Skip to main content

AI Agent Node

Predicts text using a Language Model

Properties

LabelPropertyTypeDescriptionDefault ValueIs Required
Function ConfigurationfunctionConfigbotdojo/types/kitchen_sinkObject
Use Parallel Tool CallinguseParallelToolCallingbotdojo/types/booleanWhen enabled, the agent will call tools in parallel if the model supports it. This can speed up the response time of the agent.true
Show StepsshowStepsToUserbotdojo/types/booleanWhen enabled, the tool calls will be shown to the user.true
Max IterationsmaxIterationsbotdojo/types/numberAgent will stop after this many iterations. Each iteration the agent can invoke one or more tools.10
Disable Tools on Last IterationdisableToolsOnLastIterationbotdojo/types/booleanWhen enabled, the final counted iteration does not expose or execute ordinary tools. The final_output tool remains available when structured output requires it.false
Warning Threshold IterationwarningThresholdIterationbotdojo/types/numberIf the number of iterations exceeds this threshold, the warning message will be passed as an assistant message to the LLM. This is used to nudge the LLM to finish the response.null
Warning Threshold MessagewarningThresholdMessagebotdojo/types/stringOptional. When the number of iterations exceeds the warning threshold, the warning message will be passed as an assistant message to the LLM.null
Enabled Model ContextsmodelContextsbotdojo/types/booleanAllows Model Context to be attached to this agentfalse
Disable Final Output MessagedisableFinalOutputMessagebotdojo/types/booleanBy default, if the LLM finishes without calling the final_output tool, it will be prompted to call it. When enabled, this setting disables that prompt and results in an error instead. Only applies when the agent needs to return JSON output rather than a single text response.false
Custom Final Output MessagecustomFinalOutputMessagebotdojo/types/stringOverride the default final output message prompt. default : 'You must call the final_output tool to complete the response.'null
Final Output Prompt TriesfinalOutputPromptTriesbotdojo/types/numberDefaults to 3. When the Output is not a single string, The agent needs to call the final_output tool to return the JSON. This setting controls how many times the agent will attempt to call the final_output tool before giving up.3
Validate Agent Turn with ToolenableValidatorToolbotdojo/types/booleanAdds a Validator Tool input that determines whether the agent completed a valid turn. Existing validators receive the configured output fields unchanged. To also receive bounded current-turn tool evidence, add an optional agent_turn object to the validator input schema.null
Validate Agent Turn TriesvalidateOutputTriesbotdojo/types/numberNumber of unsuccessful calls to the Validator Tool before enforcing the selected validator mode. Only applies when Validate Agent Turn with Tool is enabled. Defaults to 3.3
Validator Enforcement ModevalidatorEnforcementModebotdojo/types/optionsAvailable only when Validate Agent Turn with Tool is enabled. Blocking raises a flow error when validation cannot continue. Advisory retries normally, then publishes the last proposed response if the validator retry or Agent iteration budget is exhausted. Validator execution errors and malformed results remain blocking.blocking
Add citation references to LLM outputformatCitationsbotdojo/types/booleanWhen enabled the model output that references a citation via [^citationId] will be reformatted to link to the citation source.false

Output

LabelPropertyTypeDescriptionDefault Value
Outputoutputbotdojo/types/dataOutputnull