Free AI tools you can use today

In this tutorial you will try a handful of free AI tools on small, real tasks and fill in a one-page toolkit that says "for this job, I use that tool". You need only a browser and a Google, Microsoft or email account. No coding is needed, except for the optional last section.

Free plans, limits and features change often. This lesson describes what each tool is for and what kind of free access it has, but check each tool's own page for today's limits. If you hit a limit, wait for it to reset or try another tool on the list.

A general chatbot is your all-purpose assistant. Pick one to start (ChatGPT, Gemini or Claude) and use it for a week before comparing. All three are good for explaining a topic, drafting and editing text, brainstorming and simple coding help.

Explain [a topic from your syllabus or work, e.g. how DNS works] in simple English for someone who has never studied it. Use one everyday analogy. Then ask me 3 questions to check my understanding, one at a time, and wait for my answer before the next.

What to expect: A good answer is short, uses an analogy that fits, and waits for you after the first question. If it dumps all three questions at once, tell it to ask one at a time.

A normal chatbot answers from training (and from search if it is switched on). A search-focused tool such as Perplexity, or the search mode in ChatGPT, Gemini or Copilot, looks things up on the web and shows links beside the answer. Use these for current facts: news, prices, exam notifications, release notes. The links are the useful part: open them, because the summary can still be wrong.

What are the current eligibility rules and last date for [an exam or scheme you care about, e.g. GATE registration]? Give the answer in 5 bullet points and list the official sources you used.

What to expect: A good answer links to the official website. If the only sources are blogs or coaching sites, go to the official page yourself and confirm dates there.

NotebookLM from Google lets you upload sources (PDFs, text, web pages and more) and then ask questions that it answers using only those sources, with citations pointing back to the passage. It is excellent for revision notes, long reports and research papers. Chatbots like ChatGPT, Gemini and Claude also accept file uploads in their apps, though the file types and size limits vary.

For learning to code, a chatbot is often enough: paste an error message and ask what it means. For help inside your editor, GitHub Copilot has a free plan for VS Code and other editors. Students can also apply to the GitHub Student Developer Pack to get more. Google's Gemini tools for developers also have free options for individuals. Always run and test the code you receive.

I am a beginner in [language]. Here is my code:

[paste code]

and here is the exact error message:

[paste error]

Explain in simple words what the error means and why it happened. Then show the fix and explain what you changed.

What to expect: A good answer explains the cause before the fix. If the fix does not work, paste the new error into the same chat.

Ollama runs open models locally. Your text never leaves your computer, and it works without internet once a model is downloaded. Small models are weaker than hosted ones, and you need enough memory. Install Ollama from ollama.com, then in a terminal:

ollama pull llama3.2
ollama run llama3.2

The first command downloads a small open model (the download can be a few gigabytes; use Wi-Fi). The second starts a chat in the terminal; type /bye to exit. If the model name is not found, see the Ollama model library for names that are available today.