Prepare for a parent's cancer treatment talks with a tumor-board-style ChatGPT prompt
Copy the prompt below and paste it into the AI tool named on this page.
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
Act as a tumor board for my mother's cancer case: an oncologist, a radiation specialist, a molecular pathologist, a clinical-trials expert and a patient advocate. Using the records I share, discuss the treatment options and give me a source-cited report with questions for the doctors.
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Help my family understand a loved one's cancer treatment options and prepare questions for the care team. Questions to ask me first: - What type and stage of cancer is it, and what treatment has already been given? - What decision is coming up, and when is the next appointment? - Which records can you share (pathology, imaging, lab results, clinic notes)? Inputs (fill in or confirm): - Diagnosis and history: [DIAGNOSIS / HISTORY] - Records: [PATHOLOGY / IMAGING / LABS / NOTES] - Upcoming decision and appointment date: [DECISION / DATE] - What matters most to the patient: [PRIORITIES] Rules: - Reason from five viewpoints: medical oncologist, radiation oncologist, molecular pathologist, clinical-trials expert and patient advocate, and let them respond to each other. - Cite a source for every factual claim, and say when evidence is weak or mixed. - Flag anything in the records that seems unaddressed, such as an imaging finding or side effect, as a question for the care team. - Don't recommend a treatment; lay out options, trade-offs and questions. - Keep identifying details out unless I've chosen to include them. Checkpoint: Show a one-paragraph summary of the case as you understand it and wait for me to correct it before running the full review. If you get stuck: If records are missing for an important question, list what to request from the care team. Verify before you finish: Check that every finding you mention appears in the records I shared. Output: A source-cited report with a plain-language summary, options and trade-offs, and a numbered list of questions for the next appointment. Done when: We have a clear list of questions to take to the oncologist, and nothing in the report claims more than the records show.
AI tools
Outcome
When John Bailey's mother's cancer came back, Bailey set up an AI assistant loaded with the mother's records and treatment history, using ChatGPT Projects and custom GPTs, to summarize test results and pathology reports in plain language. For big decisions, Bailey ran Deep Research in ChatGPT, Claude and Gemini with a prompt that had the AI reason as an oncologist, a radiation specialist, a molecular pathologist, a clinical-trials expert and a patient advocate, which produced a detailed, source-cited report. On at least two occasions it surfaced details that were initially overlooked, including a finding in a radiology report. The AI didn't choose treatments; it helped the family ask better questions.
Evidence: Article or interviewA newsletter, journalist or interview account of what happened.
Source
- Posted
- by John Bailey (AEI)
- Last checked
- Method:
- How we verify
https://ctse.aei.org/what-using-ai-for-my-moms-cancer-taught-me/
Context: Health note: Bailey stresses that the AI didn't choose treatments; it helped the family prepare for conversations with the care team.
Related cases
Research a Victorian-born grandfather's life with Claude, ChatGPT and Gemini deep research (partial)
Dan Taylor-Watt gave Claude, ChatGPT and Gemini the same brief, with deep research turned on, to research a paternal grandfather, Cecil, who died in 1960, starting from a Word document written by Taylor-Watt's father. Claude took about 6 minutes, used 340 sources and wrote an 11-page, 4,219-word report; it found no significant new information but flagged inaccurate dates, and it later made a 3-minute-30-second narrated video using code and an open-source voice model. ChatGPT took 9 minutes, ran 714 searches and wrote 14 pages (4,659 words); it caught an error about the year of the fire that destroyed service records, noted that the LNER railway wasn't created until 1923, found information on the first wife's family, and spotted a Lance-Corporal's chevron in a photo, but its video attempt fell short. Gemini wrote the longest and most visual report (5,347 words), but its maps were wrong (Osmotherley is east, not south, of Northallerton), it missed the date problems, and it said it couldn't make a video.
PersonalClaudeChatGPTGeminiPartialRecreated promptEvidence: Article or interviewView CaseCompare ChatGPT, Gemini and Claude at building a resume, judged by a recruiter
How-To Geek's Dibakar Ghosh gave the same job posting and prompt to Claude, ChatGPT and Gemini, each told to ask them questions first; ChatGPT asked 30. They liked Gemini's look best, but the recruiter picked ChatGPT's: the only one-page resume, with no fabricated details, though they found it busy. They say the questionnaire step is what made it work and that AI resumes still need human oversight.
PersonalChatGPTGeminiClaudeWorkedRecreated promptEvidence: Article or interviewView CaseTurn a handwritten family pie recipe into an infographic with Gemini and ChatGPT (it garbled the recipe)
A TechRadar writer photographed their mother's 30-year-old handwritten apple pie recipe and asked Gemini and ChatGPT to turn it into a clear, cartoon-style infographic. Gemini's version was cute but full of misspellings and nonsense like 'Dash nutamon' and a cheese grater, and corrections didn't fix it; ChatGPT did marginally better but left out details. Claude gave the clearest, if plain, recreation. They called Gemini's first try unusable and kept their paper original.
PersonalGeminiChatGPTClaudeFailureEvidence: Article or interviewView Case