Skip to content
📑

Hiring Interview Notes

A shape for hiring loops that survive past the offer. Roles, candidates, rubric scores, decisions. Claude and ChatGPT compare candidates against your real rubric, not vibes.

Requires an AI connected to your Hjarni account via MCP.

https://hjarni.com/templates/hiring-interview-notes

Copy this URL and paste it into Claude or ChatGPT to install the template.

How to use

  1. 1 Share this page. Paste this URL into Claude or ChatGPT. Your AI reads the template definition and installs it.
  2. 2 Folders, tags, and instructions appear. Your AI creates the full structure in your Hjarni account, ready to use.
  3. 3 Start adding notes. The AI instructions guide your AI on where to put things and how to organize them.

Hiring loops that survive past the offer. Claude and ChatGPT compare candidates against your real rubric, not vibes.

Most hiring decisions live in a Notion page, a Slack thread, and the panel's heads. Six months later, no one remembers why the runner-up was strong, or whether to call them for the next role. This template gives the loop a structure that compounds.

Rubric first, scores second

The Rubric folder defines what each level means in plain language before any candidate is scored. When Claude or ChatGPT compares two finalists, it points to the level definition that justifies each score. The conversation stops being "I had a good feeling" and starts being "this candidate scored High on Systems thinking because…".

References that earn a second look

The runners-up are the under-tapped resource of every hiring loop. The References folder is for the people who did not get this role but should hear about the next one. When you open a new req, ask Claude to scan References for fits. The next loop starts halfway done.

A workflow that earns the template's keep

  1. Before opening a role, write the Role note and the matching Rubric.
  2. After every interview round, drop the panel notes into the Candidate note.
  3. At decision time, ask Claude or ChatGPT to compare finalists against the rubric.
  4. After the offer is signed, write a Decision note and add strong runners-up to References.

A real example

You are closing a senior backend role. Two finalists. You ask Claude, "Score Alex and Priya against our Senior Backend Engineer rubric." Claude reads the rubric, the candidate notes, and returns a side-by-side: Systems thinking, Code quality, Communication, Ownership. The panel disagreement clears in five minutes instead of an hour.

Common questions

Common questions

Is this an ATS replacement?

No. It does not handle email, scheduling, or pipeline tracking. Use your existing ATS for those. Hjarni holds the notes that survive the ATS.

Is it safe to keep candidate notes here?

These are your private notes. Be discreet, store only what was shared during the process, and follow your local hiring and data laws. Talk to legal if you are unsure.

Will the AI rewrite candidate notes?

Folder instructions tell each AI to keep the user's wording and only quote from existing notes. The AI does not paraphrase panel feedback.

Can my team share this?

Yes. Install in a team space so every panelist's Claude or ChatGPT reads from the same rubric and candidate notes.

Related pages

Structure

Tags

role candidate rubric decision reference

Folders

Hiring Interview Notes
The memory of every hiring loop. Candidates, rubric, decisions, references.
Has AI instructions
5 starter notes
Roles
One note per open or closed role. Job description, must-haves, nice-to-haves.
Has AI instructions
Candidates
One note per candidate. Background, panel notes, rubric scores.
Has AI instructions
Rubric
Scoring criteria per role. Definitions of what each level means.
Has AI instructions
Decisions
Hiring outcomes per role. Why the chosen candidate beat the runners-up.
Has AI instructions
References
Candidates worth re-engaging on a future role.
Has AI instructions

For your AI

Share this page with your AI. It reads the definition below, creates the folders, instructions, tags, and starter notes in your account.

Show template definition

Install steps for AI agents:

  1. Check existing tags with tags-list. Only create missing ones with tags-create.
  2. Create containers top-down using containers-create, noting the returned IDs. Use parent_id to build the hierarchy.
  3. For each container with llm_instructions, call instructions-update with level: "container" and the container's ID.
  4. Create any seed notes using notes-create, placing them in the correct container by ID. Use container_path to resolve which container.
  5. Discuss any customizations with the user before or after installing.
---
name: Hiring Interview Notes
description: 'A shape for hiring loops that survive past the offer. Roles, candidates,
  rubric scores, decisions. Claude and ChatGPT compare candidates against your real
  rubric, not vibes.

