ChatGPT Enterprise brought conversational AI to work, but it doesn't connect deeply to your company's tools, locks you into one AI model, and takes a...

ChatGPT Enterprise Alternatives: Best AI Platforms for Business (2026)

Your sales team is drowning in admin work. Between CRM updates, prospect research, meeting prep, and follow-ups, actual selling happens in the margins. Sound...

How To Use AI For Sales In 2026

You ask your AI assistant a question. The response comes back generic, vague, or completely missing the point. You rephrase and try again. Same problem. The...

How To Write AI Prompts In 2026

Sales reps often spend a large portion of their day on activities that aren't directly selling. Research, data entry, switching between tools, and hunting for...

AI for Sales Prospecting: How it works and Why it matters in 2026

AI agents are transforming how businesses work in 2026. Unlike chatbots that simply answer questions, AI agents can independently complete tasks, make...

How To Build An AI agent (2026)

Content marketing teams face a scaling problem. You need more content across more channels, but resources stay flat. Most AI tools help with individual tasks...

How AI Agents Transform Content Marketing (2026)

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...

Field study: Prototypes over mockups

Manus is an autonomous AI agent that builds full-stack applications, mobile apps, and presentations from single prompts. Users describe what they need, and...

Top Manus Alternatives for Building Apps (2026)

Workflow automation platforms help teams connect apps and automate processes, but not every tool fits every team's needs. Whether you're evaluating n8n...

n8n alternatives for workflow automation (2026)

Customer Success sits at a fascinating crossroads. It's a role that demands deep empathy, strategic thinking, and relationship building: fundamentally human...

The Customer Success paradox: why the most human function needs AI most

Google's NotebookLM has become a popular tool for analyzing documents using AI. Users upload PDFs, research papers, or notes, and the AI generates summaries,...

Top Notion AI alternatives for AI-powered workspace automation (2026)

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...

Product Update 21

TL;DR The top alternatives for Copilot Studio are: Dust: No-code AI agent platform with cross-platform data connections, LLM-native actions, and $29/user/month...

Top Microsoft Copilot Studio alternatives for building custom AI agents (2026)

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:...

Skills: Your entire agent fleet smarter, together

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...

Engineering Hiring Process at Dust

What is enterprise search? Enterprise search is AI-powered software that helps employees find information across all company systems. It searches through...

Top Glean alternatives for AI-powered enterprise search (2026)

As companies rush to ship "AI agent building" products, we're seeing a familiar interface pattern emerge: visual workflow canvases with boxes, arrows, and...

AI Agents don't need to be Boxes and Lines

Andrej Karpathy recently highlighted something important about the future of AI systems: "system prompt learning" matters more than fine-tuning for many...

System Prompt Learning: The feedback loop your agents are missing

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...

From the Maker's Schedule to the Hive: Engineering at the Speed of AI

Build vs Run and zero-sumness: a simple framework to reason about how to scale teams post artificial intelligence abundance. Will AI annihilate all...

Build vs Run

When we started building Dust, we saw a future where AI agents work alongside humans. But here's what we learned from watching how teams actually use Dust: the...

Mentions: Collaborate better, together

The AI world moved fast in 2025, but the Dust team moved faster . We started 2025 with a vision: a shared space where teams across your organization work...

2025 Dust Product Update Recap

One product manager edited 560 AI agents in 2025. He's not a software engineer, and he's not alone. Across Dust this year, something transformational happened....

Dust 2025 Wrapped: 80,000 Agents, 12 Million Conversations (and other wild stats)

When we started seeing customers ask about voice capabilities—first a few scattered requests, then a steady pattern—we knew we needed to move beyond...

Why Dust incorporated voice mode in its Agent Management Platform

Hi there, We've shipped significant improvements to Dust this month. Your agents now work autonomously with Triggers and Builder Observability lets you see...

Product Update 19

💡 Key results: - 70% employee adoption and 136 deployed AI agents within 2 months of launch - 50% reduction in legal contract analysis time - Dramatic...

The complete guide to implementing AI Agents: lessons from Wakam, leading European insurer

When it comes to AI agents, every leadership team eventually faces the same question: should we build this ourselves or buy a platform? It's a familiar debate....

Build vs. buy AI agents: What 1,000+ enterprise deployments taught us about the real costs

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...

Introducing Triggers: Your agents, working while you sleep

This article was written by Aaron Horwath, Director of AI Operations at Creative Force . Creative Force is an end-to-end software platform for managing content...

How Creative Force Is Using Dust to Help Define “The Future of Work”

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...

Dust Product update 18

https://www.youtube.com/embed/mDwg9N2WAmM?feature=oembed When we started noticing patterns in our agent logs back in May 2025, something caught our attention....

