Documentation

Quick start

Build your profile once, then run your first daily pipeline.

1. Build your profile

careeros start is a guided onboarding that produces your profile.yaml — your facts, targets, and constraints. It opens by asking for your CV (optional; type skip to answer questions instead).

onboard

$ careeros start

Your profile is a source of truth. Every resume bullet CareerOS ever selects is a verbatim copy of something written here, so it's worth getting right. You generate it once and edit it rarely.

2. Add your discovery credentials

Real credentials live in .careeros/secrets.env, which is gitignored. Config files hold the name of an environment variable, never the key itself.

.careeros/secrets.env

FANTASTIC_API_KEY=your-developer-fantastic-jobs-key

The two free providers need nothing. If you skip the plan setting, CareerOS assumes the free tier (500 records per week) rather than over-fetching.

3. Run the daily pipeline

run

$ careeros daily

This runs the full pipeline: discover, normalize, dedupe, constraints, gate, evaluate, threshold, artifacts, application answers, and finally the report and Sheet. Deterministic stages cost nothing; the two reasoning stages spend tokens only on jobs that earned them.

careeros daily — real terminal output

Doctor checks pass, then discovery runs against live providers — this is unedited output from an actual run, not a mockup.

4. Open your Sheet

Apply-tier jobs (score of 4.0 or higher) get a full row with a tailored resume, cover letter, and drafted application answers. Consider-tier jobs (3.5 to 4.0) get a row with the score and a one-line reason. You read the Sheet, top down, and apply to what's worth it.

Going deeper on one job

These run on demand, never as part of the daily loop:

per-job

$ careeros prep <job-id>    # a deep interview-prep report
$ careeros apply <job-id>   # draft answers for one job's form