Score work against a rubric, for HR and people teams

Score a piece of work against a written rubric, one criterion at a time, quote the evidence for each mark, and say what would reach the top level, using only the rubric you give.

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 rubric, The work to mark

Use This TemplatePrepare a prompt for your own AI chat.

Who it is for: Recruiters, hiring managers and HR partners who mark answers, work samples and applications against a rubric before a panel decides. Some states and cities have rules for using AI tools to assess candidates. Check with your HR or legal team first, and keep every hiring decision with the panel.
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.
Checklist
Follow the steps and check off the checks by hand.
Claude skill
A folder Claude loads, so it follows the steps by itself.
n8n file
Import into n8n and connect your own AI account.

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 n8n How to install a Claude skill

The same job, with and without the template

Sample

This comparison uses the Typical sample. Try an input below for a result guide matched to each sample.

One plain prompt

Score this interview answer against my rubric, one criterion at a time, using the marks in the rubric, and say what would improve it. (The same rubric and answer are pasted below.)

Overall this is a strong answer that meets most of the rubric.

Specific situation: met. It describes an angry customer and a refund past the 30-day window.
Own actions: met. The candidate read the history, called the customer and offered a voucher.
Result: met. The customer calmed down and stayed, which is a clear result.
Learning: partly met. Being good at staying calm shows self-awareness.
Stays within policy: met. Offering a voucher instead of a refund is a sensible way to respect the policy.

To improve, consider adding more detail about what the candidate would do next time.

Problem:It marks the result met with no number or before and after, counts 'good at staying calm' as learning, and says the policy was kept though the answer never says what the candidate did about it.

With this template

Result: 5 criteria marked: 2 met, 2 partly met, 1 not met.

To improve

Swipe sideways to see all columns

#	Criterion (quote)	Mark	Evidence	To reach met
3	"Result"	partly met	"The customer calmed down and stayed with us"	State the outcome with a number or a clear before and after.
4	"Learning"	not met	No passage in the work	Name one thing the candidate does differently now.
5	"Stays within policy"	partly met	"we could not refund an order past the 30-day window ... offered a replacement voucher for the same amount"	Say how the candidate kept to the refund policy or got approval to step outside it.

Met

"Specific situation"
"Own actions"

Check:Every description of met is quoted word for word from the rubric: Five criteria with their descriptions of met.
Check:Every passage is quoted word for word from the work: Five rows: four supporting passages and None found for learning.
Check:Each mark is one of the three allowed words: Five marks, each one of the three allowed words: 2 met, 2 partly met, 1 not met.
Check:Every row to improve is filled in: Three rows under To improve, each with all five cells filled.
Check:Every criterion in the report is in the rubric word for word: The three criteria used in the final table match the rubric.
Check:The counts add up to the marks: The Result line says 5 criteria: 2 met, 2 partly met and 1 not met; the table has three rows, one for each criterion not marked met.
Check:Each mark and each fix follows the rubric's own words: Each mark matches the rubric's wording for its level, and each To reach met uses only the rubric's words and facts already in the answer (30-day window).
For your read:You decide whether you agree with each mark: Do you agree the answer states no outcome number? These marks are a first read; the hiring decision stays with the panel.

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

Typical: Interview answer against a five-criterion rubricEasy: Reference request email against a two-line rubricTricky: Polished interview answer with gaps and a family remark

A short email that meets both criteria, so there is nothing to improve.

The rubric (needed)The work to mark (needed)

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 reader who turns a rubric into items that can be marked one by one.
The work is a candidate's interview answer, work sample or application, marked against a written interview rubric, and the hiring decision stays with the panel.

Your task is to list every criterion in the rubric and what it says met looks like.

The rubric:
Rubric for a reference request email. Each criterion is marked met, partly met or not met.
1. Names the role. Met: the email names the job title the candidate applied for. Partly met: it refers only to a position or a job. Not met: it names no role.
2. Gives a reply date. Met: the email gives a date to reply by. Partly met: it asks for a prompt reply with no date. Not met: it asks for no reply.

