Class FlowAgentType

Implementation of the Flow Agent Type pattern.

This agent type enables deterministic workflow execution where agents follow predefined paths through a graph of steps. Key features:

Graph-based workflow definition
Conditional path evaluation using safe boolean expressions
Support for Actions, Sub-Agents, and Prompts as step types
Deterministic execution with optional AI-driven decision points

FlowAgentType

Example

// Flow agents execute steps based on graph structure
const flowAgent = new FlowAgentType();
const nextStep = await flowAgent.DetermineNextStep(promptResult, payload);

// Steps are determined by evaluating path conditions
// Path: "payload.status == 'approved' && payload.amount < 1000"
// Leads to: "Auto-Approve" step

Hierarchy (View Summary)

BaseAgentType
- FlowAgentType

Constructors

constructor

new FlowAgentType(): FlowAgentType
Returns FlowAgentType
Inherited from BaseAgentType.constructor

Properties

`Protected`_jsonValidator

_jsonValidator: JSONValidator = ...

JSON validator instance for cleaning and validating responses

`Static` `Readonly`CURRENT_PAYLOAD_PLACEHOLDER

CURRENT_PAYLOAD_PLACEHOLDER: "_CURRENT_PAYLOAD" = '_CURRENT_PAYLOAD'

Common placeholder for current payload injection

Static

Accessors

InjectLoopResultsAsMessage

get InjectLoopResultsAsMessage(): boolean
Flow agents don't need loop results injected as messages - they navigate paths

Returns boolean
Overrides BaseAgentType.InjectLoopResultsAsMessage
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1531

RequiresAgentLevelPrompts

get RequiresAgentLevelPrompts(): boolean
Flow agents don't require agent-level prompts - they use step-level prompts exclusively

Returns boolean
Overrides BaseAgentType.RequiresAgentLevelPrompts
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1539

Methods

AfterLoopIteration

AfterLoopIteration(
 iterationResult: {
 actionResults?: ActionResult[];
 currentPayload: P;
 index: number;
 item: any;
 itemVariable: string;
 loopContext: any;
 subAgentResult?: any;
 },
): P
Flow agents apply ActionOutputMapping after each iteration
Type Parameters
- P
Parameters
- iterationResult: {
 actionResults?: ActionResult[];
 currentPayload: P;
 index: number;
 item: any;
 itemVariable: string;
 loopContext: any;
 subAgentResult?: any;
 }
Returns P
Overrides BaseAgentType.AfterLoopIteration
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1589

`Optional`BeforeLoopIteration

BeforeLoopIteration?(
 context: {
 actionParams: Record<string, unknown>;
 index: number;
 item: any;
 itemVariable: string;
 loopType: "ForEach" | "While";
 payload: P;
 subAgentRequest?: {
 message: string;
 name: string;
 templateParameters?: Record<string, string>;
 };
 },
): {
 actionParams?: Record<string, unknown>;
 payload?: P;
 subAgentRequest?: {
 message: string;
 name: string;
 templateParameters?: Record<string, string>;
 };
}
Called before each loop iteration to prepare parameters and payload.

Loop agents use this to resolve template variables ("item.email"). Flow agents typically don't need this (params already resolved).
Type Parameters
- P
Parameters
- context: {
 actionParams: Record<string, unknown>;
 index: number;
 item: any;
 itemVariable: string;
 loopType: "ForEach" | "While";
 payload: P;
 subAgentRequest?: {
 message: string;
 name: string;
 templateParameters?: Record<string, string>;
 };
 }
 Current iteration context
Returns {
 actionParams?: Record<string, unknown>;
 payload?: P;
 subAgentRequest?: {
 message: string;
 name: string;
 templateParameters?: Record<string, string>;
 };
}
Modified context or null for default behavior

Since
2.112.0
Inherited from BaseAgentType.BeforeLoopIteration
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:550

