Immigrant Friend AI
Immigrant Friend AI - From “I just landed” to “I am settled.” Moving to a new country means navigating unfamiliar systems while managing classes, money, housing, and everyday needs.
Core trick
Turns a student's profile into a prioritized settlement plan using web research, with source links and prepared actions the student completes.
Description
Immigrant Friend AI - From “I just landed” to “I am settled.”
Moving to a new country means navigating unfamiliar systems while managing classes, money, housing, and everyday needs. Immigrant Friend turns an international student’s situation into a personalized settlement plan.
My First 24 Hours prioritizes practical steps such as getting connected, confirming housing access, arranging transportation, and finding food. What Am I Forgetting? surfaces overlooked needs from the same profile and initial AI response. Ask Anything → Turn It Into Action researches questions about housing, banking, campus jobs, transportation, and student paperwork, then provides concrete next steps with source links.
Built with Python, Streamlit, GPT-6 Astra, and the OpenAI Responses API, the prototype combines web research, structured action plans, progress tracking, and downloadable checklists in a welcoming, mobile-friendly interface. It prepares actions for students to complete; it does not submit applications or make purchases.
README excerpt
# ImmigrantFriendAI **From “I just landed” to “I am settled.”** ImmigrantFriendAI turns an international student's situation into a practical settlement plan. It considers dependencies, finds information on the web, and connects each next step to an actionable resource. Built for a hackathon with Python, Streamlit, GPT-6 Astra, the OpenAI Responses API, web search, Structured Outputs, and a JSON student profile. The flagship example is a student who has just landed at SFO, is attending Santa Clara University, has no SIM or US number, needs groceries, and needs to reach an apartment in Santa Clara. The useful first step may be airport Wi-Fi and confirming apartment access before a phone purchase or a complicated transit journey. ## Run locally — ZIP or fresh folder Install Python 3.12 first. Extract `ImmigrantFriendAI.zip`, open the extracted **ImmigrantFriendAI** folder in VS Code, and open its terminal. Run: ```bash python3.12 -m venv .venv source .venv/bin/activate python -m pip install -r requirements.txt ``` Open the included `.env` file in VS Code and add your full API secret: ```dotenv OPENAI_API_KEY=your_full_project_secret_key OPENAI_MODEL=gpt-6-astra ``` Start the app with this exact command: ```bash python -m streamlit run app.py ``` Open [localhost:8501](http://localhost:8501). Stop with **Control+C**. To restart later, open the same folder, activate `.venv`, and run the Streamlit command again. The ZIP intentionally excludes the virtual environment: eac