  '
tags:
- role
- candidate
- rubric
- decision
- reference
containers:
- name: Hiring Interview Notes
  description: The memory of every hiring loop. Candidates, rubric, decisions, references.
  llm_instructions: |
    This is a hiring repository. The goal is to make hiring decisions traceable to real evidence and to keep loops consistent across roles.
    - When asked to compare candidates, read the Rubric for the relevant role first, then the Candidate notes. Score against the rubric explicitly.
    - Never invent quotes, references, or score justifications. If the Candidate note does not contain the detail, say so plainly.
    - Be discreet. Never include personal information outside what was shared during the interview process.
    - When the user closes a role, suggest writing a Decision note that captures who was hired, why, and what the runners-up did better.
    - This is a notes system, not an ATS. Do not pretend to send emails, schedule, or track applicants externally.
  children:
  - name: Roles
    description: One note per open or closed role. Job description, must-haves, nice-to-haves.
    llm_instructions: |
      Use this folder for the role itself.
      - One note per role. Title format: "<Role> <Year>".
      - Include: Reason for hiring, Must-haves, Nice-to-haves, Comp band, Hiring panel.
      - When a role closes, link the matching Decision note.
      - Tag every note with "role".
  - name: Candidates
    description: One note per candidate. Background, panel notes, rubric scores.
    llm_instructions: |
      Use this folder for candidate notes.
      - One note per candidate, scoped to one role. Title format: "<First Last> for <Role>".
      - Use the shipped skeleton: Background, Panel notes per round, Rubric scores, Strengths, Concerns, Reference check, Outcome.
      - Always cite the round and interviewer when quoting from panel notes.
      - When the candidate is referenceable, suggest creating a note in References for future re-engagement.
      - Tag every note with "candidate".
  - name: Rubric
    description: Scoring criteria per role. Definitions of what each level means.
    llm_instructions: |
      Use this folder for the standard a candidate is measured against.
      - One rubric per role. Title format: "Rubric: <Role>".
      - For each criterion, define what a low, medium, and high score looks like in plain language.
      - Treat the rubric as binding. When scoring a candidate, point to the level definition that justifies the score.
      - Tag every note with "rubric".
  - name: Decisions
    description: Hiring outcomes per role. Why the chosen candidate beat the runners-up.
    llm_instructions: |
      Use this folder for closing-the-loop notes.
      - One note per closed role. Title format: "Decision: <Role> <Year>".
      - Include: Who was hired, Why, Runners-up and their strengths, What the loop got right, What to change next time.
      - Cross-link to the Role note and to the Candidate notes for all finalists.
      - Tag every note with "decision".
  - name: References
    description: Candidates worth re-engaging on a future role.
    llm_instructions: |
      Use this folder for strong candidates who did not get the role.
      - One note per person. Include: When you met, Which role, Why they were strong, What kind of future role would fit, How they prefer to be re-engaged.
      - Be honest and discreet. Frame strengths and fit, not weaknesses.
      - Tag every note with "reference".
  notes:
  - title: Senior Backend Engineer 2026
    body: |
      A starter role note. Replace with a real role.

      ## Reason for hiring
      Our existing backend engineer is bottlenecked on infrastructure work. We want one senior hire to own the API and queue layer.

      ## Must-haves
      - 5+ years building production backend services.
      - Comfortable owning a system end to end, including on-call.
      - Strong written communication.

      ## Nice-to-haves
      - Experience with Ruby on Rails.
      - Familiarity with SQLite at scale.

      ## Comp band
      Replace with your real range.

      ## Hiring panel
      Founder, existing backend engineer, generalist.

      This is a starter note. Replace it with a real role.
    tags:
    - role
    container_path: Hiring Interview Notes > Roles
  - title: 'Rubric: Senior Backend Engineer'
    body: |
      A starter rubric. Replace with your real scoring criteria.

      ## Systems thinking
      - Low: solves the local problem, does not ask how it interacts.
      - Medium: identifies upstream and downstream effects when prompted.
      - High: proactively maps blast radius before writing code.

      ## Code quality
      - Low: works but is hard to follow.
      - Medium: clear, idiomatic, lightly commented.
      - High: clear, idiomatic, plus tests that pin down the contract.

      ## Communication
      - Low: gives short answers that hide the reasoning.
      - Medium: explains decisions clearly when asked.
      - High: writes the decision down without being asked.

      ## Ownership
      - Low: hands work off at PR submit.
      - Medium: follows up after merge.
      - High: monitors the production impact and writes the postmortem if it breaks.

      This is a starter note. Replace it with your real rubric.
    tags:
    - rubric
    container_path: Hiring Interview Notes > Rubric
  - title: Alex Martinez for Senior Backend Engineer
    body: |
      A starter candidate note. Replace with a real candidate.

      ## Background
      Eight years at two mid-stage SaaS companies. Last two years owning the billing service end to end.

      ## Panel notes
      ### Phone screen (Founder)
      Strong written portfolio. Clear about why they want to leave their current role.

      ### Technical (Backend engineer)
      Walked through the design exercise without prompting. Asked about our queue choice unprompted.

      ### Communication (Generalist)
      Clear, concise, asked what success looks like in the first 90 days.

      ## Rubric scores
      - Systems thinking: High.
      - Code quality: Medium.
      - Communication: High.
      - Ownership: High.

      ## Strengths
      Asks about blast radius before writing code. Strong written.

      ## Concerns
      Code in the exercise had minor style drift. Easy to coach.

      ## Reference check
      Past manager confirmed billing service ownership and postmortem authorship.

      ## Outcome
      Replace with the real outcome.

      This is a starter note. Replace it with a real candidate.
    tags:
    - candidate
    container_path: Hiring Interview Notes > Candidates
  - title: 'Decision: Senior Backend Engineer 2026'
    body: |
      A starter decision note. Replace with a real one.

      ## Who was hired
      Replace with the real name.

      ## Why
      Highest combined score on Systems thinking and Ownership. Reference check confirmed both.

      ## Runners-up
      - Strong communicator with weaker systems thinking. Better fit for a future product engineer role.

      ## What the loop got right
      Rubric-first scoring made the final comparison clear.

      ## What to change next time
      Move the design exercise earlier. Two candidates dropped after they realized the scope.

      See [[Senior Backend Engineer 2026]].

      This is a starter note. Replace it with a real decision.
    tags:
    - decision
    container_path: Hiring Interview Notes > Decisions
  - title: 'Reference: Priya Shah'
    body: |
      A starter reference note. Replace with a real strong candidate.

      ## When we met
      Final round for Senior Backend Engineer 2026.

      ## Why she was strong
      Top of the panel on Communication. Wrote the cleanest design doc we have ever seen from a candidate.

      ## What kind of future role would fit
      A platform or developer experience role where the writing matters as much as the code.

      ## How she prefers to be re-engaged
      Email, with a clear role description attached, not a recruiter pitch.

      This is a starter note. Replace it with a real reference-worthy person.
    tags:
    - reference
    container_path: Hiring Interview Notes > References

Write once. You both remember.

Free to start. No credit card required.

Give your AI a memory

Works with Claude and ChatGPT today. Gemini coming soon.