`Protected`createNextStep

createNextStep(
 step:
 | "Actions"
 | "Chat"
 | "Failed"
 | "ForEach"
 | "Retry"
 | "Sub-Agent"
 | "Success"
 | "While",
 options?: Partial<BaseAgentNextStep>,
): BaseAgentNextStep
Protected
Creates a standardized next step object with common defaults
Type Parameters
- P
 The payload type
Parameters
- step:
 | "Actions"
 | "Chat"
 | "Failed"
 | "ForEach"
 | "Retry"
 | "Sub-Agent"
 | "Success"
 | "While"
 The step type
- options: Partial<BaseAgentNextStep> = {}
 Additional options to merge
Returns BaseAgentNextStep
The next step object
Inherited from BaseAgentType.createNextStep
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:329

`Protected`createRetryStep

createRetryStep(
errorMessage: string,
options?: Partial<BaseAgentNextStep>,
): BaseAgentNextStep
Protected
Creates a retry step with a standardized error message
Type Parameters
- P
 The payload type
Parameters
- errorMessage: string
 The error message
- options: Partial<BaseAgentNextStep> = {}
 Additional options
Returns BaseAgentNextStep
Retry step
Inherited from BaseAgentType.createRetryStep
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:351

`Protected`createSuccessStep

createSuccessStep(
options?: Partial<BaseAgentNextStep>,
): BaseAgentNextStep
Protected
Creates a success step with optional payload changes
Type Parameters
- P
 The payload type
Parameters
- options: Partial<BaseAgentNextStep> = {}
 Success options
Returns BaseAgentNextStep
Success step
Inherited from BaseAgentType.createSuccessStep
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:372

DetermineInitialStep

DetermineInitialStep(
 params: ExecuteAgentParams,
 payload: P,
 agentTypeState: ATS,
): Promise<BaseAgentNextStep>
Determines the initial step for flow agent types.

Flow agents look up their configured starting step instead of executing a prompt. If agentTypeParams.startAtStep is provided, the flow will begin at that step instead of the configured entry point.
Type Parameters
- P = any
- ATS = any
Parameters
- params: ExecuteAgentParams
 The full execution parameters
- payload: P
- agentTypeState: ATS
Returns Promise<BaseAgentNextStep>
The initial step to execute, or null if flow context not ready

Since
2.76.0
Overrides BaseAgentType.DetermineInitialStep
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1124

DetermineNextStep

DetermineNextStep(
 promptResult: AIPromptRunResult<unknown>,
 params: ExecuteAgentParams<any, P>,
 payload: P,
 agentTypeState: ATS,
): Promise<BaseAgentNextStep>
Determines the next step based on the flow graph structure.

For Flow agents, the next step is determined by:
1. Finding the current position in the graph
2. Evaluating conditions on outgoing paths
3. Following the highest priority valid path
4. Using prompt results only when current step type is 'Prompt'
Type Parameters
- P = any
- ATS = any
Parameters
- promptResult: AIPromptRunResult<unknown>
 Result from prompt execution (null for non-prompt steps)
- params: ExecuteAgentParams<any, P>
 The full execution parameters
- payload: P
- agentTypeState: ATS
Returns Promise<BaseAgentNextStep>
The next step to execute
Overrides BaseAgentType.DetermineNextStep
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:188

GetPromptConfigurationGuidance

GetPromptConfigurationGuidance(): string
Provides Flow-specific guidance for prompt configuration

Returns string
Overrides BaseAgentType.GetPromptConfigurationGuidance
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1547

GetPromptForStep

GetPromptForStep(
 params: ExecuteAgentParams,
 config: AgentConfiguration,
 payload: P,
 agentTypeState: ATS,
 previousDecision?: BaseAgentNextStep,
): Promise<MJAIPromptEntityExtended>
Gets the prompt to use for a specific step. Flow agents may use different prompts for different steps in the flow.
Type Parameters
- P = any
- ATS = any
Parameters
- params: ExecuteAgentParams
 The execution parameters
- config: AgentConfiguration
 The loaded agent configuration
- payload: P
- agentTypeState: ATS
- OptionalpreviousDecision: BaseAgentNextStep
 The previous step decision that may contain flow prompt info
Returns Promise<MJAIPromptEntityExtended>
Custom prompt for flow steps, or default config.childPrompt