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

Hi, I'm Sophie. I work at Dust to help expand it in the UK. I spent 8 years in London - from university through my early career - and the city's tech scene has...

Why UK AI pilots struggle to scale and what companies need instead

Why non-poaching agreements hurt everyone in the French tech ecosystem The French tech ecosystem has been maturing rapidly over the past few years. Yet some...

Let the Free Market Win

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...

Introducing Frames: Interactive data, visualized

Hi there, We've shipped significant improvements to Dust this month. Schedule your agents to run automatically, build agents that run reliably for extended...

Dust Product update 17

We're excited to share some big news: Dust is now available on Google Cloud Marketplace! This means our customers can now access our AI agent platform directly...

Dust is live on Google Cloud Marketplace

Eric Glyman, CEO of Ramp recently commented that " autonomous finance is being built right now. " What Eric’s seeing in finance teams is just one instance of a...

Companies are building their Agent OS right now. Are you?

I’ve never envied AI software buyers less. AI is amorphous, the landscape changes weekly, and there’s no established playbook for what an AI‑first organization...

The easy wins AI-first GTM teams have already implemented

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...

Dust Product update 16

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...

Agent Memory: Building persistence into AI collaboration

Our latest Session for Builders showcased the game-changing potential of MCP for sales teams. Instead of outdated, rigid automation, MCP brings intelligent,...

Supercharge your sales with MCP tools in Dust

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...

Dust Product update 15

In April 2025, something kept showing up in our logs. Our AI agents were inventing their own syntax for searching content — file:front/src/some-file-name.tsx ,...

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

The Model Context Protocol (MCP) is revolutionizing how AI agents interact with external systems, and Dust is at the forefront of making this technology...

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

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...

Dust is better at company data

🏆 25+ teams spent their Friday at Qonto 's Paris office, hacking on agent-focused projects in all shapes and sizes. Special focus on the winners. If you’re...

AI agents hackathon winners

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...

Dust Product update 14

At Dust, we're building an AI operating system to transform how work gets done. We connect company infrastructure to AI capabilities, bringing intelligent...

Interviews at Dust

https://www.youtube.com/embed/RNcXWPCaLqg?feature=oembed Most companies sit on disconnected data silos – warehouses filled with business metrics, spreadsheets...

Beyond Dashboards: How Natural Language Queries Unlock Organizational Context

The Founder's Dilemma Every founder faces moments of doubt. For me, the persistent challenge has been reconciling the years of effort we've poured into Dust...

Dust for Dust

The Model Context Protocol (MCP), created by Justin Spahr-Summers and David Soria Parra at Anthropic, has emerged as a popular standard for how AI models...

MCP and Enterprise Agents: Building the AI operating system for work

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...

Dust Product update 13

Last Wednesday, we hosted our second Engineering Night in Paris, bringing together technical folks for discussions and connection! The event featured three...

Engineering Night #2: All things LLMs

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...

Introducing Attach from Knowledge

Discover the practical implications of the MCP protocol on Dust's capabilities . Today's businesses use various AI tools across departments - engineering teams...

How MCP-powered Dust agents will complete tasks for you

We recently completed a significant infrastructure project that reorganized how data flows through our infrastructure. This behind-the-scenes work lays the...

Behind-the-curtains: how we conducted our first major architecture transition with no downtime

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...

Dust Product Update 12

How MCP calls for a new kind of enterprise infrastructure for the upcoming synthetic workforce era. The Model Context Protocol (MCP) represents the...

MCP and the emerging enterprise AI OS layer

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...

Product Is Everyone's Job

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...

Building with reasoning models: infrastructure requirements and verification loops

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...

Spreadsheets, databases, and beyond: creating a universal AI query layer

We hosted our first Engineering Night in Paris on Feb. 12th bringing together over 80 AI engineers and researchers from across Europe for technical...

First Engineering Night at Dust

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....

Dust Product Update 11

Engineering an AI operating system that transforms how work gets done requires deep collaboration and rapid iteration. At Dust, we've made the deliberate...

Build in Person

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...

New reasoning capabilities: o3-mini now available in Dust

Hi there, We've shipped several features to help you work more efficiently with your Dust agents: advanced reasoning capabilities for complex use cases,...

Dust Product Update 10

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...

Permissions in the age of AI-driven companies

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...

DeepSeek-R1 and the future of AI reasoning

The average team switches between 93 different applications daily[1], fragmenting knowledge and interrupting workflows. This makes it harder for team members...

Building better workflows: the Dust Chrome extension

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...

Dust Product Update 9

We're thrilled to introduce platform improvements that enhance team collaboration and make your work easier: refined data management with spaces, new...

