Demo: Create AI Agent with OpenAI
Overview of this demo building guide
This is a demo guide on how to go about building an AI agent for the hackathon. This is the minimum action demo which you can follow as a guide to build your agent without having to do much, but remember that we expect all the participants to dive deeper and build the best agent that they can by putting in additional efforts. But if you are completely new to the world of building, you can definitely use this process to build your first agent. Note: The winners of the hackathon will be decided based on the most capable and deserving AI Agent built.
Steps 1-4: Platform Setup & Discovery
Step 1: Sign up on JCurve.Tech
Action: Visit https://jcurve.tech.
Navigation: Click AI Agent Hackathon in the top right (see Image 1, follow the arrow).
Result: You’ll land on the hackathon page. Review the details to understand the initiative.
Next: Click Signup in the top right (see Image 2) to create an account.
Image 1
Image 2
Step 2: Verify your email address and create a password
Action: On the signup screen, enter your email address (use the same email as on your CV/Resume) and click Verify Email.
Email Check: Look for a verification email in your inbox.
Verification: Click the link in the email to verify your email address.
Password Setup: After verification, create a password to complete the signup process (see Images 3 and 4).
Image 3
Image 4
Step 3: Sign in and select your dream job
Action: Log in using your credentials after password confirmation.
Navigation: You’ll see the “Select Your Dream Job” page (see Image 5).
Selections:
Choose your status (e.g., Student) and enter your student ID.
Select your Dream Company, job family/category, and skills/technologies (e.g., Front End Engineer II, IN Payments; see Image 6).
Image 5:
Image 6:
Step 4: Practical Skills and Hackathon Overview
Action: After selecting your dream job, you’ll land on the Roadmap page for that job.
Navigation: Click Practical Training - AI Hackathon 2025 to go to the Hackathon homepage.
Exploration:
Review the hackathon’s 4-week structure, learning tracks, and project details.
Understand that you’ll build production-ready AI agents, gaining real-world experience valued by employers.
Take your time browsing through the hackathon content. You'll see the 4-week structure, learning tracks, and exactly what you'll build. This isn't just theory – you'll create production-ready AI agents.
Image 7:
Image 8:
Image 9:
Steps 5-7: Hackathon Registration & Setup
Step 5: Complete Registration Form
Action: Click the Register button on the hackathon page.
Details: Fill in your personal details, select your preferred learning track, and share your motivation for joining.
Please note that Github email should be of same email account that you have on JCurve platform. Github username should be from the same Github email account used.
Result: Your registration is submitted, initiating your participation.
Image 10:
Step 6: Email Confirmation from JCurve/GitHub
Action: Check your inbox (and spam folder) for a GitHub invitation from JCurve.
Purpose: The invitation provides access to your private GitHub repository, where your code and projects will be stored.
Image 11:
Step 7: Accept GitHub Invitation
Action: Log in to GitHub and accept the invitation.
Result: Gain access to starter code, templates, and your personal development workspace in the private repository.
Image 12:
Image 13:
Your private GitHub repository is full set, and you are all set to start the AI Agent building journey.
Steps 8-10: Development Process
Step 8: Development Environment Setup - Terminal/ VSCode Installation
"With your repo ready, it's time to set up your local development environment. Follow our step-by-step setup guide to get Python, VS Code, and all necessary tools installed."
Tools Needed: Install Visual Studio Code (VSCode) and Python.
VSCode Installation: Follow Setting up Visual Studio Code.
Python Setup: Refer to Getting Started with Python in VS Code.
Launch VSCode to get started….
Steps:
Clone Repository using the command: git clone <your new private repo link>
Clone your private repository (e.g., git clone https://github.com/JCurveTech/AIAgentHack2025-rogerdev101).
Open the repository in VSCode or your preferred code editor.
Note: The demo app creates social media posts, a blog, and a story based on a user-specified topic, with a UI featuring two input fields (OpenAI key and topic).
Image 14:
Image 15:
3. Set Up Branch:
In the repo, you will get a basic template with a main.py file and requirements.txt
Create a branch for your AI agent: git checkout -b feature/ai-agent.
4. Install Dependencies:
The repository includes a main.py file and requirements.txt.
Run pip install -r requirements.txt in the terminal to install required Python libraries. Add and reinstall any additional libraries as needed.
Image 16:
5. Run the Template:
Execute the sample code with streamlit run main.py.
Image 17:
Image 18:
6. Obtain OpenAI API Key:
Sign up at https://platform.openai.com/ to get a free API key (independent of JCurve’s account creation).
Note: Please check on openai for latest free trial and pricing updates.
Image 19:
7. Now you are Ready to code your Imagination
Steps 9: Develop Your AI Agent
Action: Code your AI agent using the provided template and your imagination.
Environment: Use VSCode (Recommended) or any other code editor of your preference to write and test code in your repository’s feature/ai-agent branch.
Purpose: Build a functional AI agent that aligns with the hackathon’s objectives (e.g., creating social media content based on user input).
Step 10: Local Testing and Code Push
a. Local Testing:
Run the app locally using streamlit run main.py.
Test the agent, debug issues, and iterate until it performs as expected.
b. Push Code:
Stage changes: git add .
Commit changes: git commit -m “implemented AI agent”
If the branch is newly created on local and needs to be pushed on github then candidate needs to use git push --set-upstream origin feature/branch. If the branch is already with origin then only use git push
c. Purpose: Hands-on testing and iteration ensure a polished agent, setting you apart as a candidate.
Steps 11-12: Documentation & Submission
Step 11: Create Documentation
a. Action: Write a professional README file in your repository.
b. Content:
Explain your approach, technical decisions, and project details.
Include instructions for testing and evaluating the AI agent.
c. Purpose: The README becomes part of your portfolio, showcasing your ability to document work clearly.
Step 12: Final Submission
Submit via JCurve:
Go to the submission tab on the JCurve platform.
Provide the Repository branch URL, a demo video, and a project description.
If you need to submit another version, create another branch and resubmit the Repository branch url on the JCurve platform.
b. Result: Your completed AI agent, documentation, and submission form a portfolio piece that demonstrates your skills to employers.
Please note: Create thorough documentation and outline the steps involved to test and evaluate the agent.
Image 20:
Last updated