Since
2.76.0
Overrides BaseAgentType.GetPromptForStep
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1321

HandleStepFallback

HandleStepFallback(
 step: BaseAgentNextStep,
 config: AgentConfiguration,
 params: ExecuteAgentParams,
 payload: P,
 agentTypeState: ATS,
): Promise<BaseAgentNextStep>
Flow agents should NEVER fall back to prompt execution for Success/Failed steps. Flow agents are deterministic and driven by their graph structure (steps and paths). When a step completes (Success or Failed), the agent should terminate rather than retry with prompts.
Type Parameters
- P = any
- ATS = any
Parameters
- step: BaseAgentNextStep
- config: AgentConfiguration
- params: ExecuteAgentParams
- payload: P
- agentTypeState: ATS
Returns Promise<BaseAgentNextStep>
Since
2.113.0
Overrides BaseAgentType.HandleStepFallback
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1562

InitializeAgentTypeState

InitializeAgentTypeState<ATS = any, P = any>(
params: ExecuteAgentParams<any, P>,
): Promise<ATS>
Handles the initialization of the flow agent state that is specialized, additional state information specific to the Flow Agent Type
Type Parameters
- ATS = any
- P = any
Parameters
- params: ExecuteAgentParams<any, P>
Returns Promise<ATS>
Overrides BaseAgentType.InitializeAgentTypeState
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:169

InjectPayload

InjectPayload(
 payload: P,
 agentState: ATS,
 prompt: AIPromptParams,
 agentInfo: { agentId: string; agentRunId?: string },
): Promise<void>
Injects flow-specific context into the prompt parameters.
Type Parameters
- P = any
- ATS = any
Parameters
- payload: P
 The payload to inject
- agentState: ATS
- prompt: AIPromptParams
 The prompt parameters to update
- agentInfo: { agentId: string; agentRunId?: string }
 Agent identification info
Returns Promise<void>
Overrides BaseAgentType.InjectPayload
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:318

`Protected`parseJSONResponse

parseJSONResponse<T>(promptResult: AIPromptRunResult): T
Protected
Parses JSON response from prompt execution with automatic validation syntax cleaning
Type Parameters
- T
 The expected response type
Parameters
- promptResult: AIPromptRunResult
 The prompt execution result
Returns T
Parsed response or null if parsing fails
Inherited from BaseAgentType.parseJSONResponse
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:291

PostProcessActionStep

PostProcessActionStep(
 actionResults: ActionResult[],
 actions: AgentAction[],
 currentPayload: P,
 agentTypeState: ATS,
 currentStep: BaseAgentNextStep,
): Promise<AgentPayloadChangeRequest>
Override of BaseAgentType's PostProcessActionStep to handle Flow-specific logic.

This method checks if the current step has action output mapping configured and applies it to update the payload accordingly.
Type Parameters
- P = any
- ATS = any
Parameters
- actionResults: ActionResult[]
 The results from action execution
- actions: AgentAction[]
 The actions that were executed
- currentPayload: P
 The current payload
- agentTypeState: ATS
- currentStep: BaseAgentNextStep
 The current step being executed
Returns Promise<AgentPayloadChangeRequest>
Payload changes from output mapping
Overrides BaseAgentType.PostProcessActionStep
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1036

PostProcessSubAgentStep

PostProcessSubAgentStep(
 subAgentResult: any,
 subAgentRequest: AgentSubAgentRequest,
 currentPayload: P,
 agentTypeState: ATS,
 currentStep: BaseAgentNextStep,
): Promise<AgentPayloadChangeRequest>
Post-processes the result of sub-agent execution.

