Blog
Learn more about Dust, get product updates, AI agents best practices and more.
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,...
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...
Further reading
- Top AI Agent tools in 2026 (And when you need a platform)April 2, 2026
- Microsoft Copilot Agents: What they do and When your team needs moreApril 1, 2026
- Agentic AI vs Generative AI: What is the key difference? April 1, 2026
- Structured vs Unstructured Data: What it means for your AI agentsMarch 27, 2026
- Claude Code agents: Everything teams need to know before choosingMarch 27, 2026
- RAG vs Fine-Tuning: Key differences and when to use eachMarch 25, 2026
- AI agents for enterprise: What they do and how companies deploy them March 24, 2026
- RAG vs LLM: The difference and why they're better togetherMarch 23, 2026
- AI agents for project management: Key capabilities, use case, and PM tool comparisonMarch 20, 2026
- AI email agent: How to draft emailsMarch 18, 2026