Documentation Index
Fetch the complete documentation index at: https://mintlify.com/MadsLorentzen/ai-job-search/llms.txt
Use this file to discover all available pages before exploring further.
The /outcome command is the framework’s record-keeping layer for what happens after you submit an application. It writes to two places: the job_search_tracker.csv status column — which /scrape and /rank use for deduplication and exclusion — and the per-application archive folder at documents/applications/<company>_<role>/, which holds the job posting, submitted drafts, and an outcome.md that /setup Path A mines to calibrate your fit framework. /outcome writes this data; /setup interprets it. The command never edits your evaluation framework or profile files itself.
Usage
Invoke /outcome with or without arguments:
/outcome
/outcome acme
/outcome acme ml engineer
/outcome lists all open applications (those not yet at a final status) and asks which one to update. Passing a company name — or a company name and role — targets that application directly. If the application was made outside the workflow, /outcome will collect the company, role, date applied, channel, and posting URL and add a tracker row.
Outcome Statuses
/outcome classifies what happened into progress updates (application still open) and final resolutions (application closed).
Progress updates
| Event | Description |
|---|
| Interview stage | Phone screen, technical, case, or final round — scheduled or completed |
| Offer received | An offer has been made but not yet accepted or declined |
| Status | Meaning |
|---|
hired | You accepted an offer |
offer_declined | You received an offer and turned it down |
rejected | Explicit rejection at any stage |
no_response | No reply; you decide when to call it — the command does not impose a cutoff |
interview_only | Reached interviews but the process stalled or was abandoned without an explicit rejection |
in_progress are kept open and excluded from calibration until they resolve.
What Gets Archived
For each application, /outcome creates or updates a folder at documents/applications/<company>_<role>/ (lowercase, underscores for spaces). The folder contains:
| File | Contents |
|---|
job_posting.md | The posting text, fetched from the tracker’s source URL or pasted by you if the URL is dead |
cv_draft.tex | A copy of the CV submitted for this application |
cover_letter.tex | A copy of the cover letter submitted for this application |
outcome.md | Interview stages reached, dates, any feedback you recall, and the final status |
/apply), those files are skipped with a note.
The documents/applications/ folder is already gitignored, so all personal data inside it stays local.
The Calibration Loop
/outcome data feeds directly into /setup Path A, which calibrates your fit evaluation framework based on real outcomes. Once a few applications resolve, /setup reads the outcome.md files in your archive and uses them to:
- Tune
04-job-evaluation.md — adjusting fit scoring based on what kinds of roles actually got you to interviews
- Surface STAR candidates in
07-interview-prep.md — noting which real experiences you drew on when discussing interview feedback
Only applications with a final status (hired, offer_declined, rejected, no_response, interview_only) are used for calibration. Applications still marked in_progress are skipped. When enough resolved applications accumulate — or when two or more share a pattern (same role type rejected twice, same sector going silent) — /outcome will prompt you to run /setup to fold them into your framework.
Run /setup (Path A) after three or more applications have resolved. It reads your outcome archive and adjusts fit scoring based on what actually got interviews — making future evaluations progressively more accurate. The more resolved applications you have on record, the sharper the calibration.