agents appeared first on .NET Blog.
13 Mar
Agents have enormous potential to power secure, personal AI assistants that automate complex tasks and workflows. Realizing that potential, however, requires strong isolation, a codebase that teams can easily inspect and understand, and clear control boundaries they can trust. Today, NanoClaw, a lightweight agent framework, is integrating with Docker Sandboxes to deliver secure-by-design agent execution....
4 Feb
Every time execution models change, security frameworks need to change with them. Agents force the next shift. The Unattended Laptop Problem No developer would leave their laptop unattended and unlocked. The risk is obvious. A developer laptop has root-level access to production systems, repositories, databases, credentials, and APIs. If someone sat down and started using...
28 Oct 2025
Introducing C# Expert and WinForms Expert: experimental custom agents that help .NET developers write better code with GitHub Copilot. The post Introducing Custom Agents for .NET Developers: C# Expert & WinForms Expert appeared first on .NET Blog.
1 Oct 2025
Microsoft Agent Framework (Preview) unifies agent creation, orchestration, tooling, hosting, and observability so any .NET developer can ship production AI agents faster. The post Introducing Microsoft Agent Framework (Preview): Making AI Agents Simple for Every Developer appeared first on .NET Blog.