Rules:
- One row for each criterion, in the order the rubric gives them. Do not merge two criteria and do not add one the rubric does not have.
- Quote the criterion's name from the rubric word for word. In the last column, quote the rubric's own words for what met looks like, as short as you can while keeping its numbers and conditions. Do not reword either one.
- Use only the rubric. Do not add your own idea of what good work looks like.
- Do not read the work yet.

Return one markdown table and nothing else:
| # | Criterion (quote) | Met looks like (quote) |

Send to AICopy and open ChatGPTCopies this result and opens a blank chat. Paste and review it there.

Before Step 2, check: Every description of met is quoted word for word from the rubric.

What This Sample Should Produce

Both rows should be met: the email names the payroll analyst role and asks for a reply by Friday, October 23. No improvement needs to be invented merely to fill the table.

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.

The steps, and the check on each

Step 1: List each criterion and what met looks like
Split the rubric into separate criteria, quoted word for word, with the rubric's own words for the top level.
Hands back: A numbered table of the criteria, each with the rubric's own words for met.
Check:Every description of met is quoted word for word from the rubric
A plain rule. If it fails, run the step again (the n8n file does this for you).
Step 2: Find the passage for each criterion
For each criterion, quote the words in the work that bear on it, or say that none do.
Hands back: A table that puts a quoted passage from the work beside each criterion, or None found.
Check:Every passage is quoted word for word from the work
A plain rule. If it fails, run the step again (the n8n file does this for you).
Step 3: Mark each criterion
Compare each passage with the rubric's wording and give one of three marks, with the reason in one sentence.
Hands back: A table that gives each criterion one of three marks and the reason.
Check:Each mark is one of the three allowed words
A plain rule. If it fails, run the step again (the n8n file does this for you).
Step 4: Write the marking report
Turn the marks into a count, a list of what to improve with wording taken from the rubric, and a list of what is met.
Hands back: A report with a count line, a table of what to improve and a list of the criteria that are met.
Check:Every row to improve is filled in
A plain rule. If it fails, run the step again (the n8n file does this for you).

After the last step

Check:Every criterion in the report is in the rubric word for word
A plain rule. If it fails, run the step again (the n8n file does this for you).
Check:The counts add up to the marks
A second look by the AI. If it fails, run the step again (the n8n file does this for you).
Check:Each mark and each fix follows the rubric's own words
A second look by the AI. If it fails, run the step again (the n8n file does this for you).
Check:You decide whether you agree with each mark
You check this one. If it fails, it is flagged for you.

What you need first

The rubric(needed)
Paste the rubric as written, with what each level looks like for each criterion. The marks used here are met, partly met and not met.
The work to mark(needed)
Paste the full text of the work as it stands. Remove the person's name and any personal details the marking does not need first.

Ways to adapt it

This template marks by the rubric's own words and nothing else, so a vague rubric gives vague marks. If a criterion says only "good" or "clear", add what each level looks like before you run it.
If your rubric uses other level names, such as strong, adequate and weak, change the three words in the marks step and in its check, both.
If your rubric gives points, keep them out of the AI's job. Let it mark in words, then add the points yourself from the marks.
To check a list of must-haves rather than quality at several levels, use Check every requirement is covered instead.
For a long piece of work, run it on one section at a time, with only the criteria that apply to that section.

Change this version in the Editor. Its added context stays in every prompt and the general template stays separate.

Notes for HR and people teams

Mark the answer, not the person. Use the candidate code or name the input gives and add nothing about the candidate.
Marks stay met, partly met and not met. They are a first read for the panel, not a hiring decision.
A remark about family, age, health, background or accent is not evidence for any criterion. Give it no credit and no penalty, do not quote or repeat it in the marks or the report, and tell your HR contact it came up.
Polish, confidence and length earn no credit. Only the rubric's own wording does.
Some states and cities have rules for using AI tools to assess candidates, such as telling candidates or auditing the tool for bias. Check with your HR or legal team before you mark candidates this way.

