A Working Index

Possible
Futures.

Score postings against your compass. Discover companies. Teach the AI to know you. Own every word.

github.com/kandizzy/possible-futures →

Next.js · SQLite · Claude API · Local-first

Overview

What It Does

  • Write your career story through a guided five-chapter intake
  • Score job postings against a 6-dimension rubric grounded in your history
  • Discover companies that match your signal words and values
  • Generate application materials that follow your writing rules
  • Export ATS-friendly PDFs ready to submit
  • Track everything in one place: roles, applications, companies, contacts

Quick Start

Five commands.

mkdir career && cd career
git clone https://github.com/kandizzy/possible-futures.git
cd possible-futures && npm install
echo "ANTHROPIC_API_KEY=your-key-here" > .env.local
npm run dev

Open http://localhost:3000 and the intake begins.

Clone into a parent folder (career/, resume/, etc.) — the app writes your generated files there. New to the terminal, Node, or nvm? That's fine. The README walks through installing each piece step by step, and getting your Anthropic API key.

The ritual.

30 minutes, your last few roles in front of you, and the promise that you're writing this yourself.

The ritual gate

I

The setup.

Name, education, and the through-line that connects your work.

Chapter 1 filled in

II

The throughline.

Two or more roles. Title, company, dates, summary, proudest moment. Messy notes welcome.

Three roles entered

III

What you're looking for.

Dream role, role tiers, target companies, signal words, compensation floor.

Signal words and targets

IV

The playbook.

Red flags, banned words, voice calibration. Click phrases that sound like you, or paste your own.

Playbook started

V

The shelf of proof.

Projects, recognition, and resume versions. Add or remove versions as needed.

Three projects

V

Resume versions.

Different roles call for different resumes. Name them, describe their emphasis.

Resume versions

Press the plates.

Preview your Book, Compass, and Playbook in rendered markdown or source view.

Publish preview

The compass.

Your scoring rubric. Signal words, red flags, role tiers. Every posting is evaluated against this.

Compass preview

It's ready.

Three markdown files saved. The app is primed.

Published

An index of possible futures.

Every role scored against your compass, with status tracking across your pipeline.

Dashboard

The scoring breakdown.

Six dimensions, fit summary, signal words, gap analysis. Calibrate scores you disagree with.

Role detail

Gaps & studies.

When the posting asks for something your Book doesn't evidence, the app doesn't stop at "not a match." It turns a rejection risk into a weekend plan.

  • What's missing — the specific gap between your background and the posting.
  • Why it matters here — framed against this role, not gaps in the abstract.
  • Work already on hand — projects from your Book that partially address it, so you know what to surface.
  • Possible studies — two or three concrete, buildable projects. Not "learn Rust," but "Build a CLI that does X."

Strong fits return nothing. That silence is the confirmation — you already have the skills this role needs.

Score a posting.

Paste a job posting or fetch by URL. Scored in 15-30 seconds.

Evaluate a role

Find the next houses.

Claude suggests companies. Each is verified live against its ATS. Track or skip.

Discover companies

The houses.

Pipeline view per company. Active roles sorted by urgency, watchlist by category.

Companies page

The ledger.

Every API call, its cost, and what it was for. Export to CSV.

Work in progress. Cost estimates are computed from token counts — they haven't been reconciled against actual Anthropic billing yet. Treat as directional.

Ledger

Three documents, one source.

The Book — career history, projects, skills, writing rules, sensitive context.

The Compass — scoring rubric. Signal words, red flags, role tiers, compensation floor.

The Playbook — resume rules, cover letter rules, banned words, version strategies.

All three are plain markdown. Edit them in any text editor to customize how Claude scores and writes for you.

Change a rule, and the next score reflects it. No retraining, no waiting.

Use Revise in the sidebar to regenerate from the intake, or edit the files by hand for full control.

Settings.

Choose your AI model, tune signal words, reload source files, and access Revise.

Settings

ATS-friendly PDFs.

Generate cover letters and resume summaries, then download as clean PDFs. Arial font, single column, no graphics. Exactly what ATS scanners want.

Available on the materials page after generating content for a role.

Possible Futures

Your compass.
Your words.

Local-first. Your data stays on your machine. Runs on the Anthropic API or Claude Code.

github.com/kandizzy/possible-futures