Align yourself.
Some of the tools below use terms that are worth knowing before you start.
Model - The AI itself. A model is a system trained on large amounts of data that can understand and generate text. ChatGPT, Claude, and Gemini are all models.
Agent - An AI that does things, not just answers questions. An agent can take actions, use tools, browse the web, write code, and complete multi-step tasks on its own.
API - A way for software to talk to other software. When an app "uses AI," it is usually sending requests to an AI model through an API.
API Key - A password that proves you are allowed to use an API. Keep it private. Never share it or put it in public code.
RAG (Retrieval-Augmented Generation) - A technique that lets an AI search through a set of documents before responding, so its answers are grounded in specific information rather than general knowledge.
Vector Embedding - A way of turning text into numbers so a computer can measure how similar two pieces of text are. The backbone of most AI search systems.
Repository - A folder that stores a software project and its full history of changes. GitHub is the most common place to host repositories.
GitHub - A website where developers store, share, and collaborate on code. Think of it as Google Drive for software projects.
MCP (Model Context Protocol) - A standard developed by Anthropic that lets AI models connect to external tools and services. Instead of an AI that just answers questions, MCP lets it take actions — reading files, sending messages, querying databases, and more. Claude uses MCP. So does OpenClaw.
ChatGPT
Made by OpenAI. The most widely used AI assistant in the world.
ChatGPT is a free AI assistant you can talk to like a person. Ask it to explain something, help you write, summarize an article, brainstorm ideas, or work through a problem. It runs in your browser, no downloads required. The free version is powerful enough to get started with immediately.

What you can do with it
-
Draft and edit writing
-
Answer questions and explain concepts
-
Summarize documents and articles
-
Help plan, organize, and think through decisions
Claude
Made by Anthropic. Built for thinking, writing, and working with AI systems.
Claude is a free AI assistant that excels at reasoning through complex problems, reading and analyzing long documents, and writing with precision. It is also the tool of choice for students who want to get into agentic AI work — building systems where AI takes real actions, uses tools, and operates across workflows.

What you can do with it
-
Read and analyze long documents and PDFs
-
Write, edit, and reason through complex ideas
-
Build and work with AI agents using tools like Claude Code and the API
-
Connect Claude to other tools and services through MCP
Perplexity
Made by Perplexity AI. The best AI tool for research.
Perplexity works like a search engine that actually answers your question. Every response cites its sources so you can verify what you are reading. Use it when you need to research a topic, find recent information, or get a real answer instead of a list of links.
What you can do with it
-
Research any topic with cited sources
-
Find current news and recent developments
-
Get direct answers to specific questions
-
Dig deeper with follow-up questions in the same thread

Openclaw
Open source. A personal AI agent that runs on your computer and takes real actions.
OpenClaw is not a chatbot. It is an autonomous AI agent that lives on your machine, connects to apps you already use — WhatsApp, Slack, Discord, email — and does things on your behalf around the clock. Schedule tasks, manage files, run code, browse the web. It became the fastest growing open source project in history in early 2026, surpassing 250,000 GitHub stars. Nvidia's CEO called it "the most important software release probably ever."

What you can do with it
-
Build a personal AI agent that operates 24/7
-
Connect AI to your existing apps and workflows
-
Run and schedule automated tasks without writing much code
-
Understand what agentic AI actually feels like in practice
Note: requires broad system access — follow security best practices before deploying.
Ollama
Open source. Run AI models on your own computer.
Ollama lets you download and run AI language models directly on your laptop — no internet required, no API key, no subscription cost. It is the fastest way to understand how AI models actually work under the hood, and gives you full privacy and control over your AI setup.

What you can do with it
-
Run models like Llama, Mistral, and Gemma locally
-
Chat with AI completely offline
-
Experiment with different models side by side
-
Use it as the foundation for building your own AI-powered tools
Cursor
Made by Anysphere. The AI code editor the industry has moved to.
Cursor is a code editor built on VS Code with AI built into every layer. It knows your entire codebase and can write, explain, debug, and refactor code inline as you work. It is the most widely used AI coding tool among professional developers right now and the fastest way for a student to go from idea to working software.

What you can do with it
-
Write code with AI suggestions that understand your whole project
-
Ask questions about your codebase in plain English
-
Debug errors with AI explanations
-
Build full applications with an AI collaborator alongside you
v0
What you can do with it
-
Generate full web UIs from a text description
-
Iterate on designs by describing changes in plain English
-
Deploy instantly with one click
-
Export clean code to build on further
Made by Vercel. Build websites and interfaces with a text prompt.
v0 turns a plain English description into a working, deployable web interface. Describe what you want — a landing page, a dashboard, a form — and v0 generates the code and renders it live. No design experience required. What the Applied AI Club used alongside Codex to build the Student AI Hub.

Codex
Made by OpenAI. An AI agent that writes and runs code for you.
Codex is a coding agent that works directly inside your GitHub repository. Give it a task in plain English — fix this bug, add this feature, refactor this file — and it writes the code, runs tests, and opens a pull request. Applied AI Club members used Codex to generate the HTML structure and content formatting for the Student AI Hub.

What you can do with it
-
Write and edit code from a plain English description
-
Automate repetitive coding tasks
-
Generate structured HTML, components, and scripts
-
Open pull requests directly to a GitHub repo