The scoring guide

Sample

Each template check has a criterion marked met or not met; a person must still make the handed checks. (The guides in Quality rate a whole piece of work on three levels.) Under each one is how the example run scored.

Download the scoring guide (Markdown)

Every description of met is quoted word for word from the rubric
A plain rule
Meets:Every description of met in the table is found word for word in the rubric.
Does not meet:A description has been reworded or improved, or is not in the rubric word for word.
Example built from the before and after:Met
Every passage is quoted word for word from the work
A plain rule
Meets:Every passage is found word for word in the work (a quote joined with ... is checked piece by piece), or the row says None found.
Does not meet:A passage has been reworded, or is not found word for word in the work.
Example built from the before and after:Met
Each mark is one of the three allowed words
A plain rule
Meets:Every criterion has exactly one of met, partly met or not met.
Does not meet:A row has another word, such as mostly met or good.
Example built from the before and after:Met
Every row to improve is filled in
A plain rule
Meets:Every row under To improve has the criterion, the mark, the evidence and what would reach met filled in.
Does not meet:A row under To improve has a blank or a dash in one of its cells.
Example built from the before and after:Met
Every criterion in the report is in the rubric word for word
A plain rule
Meets:Every criterion quoted in the report is found word for word in the rubric.
Does not meet:A quoted criterion has been reworded or is not in the rubric.
Example built from the before and after:Met
The counts add up to the marks
A second look by the AI
Meets:The numbers on the Result line match the marks, and the table has one row for each criterion not marked met.
Does not meet:A count on the Result line is wrong, or a criterion not marked met has no row, or a met criterion has one.
Example built from the before and after:Met
Each mark and each fix follows the rubric's own words
A second look by the AI
Meets:Each mark matches the rubric's wording for that level, and each fix uses only the rubric's wording and facts already in the work.
Does not meet:A mark gives credit the rubric does not allow, or a fix suggests content that is in neither the rubric nor the work.
Example built from the before and after:Met
You decide whether you agree with each mark
You check this one
Meets:You read the evidence beside each mark, decided whether you agree, and treated the marks as a first read.
Does not meet:The marks are used as a final grade without being read against the work.
Example built from the before and after:For your read

Example built from the before and after: met 7 of 7, plus 1 for your read

Learn from this template

A scoring guide takes one criterion at a time, so each mark rests on a passage quoted from the work and on the rubric's own words. Marks come from a short closed list, and the last check is yours: you decide whether you agree with each one.

Where to see it: step 1 (List each criterion and what met looks like); step 2 (Find the passage for each criterion); step 3 (Mark each criterion).

Read the guide: Checks Take the lesson: Checks (lesson 4)

More to read:Adapting a template

Practice:Scoring guides Kinds of checks

The same job as a tool:Check and scoring guide builder

Which one fits?

Use Review a draft before you send it when there is no rubric and you want a general second read, with the fixes ranked.
Use Check every requirement is covered when you have a list of must-haves and want to know which ones a draft leaves out.

Related templates

All for HR and people

Review

Fact-check against sources15 min
Every claim gets a verdict and a quote from your sources

Review

Remove personal information10 min
No listed detail is left in; nothing else was changed

Review

Reconcile feedback from three readers20 min
Each actual reader comment gets an answer; conflicts stay visible

Last run: October 17, 2026: Example built from the before and after (sample run)
Tools and versions: Example built from the before and after
What was checked: The files, against each tool’s import format, and 1 sample run, each check’s finding recorded.
Version: 1.0
What changed: First release.

Report a problem with this template How we test

Score work against a rubric, for HR and people teams

How it runs

The same job, with and without the template

One plain prompt

With this template

To improve

Met

Runs and scores

Example built from the before and after

Use This Template

Step 1 Chat Prompt

The steps, and the check on each

Step 1: List each criterion and what met looks like

Step 2: Find the passage for each criterion

Step 3: Mark each criterion

Step 4: Write the marking report

After the last step

What you need first

Ways to adapt it

Notes for HR and people teams

The scoring guide

Learn from this template

Which one fits?

Related templates

Review

Review

Review