This method is called by BaseAgent after a sub-agent has been executed. Agent types can override this method to perform custom processing of sub-agent results, such as extracting specific data from the sub-agent's payload or updating context.
Type Parameters
- P = any
- ATS = any
Parameters
- subAgentResult: any
 The result from sub-agent execution
- subAgentRequest: AgentSubAgentRequest
 The sub-agent request that was executed
- currentPayload: P
 The current payload
- agentTypeState: ATS
- currentStep: BaseAgentNextStep
 The current step being executed
Returns Promise<AgentPayloadChangeRequest>
Optional payload change request

Since
2.76.0
Inherited from BaseAgentType.PostProcessSubAgentStep
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:451

PreProcessActionStep

PreProcessActionStep(
 actions: AgentAction[],
 currentPayload: P,
 agentTypeState: ATS,
 currentStep: BaseAgentNextStep,
 params?: ExecuteAgentParams,
): Promise<void>
Override of BaseAgentType's PreProcessActionStep to handle Flow-specific input mapping.

This method checks if the current step has action input mapping configured and applies it to map payload values or static values to action input parameters.
Type Parameters
- P = any
- ATS = any
Parameters
- actions: AgentAction[]
 The actions that will be executed (modified in place)
- currentPayload: P
 The current payload
- agentTypeState: ATS
- currentStep: BaseAgentNextStep
 The current step being executed
- Optionalparams: ExecuteAgentParams
Returns Promise<void>
Actions are modified in place

Since
2.76.0
Overrides BaseAgentType.PreProcessActionStep
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:841

PreProcessNextStep

PreProcessNextStep(
 params: ExecuteAgentParams,
 step: BaseAgentNextStep,
 payload: P,
 agentTypeState: ATS,
): Promise<BaseAgentNextStep>
Pre-processes steps for flow agent types.

For Flow agents, 'Retry' after actions means evaluate paths from the current step and continue the flow based on the updated payload. The only exception is when executing a Prompt step within the flow, which should execute normally.

Also, 'Success' steps after sub-agents need to be evaluated in the same way as Retry after actions
Type Parameters
- P = any
- ATS = any
Parameters
- params: ExecuteAgentParams
 The full execution parameters
- step: BaseAgentNextStep
 The retry step that was returned
- payload: P
 The current payload
- agentTypeState: ATS
 The current agent type state
Returns Promise<BaseAgentNextStep>
The next flow step, or null for prompt execution

Since
2.76.0
Overrides BaseAgentType.PreProcessNextStep
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:1177

processActionResult

processActionResult(
 actionResult: Record<string, unknown>,
 _stepId: string,
 outputMapping?: string,
 currentPayload?: P,
): AgentPayloadChangeRequest
Processes action results and applies output mapping if configured This should be called by BaseAgent after action execution
Type Parameters
- P
Parameters
- actionResult: Record<string, unknown>
- _stepId: string
- OptionaloutputMapping: string
- OptionalcurrentPayload: P
Returns AgentPayloadChangeRequest
- Defined in AI/Agents/src/agent-types/flow-agent-type.ts:810

`Protected` `Static`getAgentInstanceWithDriverClass

getAgentInstanceWithDriverClass(driverClass: string): Promise<BaseAgentType>
Protected
Instantiates an agent type class using a specific driver class name.

This method is used when an individual agent has its own DriverClass override, allowing for specialized implementations per agent instance.
Parameters
- driverClass: string
 The driver class name to instantiate
Returns Promise<BaseAgentType>
Instance of the agent type class
Inherited from BaseAgentType.getAgentInstanceWithDriverClass
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:266

`Protected` `Static`getAgentTypeInstance

getAgentTypeInstance(agentType: MJAIAgentTypeEntity): Promise<BaseAgentType>
Protected
Instantiates the appropriate agent type class based on the agent type entity.

