Dust
Enterprise workspace agent platform for grounding agents on company data (Notion, Slack, Drive, etc.) with a multi-agent surface, public trial pricing, and traction at enterprise scale.
Dust is an enterprise platform for building, deploying, and governing AI agents that are grounded in a company's own knowledge and tools. Founded by a former OpenAI researcher, it began as a developer framework and grew into a horizontal platform aimed at what it calls AI Operators, the people inside fast-moving companies who build an AI workflow with judgment, deploy it, and run it for their whole team rather than waiting for a tool to be handed to them. The result is agents that understand your company context instead of answering from general knowledge alone.
Building an agent does not require code. Anyone on a team can create one through a visual interface, writing what the agent should do in plain language, starting from templates, and connecting it to data, while developers can add custom tools and integrations when something specific is needed. Dust deliberately keeps the language approachable, calling these directions instructions rather than system prompts, so non-engineers can steer fairly sophisticated behavior.
A core part of the platform is how it connects to data. Rather than leaning on generic integration providers, Dust maintains its own connectors to systems like Notion, Slack, Google Drive, and GitHub, with a semantic knowledge layer so agents understand the structure of what they read rather than just retrieving documents. Agents can search that knowledge, query structured data, and search the web, and the platform is model-agnostic, letting teams pick a frontier model from providers like OpenAI, Anthropic, Google, or Mistral on a per-agent basis. Its multiplayer framing means people and agents work side by side from the same shared context.
Because it is built for organizations, governance sits at the center. A dual-layer permission model separates what an agent can access from who is allowed to use it, with permission spaces, SSO and SCIM-synced groups, audit logs, and a stated commitment not to use customer data for training. Dust carries SOC 2 Type II and GDPR compliance, enables HIPAA, and offers options, and its core is open source under a permissive license with a documented self-hosting path for teams that need it.
Vendor details
Canonical URL
https://dust.tt
Category
Enterprise operations agent
Company status
independent
Use cases & customers
Target customers
Deployment options
In practice
Your team's knowledge is scattered across Notion, Slack, and Drive, and a general chatbot doesn't know any of it. Dust connects its own integrations to those sources so agents answer from your company's actual context.
A capable non-engineer wants to build an agent for their team without waiting on IT. Dust's no-code builder lets them write plain-language instructions, start from a template, and connect data, with developer tools available when needed.
Your CISO needs tight control over what AI can touch. Dust separates what an agent can access from who can use it, with permission spaces, SSO, audit logs, and a no-training commitment, plus an open-source self-host option.
Sources & related URLs
Agentic Index coverage score
11.0 / 14 capabilities · 79%
| Integrations & Tool CallingOfficial docs 2026-06-08 | Full |
|---|---|
| Workflow OrchestrationMulti-agent surface docs 2026-06-08 | Full |
| Knowledge Grounding & RAGCompany data grounding docs 2026-06-08 | Full |
| Human Oversight & GuardrailsOfficial docs 2026-06-08 | Partial |
| Security, Identity & GovernanceEnterprise docs 2026-06-08 | Full |
| Observability & AuditabilityOfficial docs 2026-06-08 | Partial |
| Memory & State PersistenceOfficial docs 2026-06-08 | Partial |
| Deployment & Data ResidencyOfficial docs 2026-06-08 | Full |
| Prebuilt Agents, Templates & PacksOfficial docs 2026-06-08 | Full |
| Triggers & Channel CoverageOfficial docs 2026-06-08 | Full |
| Model Flexibility & RoutingMulti-model docs 2026-06-08 | Full |
| APIs, SDKs & MCP ExtensibilityOfficial docs 2026-06-08 | Full |
| Testing, Debugging & OptimizationOfficial docs 2026-06-08 | Partial |
| Browser & Computer UseOfficial docs 2026-06-08 | Unable to verify |
The Agentic Index coverage score grades every vendor Full, Partial or Unable to verify against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Recent platform changes
Dust released a unified login system called 'The Computer' that bridges the dust.tt and eu.dust.tt environments. The update also introduces a new Modjo MCP integration for all workspaces and adds support for reactions and status updates to the existing Slack MCP.
