TemplatesFor HR and people teams

Find themes in comments or interview notes, for HR and people teams

Read a set of comments, survey answers or interview notes, label each one, group the labels into themes, then count each theme and back it with two real quotes.

This is the version for HR and people teams. The steps and checks are the same as in the general template; each prompt carries one added line about your setting, and the examples are from your kind of work.

Sample results: runs and scores on this page are illustrations while testing is set up. How we test

Bring: The comments, What you want to learn

Use This TemplatePrepare a prompt for your own AI chat.
  • Who it is for: HR business partners, people analysts and talent teams who report what employees, leavers or new hires said in exit interviews, engagement surveys and onboarding feedback.
  • Time: 15 minutes
Edit this version
Other Formats and Files

The Step 1 chat prompt under Use This Template is the quick start. Choose a full prompt chain, checklist, Claude skill or n8n file when that destination fits your work. Checked Instructions, below, run the whole job with a hard check after every step.

Choose one format

  • Prompt chain

    Copy each step into ChatGPT or Claude, one after another.

This job also comes as Checked Instructions: the whole job in one set, with a hard check after every step. See the Checked Instructions on the general template.

Using a download:How to use this in n8nHow to install a Claude skill

Use This Template

Add your material below. Logic Lab prepares Step 1; you copy it into your own AI and check the answer there. The site does not run the workflow.

Example materialSample
Choose a sample
Choose a sample input

Ten short comments that fall into two clear themes (late setup information and a helpful buddy) plus one comment about length.

Step 1 Chat Prompt

Review the exact prompt, then paste it into your own AI. For later steps, use the chat chain in Other Formats and Files.

You are a careful analyst who reads feedback one comment at a time.
The comments come from employees, leavers or new hires, such as exit interview notes or engagement survey answers, and the findings will go to HR leaders or managers.

Your task is to give every comment below a short label of two to four words that says what it is mainly about.

What we want to learn: What did new hires think of their first week?

The comments, one per line:
I did not know where to report on my first morning.
My buddy answered every question I had.
The first-day schedule only arrived the night before.
Having a buddy made me feel welcome.
My laptop arrived two days after I started.
My buddy showed me where everything is.
I would not have found the right people without my buddy.
I was not told my login details until the afternoon.
My buddy checked in with me every day that week.
The welcome presentation could have been shorter.

Rules:
- Go through every comment, in order. Do not skip or merge comments.
- If a comment is about two things, give the label for the main one, then add a second label after a slash.
- Base each label only on what the comment says. Do not guess what the person meant.
- Do not group or count yet.

Return one markdown table with one row for every comment, and nothing else:
| # | Comment (quote) | Label |
Copy each comment word for word into the quote column. You may shorten a long comment with "..." but do not change any words.
Copy and open ChatGPTCopies this result and opens a blank chat. Paste and review it there.

Before Step 2, check: Every quote is really in the comments.

What This Sample Should Produce

A helpful buddy repeats across five comments and late setup information across four. The shorter-presentation request is a smaller separate point; do not turn all ten into complaints.

A result guide for this invented input, not an AI reply.

Want to see where the materials, steps and checks fit? Watch the general template being built.