Praison AI

Repetitive Agents

Handle batch and loop tasks with AgentFlow and the loop() helper

Run the same agent step over a list, CSV, or text file — then aggregate results in one workflow.

python
from praisonaiagents import Agent, AgentFlow, loop

processor = Agent(
    name="Processor",
    instructions="Process each item thoroughly.",
)

workflow = AgentFlow(
    steps=[
        loop(processor, over="topics"),
        Agent(name="Summariser", instructions="Summarise all processed results."),
    ],
    variables={"topics": ["AI Ethics", "Machine Learning", "Neural Networks"]},
)

result = workflow.start("Research and summarise these AI topics")

The user supplies a list of items; the workflow loops the agent over each entry then summarises results.

Diagram

Next iteration

Done

Input

Looping Agent

Task

Output

Quick Start

  1. Simple Usage

    Loop an agent over a variable list:

    python
    from praisonaiagents import Agent, AgentFlow, loop

processor = Agent(name="Processor", instructions="Process each item thoroughly.")

workflow = AgentFlow(
    steps=[
        loop(processor, over="topics"),
        Agent(name="Summariser", instructions="Summarise all processed results."),
    ],
    variables={"topics": ["AI Ethics", "Machine Learning", "Neural Networks"]},
)

result = workflow.start("Research and summarise these AI topics")
print(result["output"][:500])
  2. With Configuration

    Process rows from a CSV file with a custom handler:

    python
    from praisonaiagents import Agent, AgentFlow, WorkflowContext, StepResult, loop

support_agent = Agent(
    name="Support Agent",
    instructions="Resolve customer issues efficiently.",
    model="gpt-4o-mini",
)

def handle_customer(ctx: WorkflowContext) -> StepResult:
    row = ctx.variables.get("item", {})
    name = row.get("name", "unknown")
    issue = row.get("issue", "unknown")
    response = support_agent.chat(f"Help {name} with: {issue}")
    return StepResult(output=f"{name}: {response}")

workflow = AgentFlow(steps=[loop(handle_customer, from_csv="customers.csv")])
result = workflow.start("Process all customer issues")

How It Works

Diagram
sequenceDiagram
    participant Flow as AgentFlow
    participant Loop as loop()
    participant Agent
    participant File as CSV / list

    Flow->>Loop: iterate over items
    Loop->>File: read row or list item
    Loop->>Agent: run step per item
    Agent-->>Loop: StepResult
    Loop-->>Flow: loop_outputs
Input sourceParameterBehaviour
Variable listover="topics"Iterates variables["topics"]
CSV filefrom_csv="data.csv"One sub-step per row
Text filefrom_file="urls.txt"One sub-step per line
Parallelparallel=TrueRuns iterations concurrently

Loop outputs are stored in result["variables"]["loop_outputs"] by default.

Common Patterns

CSV customer support

csv
name,issue
John,Billing problem
Jane,Technical issue
Sarah,Password reset
python
workflow = AgentFlow(steps=[loop(handle_customer, from_csv="customers.csv")])

Line-by-line URL analysis

python
def analyse_url(ctx: WorkflowContext) -> StepResult:
    url = ctx.variables.get("item", "")
    result = url_agent.chat(f"Analyse this website: {url}")
    return StepResult(output=f"{url}: {result}")

workflow = AgentFlow(steps=[loop(analyse_url, from_file="urls.txt")])

Parallel batch processing

python
workflow = AgentFlow(
    steps=[loop(process_item, from_csv="data.csv", parallel=True, max_workers=4)]
)

Best Practices

Validate input files before starting

Check that CSV files exist and have headers. Empty files produce zero iterations silently.

Use parallel=True for independent items

When sub-steps do not depend on each other, set parallel=True and cap workers with max_workers.

Aggregate with a final summariser step

Add a summariser agent after the loop step rather than embedding aggregation inside each iteration.

Keep loop handlers focused

Pass row data via ctx.variables["item"] and return a StepResult — avoid side effects outside the workflow context.

Related

Workflow Loop

Loop patterns inside multi-step workflows

 Workflow Parallel Execution

Run independent workflow branches concurrently