Component schema

AgenticWorkflowGuardrails

object1 direct reference

Definition

Optional timeout after which the Agent0 automation will be aborted. Defaults to ten minutes.

string[]

Optionally restrict which tools are allowed. By default, all tools are allowed to be used. You can use the * character to allow all tools matching a pattern.

string[]

Optionally enforce that the Agent0 automation has executed these tool calls. If the agent is concluding is automation, but hasn't called these tools, the agent receives a follow-up prompt to call these tools. This auto-correction of the LLM behavior is only attempted once.

This is useful if you wanna ensure that the agent makes specific tool calls to external systems, e.g., to leave a message on Slack or GitHub.

AgenticWorkflowConcurrency

Duration

How long to wait before firing if the same trigger fires repeatedly. This is useful to avoid redundant automation executions when triggers fire in rapid succession. Defaults to 10s, which is also the minimum: a shorter non-zero value is raised to 10s. Set to "0s" to disable debouncing.

object

Pre-configure tool parameters that are enforced at invocation time. When a listed tool is called by the agent, these parameters are merged into the tool's arguments, overriding any values the LLM may have provided. Keys can be either fully qualified with namespace (e.g., "dash0.slackSendMessage") or bare tool names without namespace (e.g., "slackSendMessage"). Namespaced keys take precedence and allow disambiguation when multiple integrations expose tools with the same name. Values are objects of key-value pairs merged into tool arguments. Values support {{variable}} substitution using built-in variables, constants, and trigger variables.

NetworkLevelrequired

Controls outbound network access for the sandbox running the automation.

"no_network""trusted_only""full"

AgenticWorkflowCreditBudget

Optional rolling-window credit budget across all runs of this workflow. A new run is not started when the budget is already exhausted, and an in-flight run is aborted the moment it would push spend past the budget. Leave unset for no budget.

AgenticWorkflowMcpTool[]

Per-automation overrides for MCP server tools. Each entry sets whether a specific MCP tool is available to this automation, overriding the tool's enabled/disabled state in the organization's MCP integration settings. Tools not listed here fall back to their integration-settings default. This lets an automation enable a tool that is disabled in settings, or disable a tool that is enabled there, scoped to this automation only.

Used by 1

These schemas and endpoints reference this type directly.

SchemaAgenticWorkflowSpec

json

OpenAPI source123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354
{
  "properties": {
    "timeout": {
      "$ref": "#/components/schemas/Duration",
      "description": "Optional timeout after which the Agent0 automation will be aborted. Defaults to ten minutes.\n"
    },
    "allowedTools": {
      "description": "Optionally restrict which tools are allowed. By default, all tools are allowed to be used. You can use the\n`*` character to allow all tools matching a pattern.\n",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "requiredToolCalls": {
      "description": "Optionally enforce that the Agent0 automation has executed these tool calls. If the agent is concluding is\nautomation, but hasn't called these tools, the agent receives a follow-up prompt to call these tools. This\nauto-correction of the LLM behavior is only attempted once.\n\nThis is useful if you wanna ensure that the agent makes specific tool calls to external systems, e.g., to\nleave a message on Slack or GitHub.\n",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "concurrency": {
      "$ref": "#/components/schemas/AgenticWorkflowConcurrency"
    },
    "debounce": {
      "$ref": "#/components/schemas/Duration",
      "description": "How long to wait before firing if the same trigger fires repeatedly. This is useful to avoid redundant\nautomation executions when triggers fire in rapid succession. Defaults to 10s, which is also the\nminimum: a shorter non-zero value is raised to 10s. Set to \"0s\" to disable debouncing.\n"
    },
    "toolParameterOverrides": {
      "description": "Pre-configure tool parameters that are enforced at invocation time. When a listed\ntool is called by the agent, these parameters are merged into the tool's arguments,\noverriding any values the LLM may have provided.\nKeys can be either fully qualified with namespace (e.g., \"dash0.slackSendMessage\")\nor bare tool names without namespace (e.g., \"slackSendMessage\"). Namespaced keys\ntake precedence and allow disambiguation when multiple integrations expose tools\nwith the same name.\nValues are objects of key-value pairs merged into tool arguments.\nValues support {{variable}} substitution using built-in variables, constants,\nand trigger variables.\n",
      "type": "object",
      "additionalProperties": {
        "$ref": "#/components/schemas/AgenticWorkflowToolParameterOverride"
      }
    },
    "networkLevel": {
      "$ref": "#/components/schemas/NetworkLevel",
      "description": "Controls outbound network access for the sandbox running the automation.\n"
    },
    "creditBudgetWindow": {
      "$ref": "#/components/schemas/AgenticWorkflowCreditBudget",
      "description": "Optional rolling-window credit budget across all runs of this workflow. A new run is\nnot started when the budget is already exhausted, and an in-flight run is aborted the\nmoment it would push spend past the budget. Leave unset for no budget.\n"
    },
    "mcpTools": {
      "description": "Per-automation overrides for MCP server tools. Each entry sets whether a specific MCP\ntool is available to this automation, overriding the tool's enabled/disabled state in\nthe organization's MCP integration settings. Tools not listed here fall back to their\nintegration-settings default. This lets an automation enable a tool that is disabled in\nsettings, or disable a tool that is enabled there, scoped to this automation only.\n",
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/AgenticWorkflowMcpTool"
      }
    }
  },
  "required": [
    "networkLevel"
  ]
}