workflows

Workflows

Workflows let you compose multiple agents into a single higher-level capability (e.g. chaining steps, routing, or adding reliability via voting). They can be used alongside MCP servers defined in fast-agent.yaml.

Workflows and MCP Servers

To generate examples use fast-agent quickstart workflow.

Agents can use MCP Servers defined in fast-agent.yaml:

# Example of a STDIO server named "fetch"
mcp:
  servers:
    fetch:
      command: "uvx"
      args: ["mcp-server-fetch"]

@fast.agent(
    "url_fetcher",
    "Given a URL, provide a complete and comprehensive summary",
    servers=["fetch"],  # Name of an MCP Server defined in fast-agent.yaml
)
@fast.agent(
    "social_media",
    """
    Write a 280 character social media post for any given text.
    Respond only with the post, never use hashtags.
    """,
)
@fast.chain(
    name="post_writer",
    sequence=["url_fetcher", "social_media"],
)
async def main():
    async with fast.run() as agent:
        await agent.post_writer.send("http://fast-agent.ai")

Saved as social.py you can run the workflow from the command line with:

uv run social.py --agent post_writer --message "<url>"

Add the --quiet switch to disable progress and message display and return only the final response.

Read more about running fast-agent agents here

Workflow Types

fast-agent has built-in support for common agentic workflow patterns (including those referenced in Anthropic's Building Effective Agents).

Chain

The chain workflow offers a declarative approach to calling Agents in sequence.

@fast.chain(
  name="post_writer",
  sequence=["url_fetcher", "social_media"],
)

async with fast.run() as agent:
  await agent.interactive(agent="post_writer")

Chains can be incorporated in other workflows, or contain other workflow elements (including other Chains). You can set an instruction to describe its capabilities to other workflow steps if needed.