# What to Leave Out of Interview Notes (and AI Summaries) > Interview notes should stick to the job's must-haves. What to leave out, how to tell ChatGPT the same, and a debrief prompt that keeps notes fair. Source: https://learn.ynteractive.com/content/blog/what-to-leave-out-of-interview-notes · Updated 2026-10-21 · Free from Stepthrough (https://learn.ynteractive.com) Quick answer Interview notes should record only what the candidate said and did that relates to the job's requirements, and leave out anything about age, family, health, religion or other personal traits that aren't about the work. When you use ChatGPT to turn a debrief into a [scorecard](https://learn.ynteractive.com/content/glossary/ai-test-scorecard), you have to tell it the same thing, because it summarizes whatever is in the transcript. The free lesson [Interview Debrief to Scorecard](https://learn.ynteractive.com/content/chatgpt-interview-debrief-scorecard) shows a request that does this, and catches a comment about a candidate's kids before it reaches the notes. Last updated October 21, 2026 [Take the free module →](https://learn.ynteractive.com/courses/ai-for-recruiting-and-hr/4)Module 4 of the free [AI for Recruiting & HR](https://learn.ynteractive.com/courses/ai-for-recruiting-and-hr) course, about 7 minutes. No account needed. By [Robert Breen](https://learn.ynteractive.com/content/about) · Published October 15, 2026 · Updated October 21, 2026 · 6 min read Recruiting · HR · ChatGPT This guide is for recruiters, HR managers and hiring managers. It is not legal advice: follow your company's hiring policy and the law where you hire. ## What should interview notes include? Notes should tie each point to a requirement of the role, with evidence. The simplest structure is the one an [interview scorecard](https://learn.ynteractive.com/content/glossary/interview-scorecard) uses: list the must-haves, rate the candidate on each, and quote what they said. In the lesson, a made-up physical therapy practice is hiring a Front Desk Lead. The must-haves are two or more years running a front desk, insurance verification, calming upset patients, and training other staff. Good notes look like this: - **Front desk experience: Strong.** Quote: "I book about sixty patients a day across three providers." - **Insurance verification: Partial.** Quote: "I check eligibility the day before every visit." Has not done referrals or authorizations. - **Training other staff: Not discussed.** The panel ran out of time. Each line says what was asked, what the candidate said, and how it maps to the job. "Not discussed" is honest and tells you what to cover in the next round. ## What should I leave out of interview notes? Leave out anything that isn't about the job's requirements. That includes guesses or remarks about: - age, family, children or pregnancy - health or disability - religion, race, national origin or ethnicity - marital status or who the candidate lives with - appearance, accent or "culture fit" impressions with no job-related evidence In the US, federal anti-discrimination law covers characteristics such as race, color, religion, sex, national origin, age, disability and genetic information, and many states and cities add more. Notes that mention these invite questions you don't want, and they're unfair to the candidate even when nobody meant harm. The lesson's transcript has a realistic example. One panelist says the candidate "mentioned she has two little kids, so, I don't know, the early shifts..." The HR manager stops it: "Let's leave that out. It's not about the job, and we don't weigh it. We asked every candidate if the seven thirty start works, and she said yes." The job-related question is the start time, asked of everyone. The kids are not part of the notes. ## How do I tell ChatGPT to keep a debrief summary job-related? Name the must-haves, ask for a quote as evidence, and say explicitly what to leave out. The request from the lesson: ```text You're my recruiting assistant. I'm Hannah, the HR manager at Willow Bend Physical Therapy. Below is the transcript of today's panel debrief for Kira Delgado, who interviewed for Front Desk Lead. The must-haves for the role are: two or more years running a front desk, insurance verification, calming upset patients, and training other staff. Give me: 1. A three-sentence summary that scores her on each must-have (Strong, Partial or Not discussed), with a short quote from the interview as evidence 2. The decisions we made 3. The action items as a table: task, owner, due date 4. Open questions Only use what's in the transcript, and only what's about the job's must-haves. Don't guess at age, family, health, religion or anything else that isn't job-related. If an owner or date isn't said, write "Not stated". ``` The lesson's finish sums up the result: the comment about the candidate's