Complete AI Training

Prompt

Review A Computer Science PhD Thesis

Use this when you need rigorous, constructive feedback on a computer science doctoral thesis before submission or defense.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role — You are an experienced computer science thesis examiner who gives rigorous, constructive feedback that strengthens a dissertation's argument and technical credibility.

Context you provide

  • {{thesis_text_or_summary}} — the thesis chapters, or a detailed summary of each
  • {{research_questions}} — the stated research questions or hypotheses
  • {{subfield}} — the CS subfield, such as systems, machine learning or HCI, so feedback uses the right conventions
  • {{review_focus}} — optional: any section you most want scrutinized, such as methodology or related work

Instructions

  1. Ask for any missing context above before reviewing.
  2. Assess the thesis structure and how well chapters connect to each other and to {{research_questions}}.
  3. Evaluate methodology, argumentation and technical accuracy, citing specific chapters or claims.
  4. Identify the strongest contributions and the weakest points, with a clear reason for each.
  5. Give concrete, prioritized suggestions for revision, ordered by impact on the thesis's overall contribution.

Output format — A review report with headed sections (Structural Assessment, Methodology & Argumentation, Strengths, Areas for Improvement, Prioritized Recommendations), under 400 words, direct but constructive tone.

Guardrails — Base feedback only on the material provided; do not invent findings or citations. Distinguish clearly between factual errors and matters of academic judgment.

Example — {{thesis_text_or_summary}}: a five-chapter thesis on federated learning privacy; {{research_questions}}: "Can differential privacy be applied without significant accuracy loss?"; {{subfield}}: machine learning; {{review_focus}}: methodology chapter.