Dust
Type: app · Vendor: Dust · Language: Web product · License: proprietary · Status: active · Status in practice: mature
Workspace-level platform where users assemble named agents from instructions, knowledge sources, default tools (web search, file creation, image generation, memory), 100+ connectors and remote MCP servers, with explicit agent-as-tool delegation.
Description. Dust is a hosted workspace for building and running AI agents that connect to a company's data, tools and people. Each agent is configured with instructions, a model choice (OpenAI, Anthropic, Google, Mistral), Tools & Knowledge (default tools plus 100+ connector and remote MCP servers) and Data Sources. Dust supports agent-as-tool delegation via the `run_agent` tool, with a documented maximum recursion depth of 4, including a full-handoff mode where the sub-agent takes over the conversation.
Agent loop shape. Per-agent runtime: user message arrives, the agent loads its instructions and configured Tools & Knowledge, picks one or more tools per turn (search over Data Sources, default tools, connector tools, MCP-backed tools, or `run_agent` to delegate to another agent), executes, and continues. `run_agent` either calls the sub-agent in a separate conversation and returns the result, or performs a complete handoff where the sub-agent responds directly to the user. Recursion is capped at depth 4.
Primary use cases
- company-wide agent workspace over Notion / Slack / Salesforce / Gmail / etc.
- agent-as-tool delegation to specialised sub-agents
- MCP-extensible tool surface on top of native connectors
- structured-output and Deep Dive agents for long-running work
Key concepts
- Agent (docs) — Configured with instructions plus Tools & Knowledge.
- Tools & Knowledge → tool-use (docs) — Mix of default tools (web search, file creation, image generation, memory), connectors and MCP servers.
- Run Agent → supervisor (docs) — Tool that lets an agent call another agent as a sub-agent or as a full handoff.
- Remote MCP servers → mcp (docs) — Extend the toolset by registering an MCP server URL.
- Multi-provider model choice → multi-model-routing (docs) — Switch between OpenAI, Anthropic, Google and Mistral per agent.
- Connectors (docs) — 100+ production connectors covering Notion, Slack, Salesforce, Gmail, GitHub, etc.
Patterns this app implements —
- ★★Agentic RAG
Search over Data Sources is a core capability; agent picks search tools per turn against connected company data.
- ★★Model Context Protocol
Remote MCP servers extend Dust's toolset; register by URL.
- ★★Supervisor
`run_agent` is the documented agent-as-tool primitive with full-handoff mode and capped recursion depth.
- ★★Tool Use
Default tools (web search, file creation, image generation, data viz, memory), 100+ connectors, MCP-backed tools.
- ★★Multi-Model Routing
Per-agent model choice across OpenAI, Anthropic, Google, Mistral; Dust maintains integrations with multiple model providers.
- ★Handoff
`run_agent` handoff mode is an explicit agent-to-agent conversation handoff; selected agent takes over responding to the user.
Neighbourhood
Click any neighbour to follow the lineage. Scroll to zoom, drag to pan.
Alternatives & relatives
Listed as alternative by (3)
References
Provenance
- Last analyzed:
- Last updated:
- Verification status: verified