kids never made it into the notes, because the request told ChatGPT to stick to the job. ## Try it free, step by step **Score Every Candidate Fairly After the Interview using ChatGPT**. Turn the transcript of an interview panel's debrief into a scorecard against the role's must-haves, the decisions, action items with owners and dates, and a follow-up email to the candidate. You do every step yourself in a practice copy of ChatGPT, it checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/recruiting-interview-scorecard) [Or read the full step-by-step guide](https://learn.ynteractive.com/content/chatgpt-interview-debrief-scorecard) ## What should I leave out of the email to the candidate? Everything except the next steps. The panel's scores, its discussion and internal questions belong in your records, not in the candidate's inbox. The lesson's follow-up request: ```text Now write a short follow-up email from me to Kira inviting her to the final interview. Friendly and plain, under 120 words. Only the next steps: leave out the scores, our discussion and the pay question. ``` In the transcript, the candidate asked for about two dollars an hour over the posted [pay range](https://learn.ynteractive.com/content/glossary/pay-range), and the HR manager chose to check with the practice owner before deciding. That's an open question for the team, so it stays out of the email until there's an answer. ## Should AI make the hiring decision? No. The lesson is clear that the decision stays with people, not ChatGPT. Use AI to organize what the panel said against the must-haves, find what wasn't covered, and draft the follow-up. People decide who moves forward, and the lesson's panel also checks references before any offer. Candidate details are personal. Use a business account that doesn't train on your data, and leave out anything the scorecard doesn't need, like phone numbers or addresses. [Interview Debrief Template](https://learn.ynteractive.com/content/blog/interview-debrief-template) has the full debrief structure, and [ChatGPT for Recruiters](https://learn.ynteractive.com/content/blog/chatgpt-for-recruiters) covers more of the recruiting week. ## Does this work for other meeting notes too? Yes. The same "only use what's in the transcript, write Not stated instead of guessing" rule is the core of [Summarize a Meeting Transcript](https://learn.ynteractive.com/content/chatgpt-summarize-meeting-transcript), and it keeps any recap honest. For hiring, you add one more rule: only what's about the job. The [glossary entry on AI bias](https://learn.ynteractive.com/content/glossary/ai-bias) explains why that rule matters when AI handles people's information. ## Key takeaways - Interview notes should record job-related evidence against the role's must-haves, ideally with a short quote for each. - Leave out remarks or guesses about age, family, health, religion and other traits that aren't about the job. - Tell ChatGPT the must-haves, ask for Strong, Partial or Not discussed with a quote, and say "Don't guess at age, family, health, religion." - The candidate email should contain only next steps, not scores, the panel's discussion or open pay questions. - People make the hiring decision; AI organizes the notes and drafts the follow-up. ## Frequently asked questions **What should good interview notes look like?** Short, factual notes under each of the job's must-haves: what the candidate said or did, in their words where you can, and anything you still need to check. Leave out impressions about personality or appearance and anything personal that is not about the work. For what to ask when the panel meets, see these [interview debrief questions](https://learn.ynteractive.com/content/blog/interview-debrief-template). **Can I mention a candidate's availability in interview notes?** Yes, if it's about a job requirement you asked every candidate about, such as a set start time. Note the answer, not the reasons behind it. **What if a panelist brings up something personal in the debrief?** Say it isn't about the job and move on, as the lesson's HR manager does. Tell ChatGPT to only use what's about the must-haves so it stays out of the summary. **Is it legal to use ChatGPT for interview notes?** It depends on your company's policy and the law where you hire. This isn't legal advice. Keep the decision with people, share only what the scorecard needs, and use a business account that doesn't train on your data. **What does "Not discussed" mean on a scorecard?