AWS Strands is an open-source agent framework that simplifies building intelligent agents using Python decorators and a lightweight execution model. It provides a simple, callable interface for defining agents, supports built-in tools through the @tool decorator, and even enables math and reasoning capabilities out of the box. By integrating Strands with ZenML, you can run Strands agents inside production-ready pipelines. This unlocks orchestration, artifact tracking, reproducibility, and deployment flexibility—allowing you to move from experimentation to enterprise-scale AI workflows with ease. Integrating AutoGen into ZenML enables you to embed these conversational agent workflows into reproducible, versioned pipelines. This brings production-ready orchestration, tracking, continuous evaluation, and deployment flexibility—so your AutoGen agents go from prototype to scalable, monitored system faster and more reliably Analytics Vidhya.

from zenml import ExternalArtifact, pipeline, step
from agent import agent

@step
def run_strands(query: str) -> str:
    return str(agent(query))

@pipeline
def strands_weather_pipeline() -> str:
    q = ExternalArtifact(value="What's the weather like in Tokyo?")
    return run_strands(q.value)

if __name__ == "__main__":
    print(strands_weather_pipeline())