Using AI Chatbots as Personalized Tutors
Students already turn to AI chatbots when they get stuck. The question for educators is not whether this will happen, but whether students will use these tools as coaches for learning or as answer machines.
The goal is to turn the chatbot into a tutor that supports thinking, practice, and feedback — without replacing the student’s work.Why students use AI tutors
AI tutoring works best for low-stakes, high-frequency learning tasks: explaining concepts, generating practice, and helping students diagnose gaps.
Key benefits:
- Availability: help outside office hours and between classes.
- Adaptation: multiple explanations, examples, and levels of detail on demand.
- Practice: quizzes, worked examples, and targeted drills.
- Accessibility: multilingual support and the ability to rephrase or simplify text.
What an AI tutor should (and should not) do
An AI tutor is most valuable when it helps students learn how to get to an answer, not when it provides the answer immediately.
Encourage students to use it for:
- Step-by-step explanations and hints.
- Self-testing (flashcards, mini-quizzes, “explain this back to me”).
- Checking understanding (“what assumption am I using here?”).
- Feedback on reasoning or drafts, without rewriting the work.
Be explicit that they should not use it for:
- High-stakes decisions or “final authority” on correctness.
- Generating submissions to hand in as their own work.
- Fabricating sources or citations (which students must verify themselves).
Students should treat AI outputs as drafts to evaluate, not facts to trust. If you want a dedicated activity for this, see Teaching Students to Critically Evaluate AI Outputs.
Getting Started: Setting Up Your AI Tutor
Choose a platform
Pick a tool that is easy for students to access and that supports the languages you need. Also consider privacy and compliance; if required, confirm whether the platform is approved for educational use by your institution.
Define the tutor’s role and boundaries
To create a good AI tutor requires good prompting skills. Give the chatbot a clear teaching role and a clear boundary: it should help the student learn, not do the work.
For instance, students can start with:
You are a friendly and knowledgeable tutor for my Introduction to Biology course. You will explain concepts in simple terms, give examples, and ask me questions to check my understanding. If I get something wrong, guide me to the right answer step-by-step.
Adjust the prompt to fit your discipline and the level of your students. The goal is to have the AI adopt a pedagogical style: it should not just give answers away, but engage the student in learning (for example, through hints, dialogue, or worked examples they can replicate).
Share these guidelines with students so they know how to prompt effectively. Encourage them to include context (“I’m studying X, I don’t understand Y…”), and to specify the type of support they want (a hint, an analogy, a worked example, or a short quiz).
To get you started, a sample prompt is included below.
Ground it in course material (when appropriate)
If the platform allows it, have students paste excerpts or work with course-provided materials (definitions, problem statements, worked examples, rubrics). While LLMs have broad knowledge, they may not match your syllabus, notation, or conventions.
When students supply course context, the tutor becomes more aligned — and you get fewer confident-but-off-target explanations.Pilot it yourself
Test a few realistic student questions and check the outputs. If responses are too advanced, too shallow, or too “answer-first,” refine the initial prompt you plan to share with students.
Introduce it to students with norms
Explain why you’re encouraging AI tutoring and how it fits your course expectations (including what students must not do). Provide access instructions and a few “good use” examples.
It can help to do a short live demo showing how to ask for hints, how to ask follow-up questions, and how to verify claims.
Iterate based on student experience
Consider a low-stakes activity where using an AI tutor is part of the process (for example: “use it to generate a quiz, then write a short reflection on what you missed and why”).
Gather feedback: where did the tutor help, and where did it mislead? If students mostly use it as a shortcut, explicitly model better prompts (“give me a hint”, “ask me questions”, “help me check my work”).
Adapting the AI Tutor to Different Subjects
One advantage of AI tutors is that the same prompting patterns work across disciplines: ask for clarification, ask for practice, and ask for feedback. Below are concrete examples you can share with students.
Science & Engineering
Examples:
Explain this concept in three ways: intuitive, formal, and with an example.Give me 5 practice questions on [topic], with answers hidden until I ask.I tried this approach and got stuck here: [paste work]. Give me a hint, not the solution.
Humanities & Social Sciences
Examples:
List three competing interpretations of [text/event], each with the strongest supporting reasons.Ask me Socratic questions that help me refine my thesis about [topic].Critique this paragraph’s argument and evidence. Do not rewrite it.
Mathematics
Examples:
Show a step-by-step solution, then give me a similar problem to try.Here is my solution: [paste]. Check it and tell me the first step that is wrong (if any).Explain why this substitution/assumption is valid in this step.
Foreign Languages
Examples:
Only speak [language]. Correct my mistakes after each message, and explain the correction briefly.Give me 10 sentences to translate that use the past tense and common idioms.Role-play a [scenario]. Keep it at CEFR level [A2/B1/B2].
Example Prompt: General Tutor
You are a supportive, encouraging tutor. Your job is to help me understand concepts by explaining ideas and asking me questions.
Rules:
- Ask one question at a time.
- Start by asking what I want to learn. Then ask my level (beginner/intermediate/advanced). Then ask what I already know.
- Prefer hints, guiding questions, and worked examples I can follow — do not jump straight to final answers.
- If I get something wrong, point to the first mistake and give a hint for the next step.
- End most responses with a question that checks my understanding.