** The must-have never came up in the interview. It's a gap to cover in the next round, not a low score. ## Free lessons in this post - [Score Every Candidate Fairly After the Interview using ChatGPT](https://learn.ynteractive.com/content/chatgpt-interview-debrief-scorecard): Turn the transcript of an interview panel's debrief into a scorecard against the role's must-haves, the decisions, action items with owners and dates, and a follow-up… - [Summarize a Meeting Transcript with ChatGPT](https://learn.ynteractive.com/content/chatgpt-summarize-meeting-transcript): Paste a long meeting transcript into ChatGPT and get the decisions, an action items table with owners and due dates, and a follow-up email ready to send. ## Watch it in a free lesson: An AI Resume Screener, with a Fairness Step (Recruiting & HR) ### An AI Resume Screener, with a Fairness Step: video walkthrough Full walkthrough · 3:36 · with captions Have n8n read each applicant’s PDF resume, score it against the job’s must-haves with the evidence quoted, and rank it in Google Sheets, while a person makes every hiring call. The whole lesson narrated step by step, recorded in Stepthrough’s simulated practice environment. [Watch it with chapters and the full transcript](https://learn.ynteractive.com/content/ai-resume-screener-n8n-fairness#watch) From the free lesson [An AI Resume Screener, with a Fairness Step (Recruiting & HR)](https://learn.ynteractive.com/content/ai-resume-screener-n8n-fairness) ## Related terms Plain-English definitions, each with an example from a free lesson. [AI scorecard](https://learn.ynteractive.com/content/glossary/ai-test-scorecard) · [Action items](https://learn.ynteractive.com/content/glossary/action-items) · [AI bias](https://learn.ynteractive.com/content/glossary/ai-bias) · [AI citations](https://learn.ynteractive.com/content/glossary/ai-citations) · [AI note-taker](https://learn.ynteractive.com/content/glossary/ai-note-taker) · [AI summarization](https://learn.ynteractive.com/content/glossary/ai-summarization) · [Background check (employment)](https://learn.ynteractive.com/content/glossary/background-check) · [Candidate experience](https://learn.ynteractive.com/content/glossary/candidate-experience) [The full AI glossary](https://learn.ynteractive.com/content/glossary) ## Related prompts - [Action items table prompt](https://learn.ynteractive.com/content/prompts/action-items-table-prompt): Paste a meeting transcript or rough notes and get a table of every task, owner and due date, with "Not stated" wherever nobody… - [Feedback conversation script prompt](https://learn.ynteractive.com/content/prompts/feedback-conversation-script-prompt): Plan a short, direct feedback talk with a teammate: the specific moment, why it mattered, a question to hear their side and one… - [Interview debrief agenda prompt](https://learn.ynteractive.com/content/prompts/interview-debrief-agenda-prompt): Plan a short interview debrief that goes must-have by must-have, keeps the talk on job evidence and ends with a decision, owners… - [Interview scorecard prompt](https://learn.ynteractive.com/content/prompts/interview-scorecard-prompt): Turn interview notes or a debrief transcript into a scorecard: each must-have rated with a quote as evidence, gaps marked Not… [All free prompt templates](https://learn.ynteractive.com/content/prompts) ## Visual guides The same ideas as quick visual guides: swipe through the slides, or read each one as text. - [Summarize a meeting transcript with ChatGPT](https://learn.ynteractive.com/content/visual/meeting-recap-steps): A meeting transcript is useful for about five minutes, and then nobody reads it again. - [Turn an interview debrief into a fair scorecard](https://learn.ynteractive.com/content/visual/recruiting-not-discussed): Interview write-ups drift into general impressions, and a must-have nobody asked about quietly becomes an assumption. - [Meeting notes myth: “summarize this” is all ChatGPT needs](https://learn.ynteractive.com/content/visual/summarize-this-myth): Myth: paste a transcript, type “summarize this”, done. Fact: ask for the decisions, an action items table with owners and dates, and open questions. [All visual guides](https://learn.ynteractive.com/content/visual) ## Keep reading - [Interview Debrief: Best Practices and a Free Template](https://learn.ynteractive.com/content/blog/interview-debrief-template): Interview debrief best practices: a copy-ready template, agenda and debrief questions, how to keep it fair, and a ChatGPT prompt for the scorecard. - [ChatGPT for Recruiters: Interview Debrief to Scorecard](https://learn.ynteractive.com/content/blog/chatgpt-for-recruiters): ChatGPT for recruiters: turn an interview debrief transcript into a fair scorecard against the must-haves, dated next steps and a candidate email. - [How to Ask ChatGPT for a Table (Prompts That Work)](https://learn.ynteractive.com/content/blog/ask-chatgpt-for-a-table): Ask ChatGPT for a table by naming the columns and saying what goes in an empty cell. Three work prompts: action items, a promise check and a scorecard. [All blog posts](https://learn.ynteractive.com/content/blog) · [All free tutorials](https://learn.ynteractive.com/content)