Dust brings all the power of AI to me in the same tool. I don't have to ask myself between wich LLM I choose choose or pay for, Dust give me access to all of them and will adapt them depending on my AI agents' needs. Its integration to all of my different knowledge sources and tools makes it vert personalized and give context to our AI agents. There support are reactive and the Onboarding is very efficient. Shout out to Gaëlle from the Parisian team, she has been incredible to get us started and make sure we take the most out of the tool. In terms of pricing, I have to admit that it's getting confusing at the moment are they are switching to a "usage price" and will let you chosse between two different option (per seat or credit pool). The interface is clear enough, the fact that the LLMs and agents are running on a server and not on your machine let you benefit from the power of AI without having to get a super powerful machine nor to keep your laptop on all the time.

I lead a Product Analytics team, and Dust has genuinely changed how we handle our day-to-day work from initial data discovery and generating quick visualizations to full analysis automation. Our analytics agents now actively partner with our analysts to help confirm hypotheses with data. What stands out to me is how easy it is to get started without sacrificing depth. You can build a simple agent in just a few minutes, but the platform is flexible enough to handle advanced use cases using Schedules, Frames, Pods, and MCP connectors. The MCP setup in particular has been huge for us: we've connected Dust to a lot of our internal tools using both native connectors and custom MCPs. Another major differentiator is collaboration. While most AI tools focus strictly on individual productivity, Dust actually makes it easy for a whole team to work together.

Dust makes it genuinely easy to build agents. You can go from an idea to a working assistant in minutes, without needing engineering help. The connector and MCP ecosystem is a big part of that. Plugging into our existing tools meant our agents actually had the context they needed to be useful for support and RevOps work. On top of that, the value for money is hard to beat compared to other platforms we looked at.