Scribd
Upload
42 views5 pages

AI Investment Property Bot CrewAI Presentation

The document outlines the development of an AI-Powered Investment Property Bot using Crew AI, an open-source framework for autonomous AI agents. It details the project's goals, implementation steps, and technology stack, emphasizing automation in real estate investment analysis. The project aims to showcase the collaborative capabilities of multiple AI agents in specialized tasks, ultimately enhancing data gathering and reporting for investors.

Uploaded by

adnanfaya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
42 views5 pages

AI Investment Property Bot CrewAI Presentation

The document outlines the development of an AI-Powered Investment Property Bot using Crew AI, an open-source framework for autonomous AI agents. It details the project's goals, implementation steps, and technology stack, emphasizing automation in real estate investment analysis. The project aims to showcase the collaborative capabilities of multiple AI agents in specialized tasks, ultimately enhancing data gathering and reporting for investors.

Uploaded by

adnanfaya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Building an AI-Powered Investment

Property Bot using Crew AI


Slide 1: Title Slide
​
Title: Building an AI-Powered Investment Property Bot using Crew AI​
Presented By: Adnan K P​
Course: MSc ELECTRONICS​
Roll No: 244003​
(Optional: Add University/College Logo and Date)​

Slide 2: Introduction
​
What is CrewAI?​
- An open-source framework for orchestrating autonomous AI agents.​
- Enables multiple AI agents with different roles and tools to collaborate on complex tasks.​
- Focuses on "collaborative intelligence".​
​
Project Goal:​
- To demonstrate how CrewAI can be used to build a practical application: an AI bot that
researches and analyzes real estate investment properties.​
​
Relevance:​
- Automation in data gathering and analysis for real estate investment.​
- Showcases the power of multi-agent systems for specialized tasks.​
- Application of AI beyond typical chat interfaces.​

Slide 3: Core Concepts of CrewAI


​
Agents:​
- The fundamental building blocks.​
- Each agent has a specific role, goal, and backstory.​
- Can use specific Language Models (LLMs) like OpenHermes, GPT, etc.​
​
Tasks:​
- Specific assignments for agents.​
- Define expected output formats.​
​
Tools:​
- Extend agent capabilities (e.g., internet search tools like Serper).​
​
Crew:​
- A group of agents working together.​
​
Process:​
- The workflow defining how agents collaborate.​

Slide 4: Project Implementation - Step 1: Building the Agent


​
Objective: Create the primary researcher agent.​
Configuration:​
- Role: Senior Property Researcher​
- Goal: Find promising investment properties​
- Backstory: A veteran property analyst...​
- LLM: e.g., OpenHermes​
​
Code Snippet:​
researcher = Agent(​
role='Senior Property Researcher',​
goal='Find promising investment suburbs in Sydney',​
backstory='Expert analyst skilled in market research...',​
llm=my_llm_model​
)​

Slide 5: Project Implementation - Step 2: Defining Tasks


​
Objective: Tell the agent exactly what to do.​
Task Definition:​
- Description: Search the internet and find 5 promising real estate investment suburbs in
Sydney.​
- Expected Output: A structured report per suburb.​
- Agent: Assign the task to the researcher agent.​
​
Code Snippet:​
research_task = Task(​
description='Find 5 promising investment suburbs in Sydney...',​
expected_output='A detailed report listing Suburb Name, Mean Price, Rental Yield...',​
agent=researcher​
)​

Slide 6: Project Implementation - Step 3: Setting Up the Crew


​
Objective: Assemble the agent(s) and task(s).​
Configuration:​
- Define the agents and tasks.​
- Specify the process.​
​
Code Snippet:​
property_crew = Crew(​
agents=[researcher],​
tasks=[research_task],​
process=Process.sequential​
)​
results = property_crew.kickoff()​

Slide 7: Project Implementation - Step 4: Adding Tools


​
Problem: The agent needs real-time data.​
Solution: Equip the agent with tools like SerperDevTool.​
​
Code Snippet:​
from crewai_tools import SerperDevTool​
search_tool = SerperDevTool()​
​
researcher = Agent(​
tools=[search_tool],​
allow_delegation=False​
)​

Slide 8: Project Implementation - Step 5: Multi-Agent Crew


​
Objective: Add a writer agent to enhance output.​
​
Writer Agent:​
- Role: Senior Property Analyst / Report Writer​
- Goal: Summarize the research findings.​
- Backstory: Skilled in compiling analytics.​
​
New Task: Summarise the property information.​
​
Updated Crew: Include both researcher and writer agents.​

Slide 9: Technology Stack


​
Core Framework: CrewAI​
Programming Language: Python​
Key Libraries: crewai, crewai_tools​
LLMs: OpenHermes, OpenAI models, Langchain, LlamaIndex​
Tools/APIs: Serper API, other real estate APIs​
Environment: Conda/venv, .env for API keys​

Slide 10: Example Output


​
Final Output:​
- Structured report: Suburb Name, Prices, Rental Yield, Vacancy Rates, Key Factors.​
- If using writer agent: a summary or bullet points for investors.​

Slide 11: Potential Enhancements / Future Scope


​
- Integrate dedicated real estate data APIs.​
- Add agents for financial modeling or risk assessment.​
- Save results in a database.​
- Build a UI with Streamlit or Flask.​
- Use processors for enhanced state management.​

Slide 12: Conclusion


​
Summary: CrewAI allows building collaborative AI agent systems.​
​
Project Recap: Demonstrated an Investment Property Bot using CrewAI.​
​
Key Benefits: Automation, specialization, adaptability.​
​
Closing Thought: CrewAI reflects the future of autonomous AI systems.​

You might also like