This method uses the MemberJunction class factory to dynamically instantiate agent type classes. It uses the DriverClass field. If DriverClass is not specified it throws an error.
Parameters
- agentType: MJAIAgentTypeEntity
 The agent type entity to instantiate
Returns Promise<BaseAgentType>
Instance of the agent type class
Example
```
// For an agent type with DriverClass "LoopAgentType"
const agentTypeInstance = await this.getAgentTypeInstance(loopAgentType);

@protected
```
Inherited from BaseAgentType.getAgentTypeInstance
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:244

`Static`GetAgentTypeInstance

GetAgentTypeInstance(agentType: MJAIAgentTypeEntity): Promise<BaseAgentType>
Helper method that retrieves an instance of the agent type based on the provided agent type entity.

This method uses the ClassFactory to create an instance of the agent type class specified in the DriverClass field of the agent type entity. If the DriverClass is not specified, it throws an error.
Parameters
- agentType: MJAIAgentTypeEntity
 The agent type entity to instantiate
Returns Promise<BaseAgentType>
An instance of the agent type class

Async
Static
Method
GetAgentTypeInstance

Throws
If the agent type does not have a DriverClass specified or if instantiation fails
Inherited from BaseAgentType.GetAgentTypeInstance
- Defined in AI/Agents/src/agent-types/base-agent-type.ts:216

Class FlowAgentType

Example

Hierarchy (View Summary)

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Returns FlowAgentType

Properties

Protected_jsonValidator

Static ReadonlyCURRENT_PAYLOAD_PLACEHOLDER

Static

Accessors

InjectLoopResultsAsMessage

Returns boolean

RequiresAgentLevelPrompts

Returns boolean

Methods

AfterLoopIteration

Type Parameters

Parameters

Returns P

OptionalBeforeLoopIteration

Type Parameters

Parameters

Returns { actionParams?: Record<string, unknown>; payload?: P; subAgentRequest?: { message: string; name: string; templateParameters?: Record<string, string>; };}

Since

ProtectedcreateNextStep

Type Parameters

Parameters

Returns BaseAgentNextStep<P>

ProtectedcreateRetryStep

Type Parameters

Parameters

Returns BaseAgentNextStep<P>

ProtectedcreateSuccessStep

Type Parameters

Parameters

Returns BaseAgentNextStep<P>

DetermineInitialStep

Type Parameters

Parameters

Returns Promise<BaseAgentNextStep<P>>

Since

DetermineNextStep

Type Parameters

Parameters

Returns Promise<BaseAgentNextStep<P>>

GetPromptConfigurationGuidance

Returns string

GetPromptForStep

Type Parameters

Parameters

Returns Promise<MJAIPromptEntityExtended>

Since

HandleStepFallback

Type Parameters

Parameters

Returns Promise<BaseAgentNextStep<P>>

Since

InitializeAgentTypeState

Type Parameters

Parameters

Returns Promise<ATS>

InjectPayload

Type Parameters

Parameters

Returns Promise<void>

ProtectedparseJSONResponse

Type Parameters

Parameters

Returns T

PostProcessActionStep

Type Parameters

Parameters

Returns Promise<AgentPayloadChangeRequest<P>>

PostProcessSubAgentStep

`Protected`_jsonValidator

`Static` `Readonly`CURRENT_PAYLOAD_PLACEHOLDER

`Optional`BeforeLoopIteration

Returns {
actionParams?: Record<string, unknown>;
payload?: P;
subAgentRequest?: {
message: string;
name: string;
templateParameters?: Record<string, string>;
};
}

`Protected`createNextStep

`Protected`createRetryStep

`Protected`createSuccessStep

`Protected`parseJSONResponse

`Protected` `Static`getAgentInstanceWithDriverClass

`Protected` `Static`getAgentTypeInstance

`Static`GetAgentTypeInstance