Sequential

A linear workflow where each agent processes the output from the previous agent, ideal for intent refinement, multi-step validation, or staged content creation.

Overview

Sequential compositions shine when work must pass through clearly defined stages. Each agent can tighten the scope, enrich the data, or validate the previous step before passing the baton.

Demo Scenario: Refine Then Answer

Two lightweight agents collaborate on a user question:

1. Intent refiner – rewrites the user's short prompt into a clear question

2. Answerer – provides the final response using the refined question

Diagram

Implementation Steps

1. Create two agents

   from glaip_sdk import Agent
   
   refiner_agent = Agent(
       name="refiner_agent",
       instruction="""You are an intent refiner. Rewrite ambiguous user text as a clear, specific question. Respond with only the reformulated question.""",
   )
   
   answerer_agent = Agent(
       name="answerer_agent",
       instruction="""You are a helpful coding assistant. Answer concisely and include a minimal Python snippet when appropriate.""",
   )

2. Run the agents sequentially

   demo_input = "python list to str"
   
   refined_question = refiner_agent.run(demo_input)
   answerer_agent.run(refined_question)

3. Clean up the demo agents

   # Only needed if agents were deployed
   # answerer_agent.delete()
   # refiner_agent.delete()

How to Run

From glaip-sdk/python/glaip-sdk:

poetry run python examples/multi-agent-system-patterns/sequential/sequential.py

Set the usual environment variables in .env:

OPENAI_API_KEY=your-openai-key-here

Output

Sequential Multi-Agent Pattern Demo
===================================
Refined question: "How can I convert a Python list to a string?"
Answer: explains `"".join(list)` with a short example.

Notes

• Extend the pipeline with additional stages (validation, formatting) by adding new agents and invoking them in order.

• Persist intermediate outputs when debugging by saving run transcripts.

• Combine with the router pattern so only certain requests enter the sequential flow.

Related Documentation

• Agents guide — Configure instructions and streaming renderers.

• Automation & scripting — Capture transcripts inside CI pipelines.

• Security & privacy — Apply memory and PII policies between stages.