Blog
Learn more about Dust, get product updates, AI agents best practices and more.
Which AI model should you choose for a Dust agent? Our 2026 guide
💡 This is the updated version of our original 2024 model comparison guide . When we first wrote about this in May 2024, the options available in Dust felt...
The Single-Model Trap: Why AI Platforms Need Multiple Providers
Most AI platforms bet on a single model provider. We bet on the free market. This isn't just philosophy. Over the past three years, we've built Dust around a...
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...
The Era of AI Operator
Something is shifting inside the fastest-moving companies. A new kind of role is appearing on org charts, sometimes with a formal title, sometimes without one...
From Evaluation to Maintenance
An agent that works well today can start producing different results next week. Not because someone pushed a code change, but because the knowledge it queries...
Product Update 22
Your agents just got write access to Google Drive, real-time observability in the Builder so you can see exactly what's happening under the hood, and...
Why you need an Agent Management Platform
Want just the recap? Take a look at this: Frame After two years deploying AI agents with customers ranging from industrial firms to leading AI companies, we've...
Introducing the Dust Academy
At Dust, we've spent years obsessing over how AI can transform team productivity. We've built connections, agents, and workflows that let organizations...
Field study: Prototypes over mockups
A practical guide to designing with code in 2026 Someone drops a link in a thread — not a deck, not a Figma file — something you can click through, interact...
The Customer Success paradox: why the most human function needs AI most
Customer Success sits at a fascinating crossroads. It's a role that demands deep empathy, strategic thinking, and relationship building: fundamentally human...
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:...
Engineering Hiring Process at Dust
Building the Operating System for AI Agents that transforms how work gets done requires exceptional engineers. Here's what our hiring process looks like, and...
Further reading
- AI agent vs Chatbot: Key differencesMarch 13, 2026
- AI agents examples with Dust: Use cases across different teamsMarch 13, 2026
- AI agents for data analysis: Real use casesMarch 13, 2026
- What is data sovereignty and why it matters for enterprise AIMarch 13, 2026
- How to automate your Dust agents with workflow tools (2026)March 11, 2026
- Can you get an AI platform that integrates various language models?March 11, 2026
- Enterprise AI search in 2026: What you need to knowMarch 11, 2026
- Agentic AI vs AI agents: A clear breakdownMarch 11, 2026
- Dust is now on viaSocketMarch 10, 2026
- AI agents for business automation: Everything you need to knowMarch 6, 2026