Under the hood
Where these answers come from
Career Explorer doesn't guess. Every recommendation it makes is built on the federal government's own published rules: OPM's occupational series definitions, OPM's qualification standards, the Code of Federal Regulations, and live USAJOBS listings. AI helps read your resume and translate government language into plain English - but it works from these official sources, and the answers it gives are checked against them before you see them.
Three separate questions, never blended
Federal hiring really asks three different questions, and this site keeps them separate on purpose:
- Can you apply at all? (Eligibility) - determined by hiring paths you tell us about: veteran, current federal employee, recent graduate, and so on. You answer this; we never infer it.
- Where does your background fit? (Series fit) - your experience matched against all 618 the government uses to classify white-collar work.
- Would you meet the minimum qualifications? (Qualification) - your resume checked against a specific announcement's published requirements, the way a federal HR specialist would read them.
Many job tools collapse these into one score. We don't, because federal HR doesn't: you can be a perfect professional fit for a job you're not eligible to apply for, and eligible for one you don't yet qualify for. Knowing which problem you have is most of the battle.
The official sources we build on
- OPM Handbook of Occupational Groups and Families - the government's own definitions of all 618 occupational series, used to describe and match every series we recommend.
- OPM General Schedule Qualification Standards - the published requirements for 415 individual series, including which ones carry an (a degree or specific coursework you must have, no matter how strong your experience is). We tell you when one applies.
- The Code of Federal Regulations (Title 5) - the hiring regulations themselves, including time-in-grade rules for current federal employees. When the qualification check cites a rule, the citation links to the official text.
- USAJOBS - job searches run against the live USAJOBS API, the same listings you'd see there.
- O*NET Military Transition Search (U.S. Dept. of Labor) and mos.directory - for veterans, your MOS, rating, or AFSC is translated using these crosswalks, with attribution where the data appears.
For veterans specifically: we hold 1,359 military specialties across all 6 service branches - every one with a plain-language description of the work - connected to civilian job titles by 13,394 individual links. That's roughly ten civilian job titles for every specialty, which is the point: your service didn't map to one civilian job, it mapped to a dozen you may never have heard called that.
We keep dated copies of the reference material (the qualification standards on this site were fetched 2026-08-13) and check the sources for changes on a schedule - so we can tell you exactly which version of a rule an answer was based on, and notice when OPM or the CFR changes something. The plain-language glossary covers 112 terms, each linked to the authority behind it.
Go read them yourself: Handbook of Occupational Groups and Families General Schedule Qualification Standards Title 5, Part 300 — employment (incl. time-in-grade) Title 5, Part 511 — position classification USAJOBS Military Crosswalk Search mos.directory
What the AI does - and what it isn't allowed to do
AI (currently OpenAI models) is used for reading, not deciding:
- Reading your resume into a structured profile: roles, skills, tools, credentials, education.
- Translating announcements and glossary terms into plain language.
- Applying the qualification standard to your resume - following a written procedure adapted from how federal HR specialists actually make minimum-qualification determinations.
Guardrails, enforced in code rather than requested politely:
- The AI can't invent a match. Every series recommendation must be backed by evidence actually found in your resume; a recommendation the evidence can't support is discarded.
- The AI can't invent a citation. Legal citations come back as structured references, are verified against our copies of the official text, and are dropped if they don't check out. We build the link; the model never supplies a URL.
- The AI doesn't adjudicate eligibility. Your hiring paths come from your own answers, period.
- Hedged by design. Qualification results say "likely qualified" or "borderline," never "qualified" - because only an agency HR office makes that determination, and this site says so on the same screen.
How each of the three checks actually runs
Each step below is tagged with who does it: you, deterministic code, or the AI. The AI is one tagged step in the middle of each flow, with code on both sides of it.
What happens to your resume
Your resume is analyzed in memory and never written to disk. The extracted text is sent to OpenAI to build your profile (OpenAI is instructed not to store it), the original file is discarded as soon as the text is read, and the derived analysis is erased when your session ends. Visits are counted on our own server - no third-party script, no IP addresses, no way to identify you. The full details are on the Privacy & cookies page.
The honest limits
- This is a prototype. Results are decision support, not an official determination - the announcement and the agency's HR office always control.
- Qualification standards are vendored for 415 series; for 64 of them, whether an Individual Occupational Requirement applies is not yet confirmed. When we don't know, we say "unknown" rather than assuming you're fine.
- Scanned or image-only PDFs aren't read yet, and the AI can misread unusual resume formats - which is why every result shows you the evidence it was based on.
Want the version with file paths, counts, and provenance for every claim above? It's docs/ARCHITECTURE.md in the project's source repository. Military skill data courtesy of mos.directory; military crosswalk data from O*NET, U.S. Department of Labor, used under CC BY 4.0.