Blog
Learn more about Dust, get product updates, AI agents best practices and more.
Introducing self-improving skills: reusable AI capabilities that learn from usage
Skills are one of the best ways to scale expertise across digital teams of humans and agents. They contain sets of instructions that encode various team...
How Dust runs Support on Dust
Dust Support evolved from a single @support agent to @Dust, powered by a Support skill. The flow looks like the following. Trust me, it’s simpler than you...
AI x Email: Your Agent Lives in Your Inbox
Dust recently shipped a feature that lets you loop any Dust agent into an email thread — just like you'd loop in a colleague. Forward a message to...
Product Update 23
Hi there, Describe what you want an agent to do. Watch it get built. That's Sidekick, a new AI co-pilot embedded in the Agent Builder that drafts instructions,...
An AE's Day Using Dust: What It Actually Looks Like
It's a Tuesday in March. Nic Siegle drops his dog off at daycare, pulls out his phone, and opens the Slack channel where his agents have been running since...
Your browser has a point of view
When we shipped the Chrome extension last year , it solved a real problem: getting Dust agents into the browser where most work actually happens. Select text,...
Build a Flock, Not a Crowd
The average person at Dust uses over 15 different agents in a week. Each one built by someone who understood a problem: the sales team's way of qualifying...
Product Update 21
Hi there, We've shipped some of our most powerful updates yet. Your agents can now learn new skills instantly (like Neo downloading kung fu), and you can...
Skills: Your entire agent fleet smarter, together
Introducing Skills The AI world gave us models: processors that generate, analyze, follow user’s instructions. We built the platform to let you build agents:...
AI Agents don't need to be Boxes and Lines
As companies rush to ship "AI agent building" products, we're seeing a familiar interface pattern emerge: visual workflow canvases with boxes, arrows, and...
System Prompt Learning: The feedback loop your agents are missing
Andrej Karpathy recently highlighted something important about the future of AI systems: "system prompt learning" matters more than fine-tuning for many...
From the Maker's Schedule to the Hive: Engineering at the Speed of AI
Coding agents keep getting stronger. First you run one on your branch. Then you want two in parallel, so you add a second checkout. Then four. Suddenly you're...