Product Career Ops

Run your career like your best product.

A free, open-source toolkit for product leaders. It turns your career history into a private evidence bank, then works with an AI assistant to score roles, draft grounded application materials, and coach your growth.

Write the truth about your career once. Every application after that starts from strength.

Runs on your computer Five plain files you can open and edit Nothing uploaded by this project Open source, MIT

01 · Score first

Know if a role deserves you before you apply

Paste a job link, a description, or even a screenshot. The system grades the role against your real profile and tells you whether it is worth your energy.

  • Scores mandate quality, domain fit, level, and risks
  • Checks which requirements your evidence already proves
  • Roles scoring 80 or above become Active
  • Weak fits are archived with the reason written down
From a real private run

One pasted link became a scored, active opportunity the same morning. Fifteen years of healthcare product work lined up with the mandate.

02 · Packets, not cover letters

Materials grounded in what you actually did

For high-conviction roles, one command assembles everything at once. Nothing is invented. Every claim maps back to your evidence bank.

  • Tailored resume direction and application answer themes
  • Company brief and interview prep
  • A warm outreach draft ready to edit
  • An evidence map showing which proof backs which claim
From a real private run

The packet pulled three themes out of the evidence bank. They became the application answer, grounded in things that actually happened rather than generated filler.

03 · One ledger

Your whole search in one private place

Every opportunity, score, decision, and outcome lives in a spreadsheet the system maintains for you. Dated, auditable, and yours.

  • Every active, applied, and archived role at a glance
  • Archive reasons stop you rediscovering weak fits
  • Outcomes feed straight back into your positioning
From a real private run

The submitted application was logged with a follow-up date one week out, and interview prep was already built.

04 · Grow on purpose

A coaching loop between the searches

The same evidence bank powers weekly reviews, quarterly planning, and skill-gap analysis. Market feedback becomes your next deliberate bet instead of a vague anxiety.

  • /pco develop weekly captures fresh wins while they are vivid
  • /pco develop quarterly updates your thesis and target list
  • Repeated gaps become development bets
  • Stories that land in interviews get promoted into your resume

The workflow

One role, start to finish

Six steps from a job posting to a logged outcome. Each one is a short conversation with your AI assistant.

1

Capture

Hand the assistant a link, a pasted description, or a screenshot. /pco search

2

Score

The role is graded against your profile and evidence. 80 or above goes Active.

3

Decide

Read the scorecard like a decision memo: pursue, warm intro, or pass.

4

Build the packet

Materials, prep, and outreach for roles that clear the bar. /pco search packet

5

Apply yourself

The system never submits anything for you. You edit, choose, and send.

6

Record

Outcomes go back into the ledger as market feedback for the next round.

From a real private run That whole arc ran in a single day: pasted link in the morning, packet by afternoon, application submitted and logged with a follow-up date by evening.

Your data

Five files carry your whole career

Everything the system knows about you lives in plain files you can open, read, and edit. No database, no account, nothing uploaded to anyone's server by this project.

profile.yml

Who you are and what you want

Target roles, constraints, differentiators, and your career thesis.

resume.md

Your master resume

Written once, broadly. Tailored versions are derived, never invented.

evidence.yml

Proof of what you did

Achievements, hard decisions, tradeoffs, and metrics.

sources.yml

Where you look

Companies, job boards, newsletters, and communities to scan.

product-career-ops.xlsx

The ledger

Every opportunity, scorecard, decision, and review, dated and auditable.

private/

Where they all live

One folder on your computer, backed by a private repository only you can see.

Privacy by architecture

Two homes, never mixed

Tools are public so anyone can use and improve them. Your career data lives somewhere only you can reach. The split makes mixing them structurally impossible, not a matter of being careful.

Public · the engine

Shared with everyone

  • The workflows, scripts, and documentation
  • A curated product management resource library
  • A fictional demo persona with invented employers and numbers
  • A privacy exporter that refuses to publish real identifiers
Private · your data

Yours alone

  • Your profile, resume, evidence, and sources
  • Your workbook of opportunities and decisions
  • Copies of every application you actually submitted
  • Stored on your computer, in a repository only you can access

Getting started

Set up in an afternoon

Three things to have ready, five steps to run. Read the blue box before touching the Terminal.

The honest shortcut

You do not have to learn these commands. Open your AI assistant, point it at this project, and say: "Set up Product Career Ops for me, then help me replace the demo data with my real resume." The assistant runs every step below on your behalf and asks when it needs something from you.

1

Get the engine

This downloads the public toolkit to your computer.

Terminal
git clone https://github.com/vmittal2690/product-career-ops.git
cd product-career-ops
2

Install it

Terminal
python3 -m venv .venv
source .venv/bin/activate
pip install -e ".[dev]"
3

Meet Jordan Lee, the demo persona

Run the workflow on fictional data first, so you know what good output looks like.

Terminal
pco demo-init
pco opportunity add --input demo/opportunities/northstar-health.json
pco opportunity list
4

Make it yours

Create a private GitHub repository for your data, connect it as the private/ folder, and replace the demo files with your real ones.

Terminal
git clone https://github.com/<you>/product-career-ops-data.git private
pco reset --confirm RESET
pco doctor  # checks everything is wired up
5

Run your first real search

Pick one role that genuinely excites you. The goal is not a perfect application; it is an honest read on whether your evidence is strong enough.

Your AI assistant
/pco search <job link or pasted description>

The operating rhythm

A week while actively searching

The system compounds through a light weekly routine, not marathon sessions.

Monday

Refresh sources and review new roles that scored well. /pco search scan

Tue / Wed

Build packets for the top one or two roles only. Depth beats volume.

Thursday

Send the applications and warm outreach you prepared, in your own voice.

Friday

Record outcomes and capture fresh evidence while it is vivid. /pco develop weekly

Once a quarter, /pco develop quarterly steps back further: which mandates keep fitting, which gaps keep repeating, and what the next deliberate bet should be. That is when the job search stops being a scramble and becomes a strategy.