Product - Dust

Product

A collection of 31 posts

Introducing Triggers: Your agents, working while you sleep

Introducing Triggers: Your agents, working while you sleep

What if your AI agents didn't wait to be asked? Today, we're introducing Triggers: turns Dust agents from on-demand agents into autonomous workers. Schedule agents to run automatically, trigger them from external events, and let them write back to your systems; no human initiation required. Triggers

Dust Product update 18

Dust Product update 18

Hi there, We've been busy! This month brought some of our biggest updates yet: interactive Frames for data that comes alive, Deep Dive for research that goes the distance, Voice input for when typing just won't cut it. Plus we've expanded into Confluence and

Building Deep Dive: Infrastructure for AI Agents That Actually Go Deep

Building Deep Dive: Infrastructure for AI Agents That Actually Go Deep

When we started noticing patterns in our agent logs back in May 2025, something caught our attention. Users were asking agents for comprehensive, multi-step tasks, expecting depth, but they were getting surface-level answers or context window errors instead. More interesting: the agents were trying to help, spontaneously inventing filesystem-like syntax

Introducing Frames: Interactive data, visualized

Introducing Frames: Interactive data, visualized

What if your reports could handle the follow-up questions? Today, we're introducing Frames: a new way to transform Dust agents’ conversations into interactive content your team can customize, share, and collaborate on together. Reports have traditionally been one-way communications: you create them, send them, and hope people engage.

Dust Product update 17

Dust Product update 17

Hi there, We've shipped significant improvements to Dust this month. Schedule your agents to run automatically, build agents that run reliably for extended periods, and access tools and data across multiple spaces. Plus major expansions to our tool integrations across your entire workflow. Companies are moving from "

Dust Product update 16

Dust Product update 16

Hi there, We've shipped significant improvements to Dust this month. Build with GPT-5, create agents that can remember your preferences and past interactions across conversations. Ask your agents to post to Slack channels, create Linear issues, and manage your Outlook inbox directly. Here's what's

Agent Memory: Building persistence into AI collaboration

Agent Memory: Building persistence into AI collaboration

When we built Dust, we solved a fundamental problem: AI agents that start from zero. Custom agents with access to curated company knowledge meant every employee could create specialized AI that understood their context from day one. Today, we're pushing this vision further with agent memory, transforming agents

Supercharge your sales with MCP tools in Dust

Supercharge your sales with MCP tools in Dust

Our latest Session for Builders showcased the game-changing potential of MCP for sales teams. Instead of outdated, rigid automation, MCP brings intelligent, AI-first solutions that seamlessly integrate with your existing sales tools. Missed the session? Don't worry—watch the replay now and dive deeper into transforming your sales

Dust Product update 15

Dust Product update 15

Hi there, We've shipped significant improvements to Dust this month. Your agents can now create email and calendar invites, be chained together for complex workflows, and integrate with Salesforce, HubSpot, and Notion in new ways. Here's what's new in Dust. Connect your Gmail or

How We Taught AI Agents to Navigate Company Data Like a Filesystem

How We Taught AI Agents to Navigate Company Data Like a Filesystem

Dust built synthetic filesystems that map disparate data sources into navigable Unix-inspired structures. This transforms AI agents from search engines into knowledge workers capable of both structural exploration and semantic investigation across company data.

Give Dust Agents Access to Your Internal Systems with Custom MCP Servers

Give Dust Agents Access to Your Internal Systems with Custom MCP Servers

The Model Context Protocol (MCP) is revolutionizing how AI agents interact with external systems, and Dust is at the forefront of making this technology accessible to everyone. In our last Dust session for builders, we demonstrated how MCP transforms the way you can create and deploy AI agents that take

Dust is better at company data

Dust is better at company data

Word is on the street that for AI agents to be useful at work, they should be plugged to your company data. But when an AI agent provider says it's ‘plugged to your company data’ it actually doesn't mean anything. It's like saying a

Dust Product update 14

Dust Product update 14

Hi there, We've introduced significant improvements to Dust. You can now build with Claude 4 Sonnet, discover agents through our enhanced tagging system, and connect to any MCP-compatible server with our standardized foundation. These updates make your agents more powerful and easier to work with. Here's

Dust Product update 13

Dust Product update 13

Hi there, We've made it easier to access your knowledge directly in conversations, added OpenAI and Gemini's latest models, and released a beta version of our Salesforce Connection. We're previewing exciting new tools that expand what your agents can do. Here's what&

Introducing Attach from Knowledge

Introducing Attach from Knowledge

We're launching a powerful upgrade to how you interact with your company's knowledge in Dust. Now you can instantly search and attach documents, tables, or entire folders from your data sources, directly in conversations. No more downloads, uploads, or context switching. Direct access to your company

Gong connection

Dust Product Update 12

Hi there, We've introduced a new Gong Connection, keyword search in the agent builder, smarter label filtering, and better markdown support to make your agents more powerful and easier to work with. Here's what's new in Dust. Gong Connection Connect Gong call transcripts to

Spreadsheets, Databases, and Beyond: Creating a Universal AI Query Layer

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 language, they struggle with quantitative analysis when data is presented as unstructured text. This is where Query Tables comes in – a powerful feature that enables

Product Update 11

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. Here's what's new in Dust. Try Claude 3.7 Sonnet Anthropic’s first hybrid reasoning model is

New reasoning capabilities: o3-mini now available in Dust

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 reasoning, they're not optimal as standalone conversational agents. That's why we've made O3-mini available primarily as

Dust Product Update 10 - Reasoning Tools, meeting transcripts, feedback loop,

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, Deepseek in Dust, agent user feedback loop, new files formats and more! Here's what's new in Dust. 🧠 🧠 Advanced reasoning capabilitiesWe'

Permissions in the age of AI-driven companies

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 building the foundational layer to handle these new requirements. Let me explain why this matters and how we're approaching it. The

Building better workflows: the Dust Chrome extension

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 to collaborate and work as one and means the browser is often a central hub for cross-app work. We’re introducing a Chrome Extension to bring Dust agents

Product Update 9 - Sync Private Slack Channel - Data Tools

Dust Product Update 9

Hi there, We've shipped several new capabilities to help you work more efficiently with your Dust agents. Here's what's new: 💬 Sync Private Slack Channels You can now synchronize private Slack channels with Dust: * Add the Dust bot to your private channel * Admins will see

Product Update 8 - Spaces - Snowflake

Dust Product Update 8

We're thrilled to introduce platform improvements that enhance team collaboration and make your work easier: refined data management with spaces, new transcript storage capabilities for Google Meet and Gong, and Snowflake integration for database queries. We've also added visualization downloads, agent favorites, and improved incident reporting.

Product Update 7 - @help assistant - Make Integration

Dust Product Update 7

Hi there, We're excited to introduce enhancements that boost productivity and expand Dust's reach. Our updated @help and @dust agents now provide precise support with direct documentation access and targeted data searches. We've streamlined conversation management and integrated Dust with Zendesk and Make.com,