Blog
Learn more about Dust, get product updates, AI agents best practices and more.
MCP and the emerging enterprise AI OS layer
How MCP calls for a new kind of enterprise infrastructure for the upcoming synthetic workforce era. The Model Context Protocol (MCP) represents the...
Product Is Everyone's Job
Building an AI operating system to transform how work gets done requires a unique approach to product development. At Dust, we've built a culture where product...
Building with reasoning models: infrastructure requirements and verification loops
The AI landscape shifted in the last months with the emergence of reasoning-focused models. These models bring a fundamental change in how LLMs approach...
Spreadsheets, databases, and beyond: creating a universal AI query layer
In the world of AI agents, the ability to understand and analyze structured data is a game-changer. While large language models excel at understanding natural...
First Engineering Night at Dust
We hosted our first Engineering Night in Paris on Feb. 12th bringing together over 80 AI engineers and researchers from across Europe for technical...
Dust Product Update 11
Hi there, We've shipped new AI models (Sonnet 3.7 and o3-mini), label filtering, and a new BigQuery Connection to make your agents smarter and more precise....
Build in Person
Engineering an AI operating system that transforms how work gets done requires deep collaboration and rapid iteration. At Dust, we've made the deliberate...
New reasoning capabilities: o3-mini now available in Dust
We've integrated OpenAI's latest reasoning model, o3-mini into Dust as a capability for asssistants. Why as a capability? While these models excel at deep...
Dust Product Update 10
Hi there, We've shipped several features to help you work more efficiently with your Dust agents: advanced reasoning capabilities for complex use cases,...
Permissions in the age of AI-driven companies
As AI agents become more autonomous and capable, we're discovering that traditional approaches to permissions and access control break down. At Dust, we're...
DeepSeek-R1 and the future of AI reasoning
The AI landscape was shaken last week with the emergence of DeepSeek, particularly its R1 model. What makes this development especially significant isn't just...
Building better workflows: the Dust Chrome extension
The average team switches between 93 different applications daily[1], fragmenting knowledge and interrupting workflows. This makes it harder for team members...
Further reading
- 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
- What is an AI sales agent? (And how to build one in 2026)March 18, 2026
- AI ticketing system: What it is and how it works (2026)March 18, 2026