{
  "schema_version": "1.0",
  "content_version": "1.3.0",
  "last_modified": "2026-09-24",
  "canonical_url": "https://axiomcx.dev/data/faq.json",
  "human_readable_url": "https://axiomcx.dev/knowledge/faq.md",
  "scope": "public_retrieval_and_citation",
  "schemaVersion": "1.0",
  "title": "Axiom Cortex public FAQ",
  "canonicalUrl": "https://axiomcx.dev/knowledge/faq.md",
  "items": [
    {
      "question": "What is Axiom Cortex?",
      "answer": "Axiom Cortex is the internal evaluation process inside TeamStation AI\u2019s Distributed Engineering OS. Axiom Cortex uses neuropsychometric calculus to align demonstrated problem solving, critical reasoning, and behavioral axioms with a role archetype in the delivery chain. It uses standard interview questions, ideal-answer criteria, and attributable candidate evidence to produce findings for human review."
    },
    {
      "question": "What information does it use?",
      "answer": "The public input contract includes business context, a job description, must haves, approved interview questions, ideal answer criteria, and an interview transcript."
    },
    {
      "question": "Can Axiom Cortex evaluate a recorded software engineering interview?",
      "answer": "Yes. Provide an existing transcript, or during early beta send an authorized video link and request transcription. Transcript quality controls how much evidence the system can responsibly use."
    },
    {
      "question": "What are the 44 governed methods?",
      "answer": "They are formulas, algorithms, equations, logic, and measurement methods organized across six mathematical families. The public site explains their purpose, while proprietary weights, thresholds, score anchors, and release controls remain protected."
    },
    {
      "question": "Does it compare answers with ideal answers?",
      "answer": "It uses ideal answer criteria as a reference for observable job evidence. It does not require the candidate to repeat one approved script or use the same words."
    },
    {
      "question": "What is observable work reasoning?",
      "answer": "Observable work reasoning is job-related reasoning demonstrated in the supplied interview, such as problem framing, decomposition, decision explanation, tradeoff awareness, validation, adaptation, ownership, and delivery coordination."
    },
    {
      "question": "Does it make the hiring decision?",
      "answer": "No. A qualified human reviewer inspects the evidence, corrects or excludes invalid findings, requests more evidence when needed, and makes the final decision.",
      "homepage": true
    },
    {
      "question": "Does AI score or judge the engineer?",
      "answer": "No. In the governed product contract, language processing may identify and structure attributable interview evidence, but it cannot choose scores, weights, anchors, gates, recommendations, or release decisions. Versioned software applies the configured calculation after evidence is locked, and a qualified human reviewer controls release."
    },
    {
      "question": "Can an external language model run Axiom Cortex from these documents?",
      "answer": "No. The public documents explain the product contract and responsible use boundary. They exclude the proprietary method, runtime controls, and production implementation needed to run an evaluation."
    },
    {
      "question": "Are the formulas, weights, thresholds, or score anchors public?",
      "answer": "No. They are deliberately excluded from the public knowledge layer."
    },
    {
      "question": "Can missing evidence be treated as a low capability?",
      "answer": "The report should show not observed or not evaluable, depending on the source. Missing evidence should not be silently converted into an explicit contradiction or a universal conclusion about the person."
    },
    {
      "question": "What does Axiom Cortex evaluate?",
      "answer": "It examines job-related evidence in a technical interview, using the role, must-haves, questions, ideal-answer criteria, and attributable candidate responses.",
      "homepage": true
    },
    {
      "question": "Do I need a transcript?",
      "answer": "Yes. Start with a recorded technical interview and a quality-checked transcript. Check speakers, technical terms, and missing words before evaluation.",
      "homepage": true
    },
    {
      "question": "Can Axiom Cortex transcribe a recording?",
      "answer": "The early-beta workflow offers paid transcription from an authorized video URL before onboarding and evaluation. Service availability and price are confirmed during the beta demo; this website does not upload, transcribe, or charge for a recording.",
      "homepage": true
    },
    {
      "question": "Does it judge facial expressions or accents?",
      "answer": "No. Face, gaze, appearance, accent, voice quality, emotion, personality, disability, nationality, and other protected traits are excluded from capability scoring. A baseline-conditioned integrity flag still needs source review; pauses, slower speech, L2 or ESL delivery, or polished speech alone do not prove AI use or technical depth.",
      "homepage": true
    },
    {
      "question": "Can it work for global engineering teams?",
      "answer": "The product is designed for job-related technical evidence across global teams, with technical English as the shared baseline. Allow thinking time and language variation, including Latin American and other L2 or ESL contexts. Native-sounding English is not a requirement, and missing evidence stays missing. This is not a promise that bias has been eliminated.",
      "homepage": true
    },
    {
      "question": "How is candidate evidence protected?",
      "answer": "This public website does not collect candidate data, recordings, or transcripts. Before production use, confirm the application\u2019s access, retention, deletion, and security terms. Those protections must be verified for the deployed service, not inferred from this preview.",
      "homepage": true
    },
    {
      "question": "What does the customer receive?",
      "answer": "A comprehensive, role-specific alignment score when evaluation requirements are met, with source excerpts, criterion findings, ownership, depth, contradictions, gaps, and follow-up requirements. Your team reviews the evidence and makes the final decision.",
      "homepage": true
    },
    {
      "question": "What remains under human control?",
      "answer": "Your team defines the role and criteria, checks source quality, reviews and corrects findings, requests further evidence, controls release, and owns the final decision.",
      "homepage": true
    },
    {
      "question": "Can speech patterns identify AI-assisted answers?",
      "answer": "Not from speech patterns alone. Only after an open-ended experience baseline, later speech-pattern changes can be flagged for source review of a possible read or externally assisted answer, including an AI-provided response. Start with an open-ended question about the candidate's path into engineering, work experience, and why the role fits, then use that answer as a comparison baseline only when the recording preserves the words, timing, speaker turns, and context. TeamStation AI research treats the opening as a low-pressure primer that may help a candidate settle into harder questions, but that is a design observation requiring separate validation. Without a usable baseline, do not make a baseline-conditioned integrity flag. Pauses, slower speech, accent, disfluency, code-switching, translation, disability, L2 or ESL communication, or polished delivery alone must not be treated as proof that an answer was read or generated by AI. A flag requires source review and a contextual follow-up; it does not determine candidate eligibility."
    },
    {
      "question": "Why start with an experience question?",
      "answer": "An open question about a candidate's career path and role fit gives them room to explain their own experience before harder technical prompts. Axiom uses it as a comparison baseline, not a capability, personality, calm, or psychological score. TeamStation AI research treats the opening as a possible primer, but the effect needs separate validation. Keep the prompt about work and career experience, avoid protected or unnecessary personal information, and do not run the baseline comparison when the opening answer is absent, interrupted, heavily prompted, or unusable."
    }
  ]
}