An enterprise AI assistant and agent platform connected to company knowledge and collaboration tools.
An enterprise AI assistant and agent platform connected to company knowledge and collaboration tools.
Dust is an AI tool in the enterprise AI category, profiled from its public website at https://dust.tt and, where available, its pricing page. The fetched pages describe it around these concrete capabilities: Dust pages describe multiplayer AI for human-agent collaboration, custom agents that execute actions, connections to tools such as GitHub, Notion, Slack, MCP for proprietary systems, webhooks, OAuth2, Chrome extension, frames, and enterprise readiness.. That makes it most useful when a team wants an operational tool rather than a demo: company knowledge agents, department assistants, secure internal AI workflows. For builders, the main value is speed. Instead of starting from a blank editor or a loose prompt, users get a product surface with opinionated workflows, integrations, collaboration controls, or production-ready exports. For business users, the important question is whether the tool fits an existing process. This profile therefore emphasizes what the vendor page actually exposed: visible feature language, plan names, limits, security posture, and integration claims. Pricing observed in the fetched HTML: Pro: 29€/user/month excl. tax; Enterprise: Custom. If a plan is marked custom or omitted, it means the run did not extract a dependable amount from the vendor page. MCP compatibility is a practical part of this profile: Dust homepage text explicitly mentions MCP for proprietary systems, indicating agents can connect to MCP-exposed internal tools. In practice, evaluate Dust by running a small pilot with real data, checking export paths, admin controls, and whether usage limits map to normal work rather than only a toy example. It is especially worth testing the edge cases: permissions, handoff to humans, generated-output editing, and cost growth under repeated AI usage. The profile is intentionally conservative: if the site was JavaScript-heavy, blocked, or showed only marketing copy, this file flags manual verification instead of inventing missing details. Overall, Dust appears best suited to teams that want measurable productivity gains from AI while keeping enough structure to review, revise, and govern the output before it reaches customers or internal stakeholders.
Was this helpful?
Dust handles retrieval-augmented generation workflows such as document ingestion, chunking, embedding, and semantic search indexing. This reduces the need for teams to build and maintain their own vector databases or embedding infrastructure when creating AI agents grounded in company data.
The platform supports access to multiple foundation models from different providers, including GPT-4, Claude, Mistral, and Gemini according to the visible product description. Teams can configure model use for assistant needs, but exact routing behavior, model availability, and plan-level limits should be verified against Dust's current documentation.
Dust provides a graphical interface for designing multi-step LLM pipelines without writing code. Users can chain together retrieval steps, model calls, tool invocations, and data transformations into structured workflows. This makes it possible for product managers and operations teams to create and iterate on AI agent behavior while still offering depth for technical users.
Integrations with workplace tools, repositories, databases, APIs, and uploaded files can help Dust ingest and index organizational data for assistant use. Exact connector coverage, permission mapping, and synchronization behavior should be confirmed from Dust's current integration documentation.
Administrators can define which data sources and tools each AI agent can access, creating boundaries aligned with organizational security policies. Teams evaluating Dust for regulated or sensitive data should verify current compliance certifications, audit logging, SSO support, retention controls, and residency options directly with Dust.
29€/month/user excl. tax; 14-day free trial; from 1 user
Custom pricing from 100 members with multiple workspaces, SSO, and enterprise controls
Ready to get started with Dust?
View Pricing Options →We believe in transparent reviews. Here's what Dust doesn't handle well:
Weekly insights on the latest AI tools, features, and trends delivered to your inbox.
The provided website content does not include a dated 2026 product changelog or release notes. Based only on the supplied content, Dust's current positioning emphasizes multiplayer AI, human-agent collaboration, custom company-data assistants, managed RAG, semantic search, multi-step LLM pipelines, and support for multiple foundation models.
No reviews yet. Be the first to share your experience!
Get started with Dust and see if it's the right fit for your needs.
Get Started →Take our 60-second quiz to get personalized tool recommendations
Find Your Perfect AI Stack →Explore 20 ready-to-deploy AI agent templates for sales, support, dev, research, and operations.
Browse Agent Templates →