External Integrations

Description

Agent Composer provides multiple ways to integrate with external systems, enabling agents to take actions, retrieve data, and interact with enterprise services.

Integration Options

Integration	Use Case	Step Type
MCP	Connect to MCP-compatible services	`MCPClientStep`
Webhooks	Call REST APIs and trigger actions	`WebhookStep`
Code Execution	Run Python code for calculations	`CodeExecutionStep`
Salesforce	Query Salesforce data	`SalesforceSOSLStep`
Web Search	Search the web for current information	`WebSearchStep`
Other Agents	Query other Contextual AI agents	`ContextualAgentStep`

Salesforce Integration

Use SalesforceSOSLStep to execute SOSL searches against Salesforce:

salesforce_search:
  type: SalesforceSOSLStep
  config:
    client_id: "${SF_CLIENT_ID}"
    client_secret: "${SF_CLIENT_SECRET}"
    login_url: "https://login.salesforce.com"
    objects_to_return: "Case(Id, Subject, Status, Priority, Account.Name)"
    limit: 250
  input_mapping:
    query: __inputs__#query

Salesforce Configuration

Parameter	Type	Required	Description
`client_id`	`str`	Yes*	Salesforce connected app client ID
`client_secret`	`str`	Yes*	Salesforce connected app client secret
`login_url`	`str`	No	Salesforce login URL (default: production)
`objects_to_return`	`str`	No	SOSL RETURNING clause
`limit`	`int`	No	Maximum results (default: `250`)
`timeout`	`int`	No	Request timeout (default: `30`)

*Alternative: Use username, password, and security_token for user-based auth.

Web Search

Use WebSearchStep for real-time web information:

web_search:
  type: WebSearchStep
  config:
    model: "gemini-2.5-flash"
  input_mapping:
    query: __inputs__#query

Web Search Outputs

Output	Type	Description
`web_result`	`WebResult`	Search results with sources

Query Other Agents

Use ContextualAgentStep to retrieve information from other Contextual AI agents:

query_specialist:
  type: ContextualAgentStep
  config:
    agent_ids:
      - "agent-id-for-hr-docs"
      - "agent-id-for-legal-docs"
  input_mapping:
    query: __inputs__#query

This enables multi-agent architectures where specialized agents handle specific domains.

Vision Language Models

Use VisionLanguageModelStep for multimodal inputs:

analyze_image:
  type: VisionLanguageModelStep
  config:
    model_id: "vertex_ai/gemini-2.0-flash"
    temperature: 0.0
    max_tokens: 4096
  input_mapping:
    query: __inputs__#query
    images: image_extractor#extracted_images

VLM Configuration

Parameter	Type	Default	Description
`model_id`	`str`	`"vertex_ai/gemini-2.0-flash"`	Vision-capable model
`temperature`	`float`	`0.0`	Response creativity
`max_tokens`	`int`	`4096`	Maximum response length

Example: Multi-System Agent

version: 0.1
inputs:
  query: str

outputs:
  response: str

nodes:
  create_message_history:
    type: CreateMessageHistoryStep
    input_mapping:
      query: __inputs__#query

  research:
    type: AgenticResearchStep
    ui_stream_types:
      retrievals: true
    config:
      tools_config:
        # Internal documentation
        - name: search_docs
          description: Search internal documentation and policies.
          step_config:
            type: SearchUnstructuredDataStep
            config:
              top_k: 50

        # CRM data via MCP
        - name: search_crm
          description: Look up customer records and history.
          step_config:
            type: MCPClientStep
            config:
              server_url: "https://crm.example.com/mcp"
              tool_name: "search"
              tool_args: '{"query": "$query"}'
              auth_headers:
                Authorization: "Bearer ${CRM_TOKEN}"

        # Salesforce cases
        - name: search_salesforce
          description: Find support cases in Salesforce.
          step_config:
            type: SalesforceSOSLStep
            config:
              client_id: "${SF_CLIENT_ID}"
              client_secret: "${SF_CLIENT_SECRET}"
              objects_to_return: "Case(Id, Subject, Status)"

        # Real-time web info
        - name: search_web
          description: Search the web for current information.
          step_config:
            type: WebSearchStep

      agent_config:
        agent_loop:
          num_turns: 10
          model_name_or_path: "vertex_ai/claude-sonnet-4-5@20250929"
          research_guidelines_prompt: |
            Choose the appropriate tool based on the query:
            - `search_docs` for policies and procedures
            - `search_crm` for customer information
            - `search_salesforce` for support cases
            - `search_web` for current events or external info

    input_mapping:
      message_history: create_message_history#message_history

  generate:
    type: GenerateFromResearchStep
    ui_stream_types:
      generation: true
    config:
      model_name_or_path: "vertex_ai/claude-sonnet-4-5@20250929"
    input_mapping:
      message_history: create_message_history#message_history
      research: research#research

  __outputs__:
    type: output
    input_mapping:
      response: generate#response

Key Terms & Concepts

Agent Composer

Agent Configs

Datastore Configs

Description

Integration Options

Salesforce Integration

Salesforce Configuration

Web Search

Web Search Outputs

Query Other Agents

Vision Language Models

VLM Configuration

Example: Multi-System Agent

​Description

​Integration Options

​Salesforce Integration

​Salesforce Configuration

​Web Search

​Web Search Outputs

​Query Other Agents

​Vision Language Models

​VLM Configuration

​Example: Multi-System Agent

​Related

Description

Integration Options

Salesforce Integration

Salesforce Configuration

Web Search

Web Search Outputs

Query Other Agents

Vision Language Models

VLM Configuration

Example: Multi-System Agent

Related