70 lines
2.7 KiB
Markdown
70 lines
2.7 KiB
Markdown
# Go through the following steps to run the application:
|
|
|
|
1) Create Python Virtual Env from your root directory
|
|
python -m venv venv
|
|
|
|
2) Activate Virtual Env
|
|
a) Windows: venv\Scripts\activate.bat
|
|
b) Unix: source venv/bin/activate
|
|
|
|
3) Installing Dependencies
|
|
pip install -r requirements.txt
|
|
|
|
4)
|
|
Install GTK-for-Windows (needed to generate the PDF)
|
|
1.Download the installer and install: Go to the GTK-for-Windows runtime project on GitHub (https://github.com/tschoonj/GTK-for-Windows-Runtime-Environment-Installer/releases)
|
|
2.Ensure you check the box during installation that says "Add to the PATH environment variable".
|
|
|
|
5)
|
|
Disable Smart App Control (SAC) on Windows
|
|
1.Open the Start menu, type Windows Security, and press Enter.
|
|
2.Click on App & browser control from the left navigation panel or home menu.
|
|
3.Click the Smart App Control settings link.
|
|
4.Select Off to disable the feature
|
|
|
|
6) Setup OPENAI_API_KEY, LANGCHAIN_API_KEY, and SERPAPI_API_KEY from terminal
|
|
set LANGCHAIN_API_KEY=<your-langsmith-key>
|
|
set OPENAI_API_KEY=<your-api-key>
|
|
sett SERPAPI_API_KEY=<your-serpapi-key>
|
|
|
|
7) Running the Streamlit Application
|
|
python -m streamlit run app.py
|
|
|
|
|
|
# capstone_msagi
|
|
|
|
Course-end Project: Product Strategy Simulation
|
|
|
|
Multi-Agent Market Research and GTM Planning (n8n, MCP, and CrewAI)
|
|
|
|
Description
|
|
|
|
Overview
|
|
In this project, you will design and implement a multi-agent workflow system that automates market research and go-to-market (GTM) planning. The systems are implemented in n8n and CrewAI separately, but with similar functionality. The solution integrates four agents:
|
|
|
|
• Head Planner (orchestrator and documenter)
|
|
• Research Agent (finder)
|
|
• Analyst Agent (sense-maker)
|
|
• Strategy Agent (planner)
|
|
|
|
The workflow must orchestrate desk research, competitor analysis, and GTM plan drafting before exporting structured strategy documents to Google Docs.
|
|
|
|
Instructions
|
|
|
|
• Review the lessons and supporting materials on n8n workflows, MCP, and CrewAI
|
|
• Set up the required environment on the Ubuntu VM, including Node.js, n8n, and Python for CrewAI
|
|
• Execute the following steps:
|
|
|
|
Build the multi-agent orchestration with a Head Planner and three specialist agents with tools
|
|
Start the MCP server
|
|
Configure and connect the n8n workflow with the MCP
|
|
Implement CrewAI with defined agents, flows, and tools (MCP, SerpAPI)
|
|
• Test and debug each component individually (MCP tools with curl, n8n nodes with Execute Node, and CrewAI tasks end-to-end)
|
|
• Document the architecture, configuration steps, test runs, and error resolutions
|
|
• Submit the following:
|
|
|
|
Exported n8n workflow JSON file
|
|
CrewAI project files (UV structure)
|
|
Sample Google Doc output
|
|
CrewAI chatbot screenshots
|
|
Documentation (README file) covering the architecture, setup, and testing notes |