Dust · Arazzo Workflow

Dust Find Agent and Start a Conversation

Version 1.0.0

Search for an agent by name, resolve its full configuration, then open a conversation mentioning it.

1 workflow 2 source APIs 1 provider
View Spec View on GitHub AgentsArtificial IntelligenceCustom WorkflowsData SourcesDustEnterprise AIKnowledge-ManagementLLMMCPMulti-ModelRAGArazzoWorkflows

Provider

dust-tt

Workflows

find-agent-and-start-conversation
Search an agent by name and open a conversation that mentions it.
Searches for an agent configuration matching the supplied name, fetches its full configuration, and creates a conversation seeded with a message that mentions the matched agent.
3 steps inputs: agentName, apiToken, content, title, wId outputs: conversationId, matchedAgentId
1
searchAgents
{$sourceDescriptions.agentsApi.url}#/paths/~1api~1v1~1w~1{wId}~1assistant~1agent_configurations~1search/get
Search agent configurations by name and capture the sId of the first match.
2
getAgent
{$sourceDescriptions.agentsApi.url}#/paths/~1api~1v1~1w~1{wId}~1assistant~1agent_configurations~1{sId}/get
Retrieve the full configuration of the matched agent so its identity and tools are confirmed before use.
3
createConversation
{$sourceDescriptions.conversationsApi.url}#/paths/~1api~1v1~1w~1{wId}~1assistant~1conversations/post
Open a new conversation seeded with a human message that mentions the resolved agent.

Source API Descriptions

Arazzo Workflow Specification

Raw ↑
arazzo: 1.0.1
info:
  title: Dust Find Agent and Start a Conversation
  summary: Search for an agent by name, resolve its full configuration, then open a conversation mentioning it.
  description: >-
    Resolves a human-friendly agent name into a usable conversation. The
    workflow searches agent configurations by name, branches when no agent is
    found, otherwise retrieves the full configuration of the first match and
    opens a new conversation that mentions that agent. Each step spells out its
    request inline so the flow can be read and executed without opening the
    underlying OpenAPI description.
  version: 1.0.0
sourceDescriptions:
- name: agentsApi
  url: ../openapi/dust-tt-agents-api-openapi.yml
  type: openapi
- name: conversationsApi
  url: ../openapi/dust-tt-conversations-api-openapi.yml
  type: openapi
workflows:
- workflowId: find-agent-and-start-conversation
  summary: Search an agent by name and open a conversation that mentions it.
  description: >-
    Searches for an agent configuration matching the supplied name, fetches its
    full configuration, and creates a conversation seeded with a message that
    mentions the matched agent.
  inputs:
    type: object
    required:
    - apiToken
    - wId
    - agentName
    - content
    properties:
      apiToken:
        type: string
        description: Dust API key used as the Bearer token.
      wId:
        type: string
        description: The workspace identifier.
      agentName:
        type: string
        description: Name (or partial name) of the agent to search for.
      content:
        type: string
        description: The text of the first human message in the conversation.
      title:
        type: string
        description: Optional title for the new conversation.
  steps:
  - stepId: searchAgents
    description: >-
      Search agent configurations by name and capture the sId of the first
      match.
    operationPath: '{$sourceDescriptions.agentsApi.url}#/paths/~1api~1v1~1w~1{wId}~1assistant~1agent_configurations~1search/get'
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.apiToken
    - name: wId
      in: path
      value: $inputs.wId
    - name: q
      in: query
      value: $inputs.agentName
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      matchedAgentId: $response.body#/agentConfigurations/0/sId
    onSuccess:
    - name: agentFound
      type: goto
      stepId: getAgent
      criteria:
      - context: $response.body
        condition: $.agentConfigurations.length > 0
        type: jsonpath
    - name: noAgent
      type: end
      criteria:
      - context: $response.body
        condition: $.agentConfigurations.length == 0
        type: jsonpath
  - stepId: getAgent
    description: >-
      Retrieve the full configuration of the matched agent so its identity and
      tools are confirmed before use.
    operationPath: '{$sourceDescriptions.agentsApi.url}#/paths/~1api~1v1~1w~1{wId}~1assistant~1agent_configurations~1{sId}/get'
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.apiToken
    - name: wId
      in: path
      value: $inputs.wId
    - name: sId
      in: path
      value: $steps.searchAgents.outputs.matchedAgentId
    - name: variant
      in: query
      value: full
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      agentId: $response.body#/agentConfiguration/sId
      agentName: $response.body#/agentConfiguration/name
  - stepId: createConversation
    description: >-
      Open a new conversation seeded with a human message that mentions the
      resolved agent.
    operationPath: '{$sourceDescriptions.conversationsApi.url}#/paths/~1api~1v1~1w~1{wId}~1assistant~1conversations/post'
    parameters:
    - name: Authorization
      in: header
      value: Bearer $inputs.apiToken
    - name: wId
      in: path
      value: $inputs.wId
    requestBody:
      contentType: application/json
      payload:
        title: $inputs.title
        blocking: false
        message:
          content: $inputs.content
          mentions:
          - configurationId: $steps.getAgent.outputs.agentId
    successCriteria:
    - condition: $statusCode == 200
    outputs:
      conversationId: $response.body#/conversation/sId
  outputs:
    matchedAgentId: $steps.searchAgents.outputs.matchedAgentId
    conversationId: $steps.createConversation.outputs.conversationId

Work with this as data

Every workflow here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for arazzo workflows

4 MCP tools reach this
  • find_arazzoBrowse and filter every workflow in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This workflow
curl "https://apis.io/api/v1/arazzo/dust-tt-find-agent-and-start-conversation-workflow"
All arazzo workflows
curl "https://apis.io/api/v1/arazzo?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.