Dust

Dust indexes and semantically searches across connected data sources (Slack, Google Drive, Notion, Confluence, GitHub, Zendesk) using vector embeddings, enabling agents to retrieve relevant context from fragmented enterprise knowledge without manual aggregation. The platform maintains separate vector indices per data source and performs cross-source ranking to surface the most relevant documents, with real-time synchronization for connected tools.

Dust provides a browser-based, drag-and-drop interface for non-technical users to compose multi-step agent workflows without writing code. Users connect pre-built tool blocks (search, data analysis, web navigation, API calls) in a visual canvas, define conditional logic and loops, and deploy agents to production. The platform abstracts away prompt engineering and tool orchestration complexity through a declarative workflow model.

Dust organizes agents, data sources, and team members into isolated workspaces, enabling organizations to segment AI capabilities by team, department, or project. Each workspace has its own agents, knowledge bases, and access controls. Users can be assigned roles (admin, member, viewer) with granular permissions controlling who can create agents, access data sources, and invoke agents. Workspace isolation ensures data and agents from one team don't leak to another.

Dust offers enterprise-grade security including SOC2 Type II compliance, zero data retention policies, and single sign-on (SSO) via Okta, Entra ID, or Jumpcloud. Enterprise tier includes advanced security controls, SCIM user provisioning for automated account management, and US/EU data hosting options. The platform provides audit logging and compliance monitoring capabilities for regulated industries.

Dust provides dashboards and analytics for monitoring agent performance, including execution logs, success/failure rates, and usage metrics. Users can track how often agents are invoked, what tools they use, and whether they're meeting user expectations. The platform surfaces performance bottlenecks and suggests optimizations, enabling teams to continuously improve agent effectiveness.

Dust enables teams to create and manage multiple versions of agents, test changes in staging environments, and deploy updates to production with rollback capabilities. Users can compare agent versions, track changes, and revert to previous versions if needed. The platform supports gradual rollouts (e.g., deploying to 10% of users first) and A/B testing different agent configurations.

Dust abstracts away LLM provider differences by supporting GPT-5 (OpenAI), Claude (Anthropic), Gemini (Google), and Mistral through a unified interface. Users select their preferred model at the workspace or agent level, and Dust handles prompt formatting, token counting, and API calls to each provider. Advanced models are available in Pro tier and above, allowing users to trade off cost vs. capability.

Dust agents operate in a human-supervised mode where agents propose actions (e.g., sending messages, updating records) and humans review and approve before execution. The platform provides an execution dashboard showing agent reasoning, tool calls, and proposed outputs, enabling teams to maintain oversight while automating routine tasks. Agents can be configured to auto-execute low-risk actions (e.g., retrieving information) while requiring approval for high-risk actions (e.g., modifying data).

Dust agents can be deployed directly into Slack as bots that respond to messages, participate in threads, and execute workflows triggered by Slack events. The platform maintains conversation history within Slack, allowing agents to reference previous messages and context. Users can invoke agents via @mentions, slash commands, or automated triggers, and agents can post results, summaries, or formatted outputs back to Slack channels. The integration includes native support for Slack's message formatting and interactive elements.

Dust agents can browse the web, fetch content from URLs, and extract information from live web pages. This capability enables agents to retrieve real-time data (e.g., pricing, status pages, news) and incorporate it into responses. The platform handles HTTP requests, HTML parsing, and content extraction automatically, allowing agents to reference web content in their reasoning and outputs.

Dust exposes agents via a REST API, enabling external systems to invoke agents programmatically and retrieve results. The platform also provides native integrations with Zapier and Google Sheets, allowing non-technical users to trigger agents from other tools and embed agent outputs into spreadsheets. API calls include free credits on Pro tier with additional usage available at fixed (Pro) or custom (Enterprise) rates.

Dust agents can analyze data and execute queries against connected databases without users writing SQL. Agents interpret natural language questions (e.g., 'How many customers signed up last week?') and translate them into database queries, returning results in human-readable formats. The platform handles schema understanding, query optimization, and result formatting automatically, enabling non-technical users to extract insights from databases.

Dust agents can generate documents, emails, reports, and other content based on templates and user inputs. Agents combine data from knowledge bases, databases, and web sources with templates to produce formatted outputs. The platform supports various output formats (text, markdown, HTML) and can integrate with document systems (Google Docs, Notion) to publish generated content directly.

Dust provides native connectors to 6+ enterprise tools (Slack, Google Drive, Notion, Confluence, GitHub, Zendesk) that maintain real-time synchronization with Dust's knowledge base. Connectors handle authentication, incremental updates, and schema mapping automatically. Users configure connectors once, and Dust continuously syncs data without manual intervention, ensuring agents always have access to current information.