The task
You need a thesis topic (undergraduate honours, masters, or PhD proposal) and every idea you have either feels done, infeasible in your timeline, or unaligned with your advisor’s interests. Topic selection is famously the worst-shaped part of grad school: you do not yet know what you do not know. AI is useful here because it scans broadly across recent work and forces you to compare 15 directions instead of fixating on the first idea.
When AI helps — and when it does not
AI is excellent at breadth: listing 15 directions across a field, suggesting cross-disciplinary angles, and roughing out the research question. It is dangerous at depth. AI confidently fabricates papers, misattributes findings, and miscalls feasibility. Treat AI as a brainstorming partner whose feasibility scores you ignore until verified. The final list goes to a human advisor; nothing AI says about citations is reliable without checking.
What to feed the AI
- Field and sub-area (Health Informatics, with focus on EHR ML)
- Your advisor’s known interests and recent papers
- Methodology preferences (qualitative, quantitative, mixed, computational)
- Hard constraints: time, data access, IRB feasibility, funding
- Your prior work / coursework, so AI does not propose topics you have already touched
- Programmatic requirements (page count, defence format)
Copy-ready prompt
Generate 15 thesis topic directions.
Field and sub-area: <area>
Advisor's interests (recent paper titles or themes): <list>
Method preferences: <quant / qual / mixed / computational>
Hard constraints: <time / data / IRB / funding>
My prior work or related coursework: <list>
Programme requirements: <page count, defence format>
For each direction, return:
- A one-sentence research question (specific, falsifiable, scoped)
- Why this matters (in 2 sentences — to whom, what changes if answered)
- Feasibility within my constraints, 1-5 (be honest)
- Main risks (data access, ethics, scope creep, novelty)
- Adjacency to advisor interests (1-5)
- A starting paper to read — name a real paper if you can verify it; otherwise write [VERIFY: type of paper to find]
The 15 should span at least 3 sub-areas. If two are too similar, replace one. Do not invent citations.A follow-up pass: “For my top 3, write a half-page proposal each — problem, hypothesis, method sketch, expected contribution, risks.”
Recommended output structure
A 15-row table: title / research question / why / feasibility / risks / adjacency / starting paper. Highlight 3 to take to your advisor. Bring printouts to office hours, not a list on a phone.
How to check the output is usable
- Each research question is falsifiable and scoped: not “study X in Y context” but “does X change Y under condition Z?”
- Feasibility scores match your constraints honestly. A 5/5 with no data access is wrong
- Starting papers are real (search the title; do not trust AI)
- The 15 are not minor variations of one idea
- 3 directions are clearly aligned with your advisor’s interests
Common mistakes
- Trusting AI feasibility scores: AI overestimates almost everything
- Letting AI invent citations: even confidently named ones are often wrong. Verify every paper
- Skipping advisor adjacency: a brilliant topic your advisor cannot supervise is a dead topic
- Picking the most exciting topic: pick the most finishable one within your timeline
- Going wide instead of deep: once you have 15, narrow fast
Practical depth notes
For AI Thesis Topic Brainstorm: 15 Directions with Feasibility Notes, the difference between a usable AI result and a generic one is the input packet. Give the model the audience, the current draft or raw material, the desired format, the decision you need to make, and two examples of what good and bad output look like. Ask it to preserve facts first, then improve structure or wording second.
After the first response, do a separate review pass. Look for missing constraints, invented details, weak calls to action, and language that sounds plausible but does not match the real situation. The best final output should be easy to use immediately: clear owner, clear next step, and no hidden assumption that someone else has to untangle. A stronger version of this workflow also defines the handoff. Decide who will use the output, what they should do next, and what information would make them reject it. If the deliverable is copy, test whether it has a single clear action. If it is analysis, test whether it separates observation from recommendation. If it is planning, test whether dates, owners, and tradeoffs are explicit enough for someone else to execute.
FAQ
- How early should I do this? 6-12 months before proposal deadline; later if undergrad.
- Should I run the prompt with different AI models? Yes. They have different reading biases, so two models give better variety.
- What about novelty? AI is bad at novelty assessment. A real lit search and your advisor are the source of truth.
Related
- Study plan prompts: schedule the topic-search process
- Explain difficult concept: for tough background reading
- Study notes cleanup: clean notes from lit reviews
- AI paper reading workflow: read recent literature efficiently
- Claude long doc workflow: when papers are long
- Exam study plan: same scheduling pattern