Dust Product Update 8

This story is brought to you by Stanislas Polu, co-founder of Dust I recently had the opportunity to share Dust's journey on the Open Source Startup Podcast,...

Reflections on Dust's Journey: Insights from the Open Source Startup Podcast

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...

Dust Product Update 7

We've added new features to Dust: a Microsoft SharePoint Connection, updated documentation, image processing for Anthropic models, and data visualization...

Dust Product Update 6

Hey Dust community! We've got some big news.Dust has always been about making work work better. Our platform lets teams create custom AI agents using top-notch...

How Marketing and Engineering Teams Can Use Vision with Dust

We've been working on some new features and improvements at Dust: Dust can now see, you can drag and drop files when you chat and ask questions in our...

Dust Product Update 5

We recently held our second edition of Dust’s session for Builders—thanks to the 150+ builders who watched! Daphné Popin (software engineer) and Stanislas Polu...

From Single Action Towards Tools

Dust raises $16m in additional funding led by Sequoia and passes $1m ARR with 70% WAU/MAU. Founded in February 2023, Dust’s mission is to get work to work...

Dust accelerates fast-moving companies with teams of specialized agents

We've been hard at work improving Dust to help you work smarter with AI agents. We're thrilled to unveil Multi-Tool agents , a feature that fundamentally...

Dust Product Update 4

Dust agents can now pick and choose from several tools, thinking in steps in order to best answer user queries. We’ve also expanded the list of tools that can...

Introducing: multi-tool agents

This story is brought to you by Thibault, part of the Business Operations team at Dust. Since starting at Dust 1 month ago, I've found our product invaluable....

How the Data Team Uses Dust at Dust

Have you ever wished you could organize all your written knowledge in a structured way ? I'm talking about Slack discussions, support tickets, customer...

Extract Structured Data from Unstructured Sources with AI

One of the most frequent questions we get is: “Which AI model should I choose when creating my agent?”. It’s a great question, and based on our experience...

Choosing the Right AI Model for Your Dust Agent

GPT-4o - OpenAI's newest frontier model - is now available on Dust and we’ll be fast following with support for Google’s Gemini 1.5 Pro. We also released new...

Dust Product Update 3

At Dust, we've always believed that building the right product layer is the path to unlocking the full potential of large language models (LLMs). While...

Using Multiple AI Agents: A Pioneer's Perspective

At Dust, our goal is to let you add AI to your company's life by making sure you get accurate answers from LLM models using your data. For that, we're building...

Easily add AI to your Zendesk Help Center - Dust Apps Example #1

We held our very first Dust's Session for Builders a month ago, an exciting gathering of the Dust Builder Community. This event was an opportunity for builders...

Builders Session #1

Hi there, Dust’s mission is to make work "work better" by enabling anyone to equip themselves with generative AI, without needing to rely on engineers. Here's...

Dust Product Update 2

Hi! Dust makes work work better with custom AI agents. The past month has been packed with powerful new features and upgrades. ⛵️Mistral Large Now Available •...

Dust Product Update 1

Dust's latest capability, structured data analysis with table queries, marks a significant leap forward to help anyone in the company make the most of data....

How Dust's Table Queries are Changing the Game for Quantitative Analysis with LLMs

In this article, I'll expose the core motivations behind building Dust , how we believe the generative AI ecosystem will evolve and why we are building...

Why Dust?

2023 was a year of exciting exploration for many teams as they sought to understand the capabilities of generative AI (“GenAI”) and the impact it could have on...

Happy Acceleration in 2024!

The convergence of models' interfaces on the Chat Message API as well as the global push toward larger context sizes opens an interesting opportunity to...

A fair comparison of modern models' reasoning capabilities

Stay on top of key projects with a custom Dust agent. From rolling out Dust and agents across companies, we've seen tremendous value in creating AI agents that...

Build an AI Agent to Track Internal Project Status

Take the load off your data analysts with a Dust agent specialized in SQL. From wide-scale rollouts, we've seen immense value in AI agents that automatically...

Automate SQL Query Generation with a Custom Dust Agent

Based on our experience rolling out Dust agents to augment our users’ customer service teams, we’ve compiled below some best practices to serve this use case...

Boost Customer Satisfaction with Custom AI agents

Dust is an AI-native company based in Paris, France. We’re excited to share that we’ve raised €5M in seed funding led by Sequoia Capital with participation...

Announcing our seed round

Behind the beautiful name of Speculative sampling lies a neat technique to have a large language model generate tokens up to three times faster 🔥 The...

Speculative sampling: LLMs writing a lot faster using other LLMs

The opportunity opened by Large Language Models (LLMs) is vast. It’s allowed the birth of Dust, an AI-native company that wants to make work “work better” for...

Blog

Dust Product Update 2

Dust Product Update 1