Dust Review 2026

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.