Bears on: MCP / tool calling / API
View sourceDust released a significant update to its integration and agent capabilities, highlighted by making the platform available as a remote MCP server to allow access from any external MCP-capable client. The release also adds personal Zendesk account connections, a Lemlist MCP server for outbound prospecting, and AI-driven duplicate skill warnings during agent creation. Furthermore, Dust improved its Slack functionality to support agent reactions and status updates, and configured email interactions to keep entire threads within a single continuous conversation.
Bears on: MCP / tool calling / API
View sourceAdomik became a default Dust integration via OAuth with read-only access to monetization analytics and the Adomik knowledge base.
Bears on: Integrations
View sourcePricing
Pro $30/user/mo ($24 annual) · free option
seats
Included quota
Seat types carry monthly credit allocations that reset each billing period: Free 500 credits lifetime, Pro 8,000 credits/month, Max 40,000 credits/month. Seat types can be mixed and reassigned within a workspace. All plans include 20+ models (OpenAI, Anthropic, Google, Mistral, DeepSeek) with per agent model choice and no model gating.
What is public
Dust publishes full pricing. The Business plan offers three seat types an admin assigns per user: Free (0 dollars, 500 lifetime credits, up to 5 users, 3 connectors, 5 Spaces), Pro (30 dollars a month or 24 annual, 8,000 credits a month), and Max (150 dollars a month or 120 annual, 40,000 credits a month), up to 100 seats. Every plan includes 20+ models from OpenAI, Anthropic, Google, Mistral, and DeepSeek with per agent model choice and no model gating. Enterprise adds unlimited users and connectors, SSO, SCIM, audit logs, and advanced credit controls at custom pricing. A 15 day Pro trial and a no card free option exist.
Billing mechanics
Self serve Business plan with mixable seat types (Free $0 / Pro $30 monthly or $24 annual / Max $150 monthly or $120 annual), each carrying a monthly credit allocation that resets per billing period. Prorated mid cycle seat additions; monthly seats cancel anytime, annual seats stay reassignable until the commitment ends. Enterprise is sales led with unlimited users and connectors, SSO, SCIM, audit logs, and advanced credit controls.
Cost watchouts
Credits meter actual usage: higher capability models consume more credits per message, and heavy agent use can exhaust monthly allocations, pushing users to Max seats or admin enabled overage (capped). Business plan caps at 100 seats, 3 connectors, and 5 Spaces; unlimited connectors, SSO, SCIM, and audit logs require the custom priced Enterprise plan.
Variable cost rationale
Per seat pricing is predictable, but the credit metering layer means effective cost tracks usage intensity and model choice; heavy users migrate from 30 dollar Pro to 150 dollar Max seats or incur capped overage.
Additional watchouts
Costs scale with usage through the credit system rather than just seats, so heavy agent workloads should be modeled on Max seat economics rather than the Pro entry price.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free option (no card, up to 5 users) + 15-day Pro trial
Lowest paid plan
Pro seat $30/mo, or $24/mo billed yearly (8,000 credits/mo)
Commercial notes
Founded by former Stripe engineers, backed by Sequoia, 5,000+ organizations. Positioned as the workspace agent platform for AI Operators; teams like Vanta and Persona cited at 70 to 90 percent team usage.
Key ambiguities
Enterprise pricing is custom and unpublished (generally 100+ users). Credit consumption per message varies by model, so effective cost per unit of work depends on model mix.
Missing data
Enterprise pricing and minimums unpublished; credit consumption rates per model not published as a table.
Related vendors
- 11th Estate — Agentic platform whose AI engine scans markets, matches an…
- Aera Technology — Decision intelligence platform where an always on agent executes…
- Akro AI — On premise operational intelligence that automates document heavy…
- alfred_ — AI executive assistant that triages the inbox overnight and scores…
- Algebra AI — Delivery led provider that builds and runs human governed AI agents…
- Alloy.ai — Commerce intelligence system for consumer brands that unifies four…
Alternatives to Dust
The closest documented capability profiles to Dust among enterprise operations agents tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- Ema11.0 / 14Fuller documented coverage on Human Oversight & GuardrailsDust vs Ema →
- Glean12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & AuditabilityDust vs Glean →
- monday.com10.0 / 14A lighter documented profile than Dust
- Workato12.0 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
- Boomi12.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
- Celonis11.5 / 14Fuller documented coverage on Human Oversight & Guardrails and Observability & Auditability
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded