agent-skills/skills/multi-agent-sequential-workflow/SKILL.md

name, version, description, inputs, steps, outputs, tags, metadata

name	version	description	inputs	steps	outputs	tags	metadata
multi-agent-sequential-workflow	1.0.0	Gather and process information from multiple agents to generate a comprehensive travel guide.	User query with location	Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination. Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and the raw information provided by the researcher. Step 3: Writer agent (agent.py) formats the final response, including the structured travel guide content and prominently featuring the 'Suggested Web Pages' section.	Structured travel guide with key sections Final client response		source_repo extracted_at confidence https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git 0.95

multi-agent-sequential-workflow

Gather and process information from multiple agents to generate a comprehensive travel guide.

Setup

Dependencies:

pip install python langchain strands

Setup steps:

1. Install required dependencies using pip and ensure the BedrockModel is properly configured.

Key Files

• agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/agent.py - Contains the sequential workflow logic for gathering and processing information.
• agents/aws_strands/05-agent-strands-multiagent-workflow-sequential/app.py - Provides a FastAPI endpoint to interact with the multi-agent system.

Steps

1. Step 1: Researcher agent (agent.py) uses LangGraph create_react_agent with BedrockModel to gather raw facts about the destination.
2. Step 2: Travel Guide Generator agent (agent.py) synthesizes the gathered data into a structured travel guide based on the user's request and the raw information provided by the researcher.
3. Step 3: Writer agent (agent.py) formats the final response, including the structured travel guide content and prominently featuring the 'Suggested Web Pages' section.

Implementation Details

research_output = researcher_agent(query, stream=False)

guide_output = travel_guide_agent(planner_prompt, stream=False)

final_response = writer_agent(writer_prompt, stream=False)

Inputs

• User query with location

Outputs

• Structured travel guide with key sections
• Final client response

Failure Modes

• Specific failure scenario with mitigation: If any of the agents fail to process their tasks (e.g., network issues, model errors), the workflow will fail. Mitigation involves robust error handling and fallback mechanisms.

Source

Extracted from: https://github.com/omerbsezer/Fast-LLM-Agent-MCP.git Confidence: 0.95