> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentium.in/llms.txt
> Use this file to discover all available pages before exploring further.
# Workflows
> Stateful step-based execution in Agentium. WorkflowConfig, state machine concept, and basic example.
# Workflows
**Workflows** orchestrate multi-step pipelines with shared state. Define steps (agents, functions, conditions, parallel execution), pass state between them, and handle retries and errors—all in a declarative, state-machine style.
***
## Stateful Step-Based Execution
Each step reads from and writes to a typed `TState` object passed through the workflow.
AgentStep, FunctionStep, ConditionStep, ParallelStep.
Configurable retry policy and step result status (done, error, skipped).
Optional EventBus for workflow lifecycle events.
***
## WorkflowConfig
```typescript theme={null}
interface WorkflowConfig {
name: string;
initialState: TState;
steps: StepDef[];
storage?: StorageDriver;
retryPolicy?: { maxRetries: number; backoffMs: number };
eventBus?: EventBus;
}
```
Display name for the workflow.
Initial state object. Steps read from and merge updates into this state.
Ordered array of steps. See Workflow Steps.
Storage for workflow persistence (e.g., resuming, audit).
`{ maxRetries, backoffMs }` for failed steps. See Retry & Error Handling.
Custom event bus for workflow events.
***
## State Machine Concept
Workflows behave like state machines:
1. **Initial state** — `initialState` is the starting point.
2. **Steps** — Each step receives the current state and can return a partial update.
3. **State merge** — Updates are merged into the state before the next step.
4. **Result** — `WorkflowResult` contains final state and `stepResults`.
***
## Basic Example
```typescript theme={null}
import { Workflow, Agent, openai } from "@agentium/core";
interface ContentState {
topic: string;
research_output?: string;
write_output?: string;
}
const researcher = new Agent({
name: "Researcher",
model: openai("gpt-4o-mini"),
instructions: "Research topics and provide factual summaries.",
});
const writer = new Agent({
name: "Writer",
model: openai("gpt-4o-mini"),
instructions: "Write clear content from research notes.",
});
const workflow = new Workflow({
name: "Content Pipeline",
initialState: { topic: "Quantum computing basics" },
steps: [
{
name: "research",
agent: researcher,
inputFrom: (state) => `Research: ${state.topic}`,
},
{
name: "write",
agent: writer,
inputFrom: (state) => `Write a draft using: ${state.research_output}`,
},
],
});
const result = await workflow.run();
console.log(result.state.write_output);
```
***
## WorkflowResult
```typescript theme={null}
interface WorkflowResult {
state: TState;
stepResults: StepResult[];
}
```
Final state after all steps (including any updates from steps).
Per-step results: `stepName`, `status` (done | error | skipped), `error?`, `durationMs`.
***
## Next Steps
AgentStep, FunctionStep, ConditionStep, ParallelStep.
retryPolicy, StepResult status, WorkflowResult.