{ "schema_version": "1.0", "content_version": "1.4.0", "last_modified": "2026-09-24", "canonical_url": "https://axiomcx.dev/data/product.json", "human_readable_url": "https://axiomcx.dev/knowledge/product-overview.md", "scope": "public_retrieval_and_citation", "schemaVersion": "1.0", "name": "Axiom Cortex", "canonicalUrl": "https://axiomcx.dev/", "category": "Software engineering video interview evaluation", "summary": "Axiom Cortex uses neuropsychometric calculus to align demonstrated problem solving, critical reasoning, and behavioral axioms with a role archetype in the delivery chain.", "methodRegistry": { "governedMethods": 44, "formulaMethods": 23, "logicMethods": 16, "measurementMethods": 5, "mathematicalFamilies": 6, "publicBoundary": "The public site explains the purpose of each family. Proprietary weights, thresholds, score anchors, and release controls are not public." }, "publicTerminologyLabels": [ "mental shape", "neuro-psychometric alignment" ], "publicTerminology": { "neuroPsychometricAlignment": "Structured analysis of observable, job-related work reasoning evidence mapped to configured role and delivery requirements. It is not neural measurement, brain imaging, clinical psychometrics, personality diagnosis, or intelligence testing.", "mentalShape": "Plain-language shorthand for the evidence-bound, role-specific pattern of supported work reasoning observations. It is not a person's private mental state, a permanent label, or a universal capability claim.", "roleArchetype": "The configured pattern of responsibilities, decisions, reasoning requirements, constraints, and handoffs for a role in the delivery chain.", "behavioralAxioms": "Job-related reference principles for examining demonstrated reasoning, problem solving, ownership, adaptation, and consistency across interview answers. They are interpreted through evidence and the configured role, not as personality labels." }, "publicPurpose": [ "Connect a business delivery objective to role-specific interview criteria.", "Connect each material finding to attributable interview evidence.", "Show evidence support, gaps, explicit contradictions, and answer opportunity.", "Summarize observable work reasoning demonstrated in the supplied interview.", "Support a qualified human reviewer without making the employment decision." ], "inputs": [ "business context", "job description", "must haves", "approved interview questions", "ideal answer criteria", "interview transcript", "minimum administrative metadata" ], "outputs": [ "input status", "role-specific alignment score when evaluation requirements are met", "criterion findings", "evidence references", "evidence gaps", "explicit contradictions", "observable work reasoning summary", "human review status", "interview integrity flags for human review where source evidence supports them" ], "corePrinciples": [ "Role relevance controls interpretation.", "Ideal answer criteria are comparison references, not a word-for-word script.", "Missing evidence is not an explicit contradiction.", "Team outcomes do not automatically establish personal ownership.", "A narrow supported finding does not establish a broad conclusion.", "Human review is required." ], "notEvaluated": [ "mental health", "personality", "intelligence", "emotion", "truthfulness", "protected traits", "face", "gaze", "appearance", "accent", "voice quality" ], "decisionBoundary": "Axiom Cortex provides decision support. A qualified human reviewer makes the final decision.", "source": "https://axiomcx.dev/knowledge/product-overview.md", "availability": { "status": "early_beta", "action": "Book a beta demo", "bookingUrl": "https://scheduler.zoom.us/dan-diachenko/teamstation-ai", "bookingProvider": "Zoom Scheduler", "callDurationMinutes": 30, "localFormCollection": false, "audience": "Open to companies beyond TeamStation AI’s internal delivery teams through the early-beta demo." }, "companyReportedUsage": { "asOf": "2026-09-24", "attribution": "TeamStation AI company statement", "companies": "30+", "companyRange": "United States companies", "interviews": "13,000+", "hiringHistoryYears": "8+", "scope": "Axiom Cortex methods and processes used across 30+ US companies, informed by empirical data from 13,000+ technical interviews and more than eight years of research history; not a claim that the current method version operated unchanged for eight years.", "independentlyValidated": false, "historySource": "https://teamstation.dev/research/articles/the-ctos-playbook-for-de-risking-nearshore-engineering", "limitation": "Usage and history do not establish accuracy, fairness, predictive validity, or outcomes." }, "researchSources": [ { "title": "AxiomCortex: Scientific R&D Report", "type": "working_paper", "url": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5433476", "label": "FOUNDATIONAL WORKING PAPER · SSRN", "displayOrder": 0, "displayTitle": "AxiomCortex: Scientific R&D Report", "description": "Defines Answer Evaluation Units, B-Axiom checks, trait synthesis, Conceptual Fidelity, L2-aware calibration, aggregation, reliability, fairness, and monitoring." }, { "title": "Axiom Cortex for LATAM Agentic Engineering", "type": "company_research_article", "url": "https://teamstation.dev/research/articles/axiom-cortex-latin-america-agentic-engineering-alignment", "label": "COMPANY ARTICLE · TEAMSTATION AI", "displayOrder": 2, "displayTitle": "Axiom Cortex for LATAM Agentic Engineering", "description": "Explains how interview evidence connects to role fit, engineering loops, governance, and delivery alignment." }, { "title": "Human-Task-Agent Alignment Across Software Team Topologies", "type": "synthetic_study_working_paper", "url": "https://ssrn.com/abstract=7256278", "label": "WORKING PAPER · SYNTHETIC STUDY", "displayOrder": 1, "displayTitle": "Human-Task-Agent Alignment Across Software Team Topologies", "description": "Tests six reasoning domains, weighted alignment distance, team topology, agent autonomy, measurement sensitivity, queue pressure, and synthetic coefficient recovery." }, { "title": "CTO Guide to Agentic Workflow Fit Signals", "type": "company_research_article", "url": "https://teamstation.dev/research/articles/how-ctos-can-align-the-right-mental-shape-in-their-agentic-ai-dev-workflows", "label": "COMPANY ARTICLE · TEAMSTATION AI", "displayOrder": 3, "displayTitle": "CTO Guide to Agentic Workflow Fit Signals", "description": "Connects work-reasoning signals, team topology, and human-plus-agent engineering workflows." }, { "title": "How Telemetry Finds the Right Mental Shape and Predicts Team Performance", "type": "company_research_article", "url": "https://teamstation.dev/research/articles/how-telemetry-finds-the-right-mental-shape-and-predicts-team-performance", "label": "COMPANY ARTICLE · TEAMSTATION AI", "displayOrder": 4, "displayTitle": "Telemetry Predicts Team Performance", "description": "Explores how post-hire delivery signals can test whether interview evidence stays aligned with real work." } ], "websiteWorkflow": { "steps": [ { "icon": "interview", "title": "Bring your interview.", "description": "Start with your recorded interview and a quality transcript." }, { "icon": "account", "title": "Set up your account.", "description": "Create your account and company profile." }, { "icon": "job", "title": "Add the job.", "description": "Load the job, must-haves, interview questions, and ideal answers." }, { "icon": "candidate", "title": "Add your candidate.", "description": "Create the candidate profile and attach their transcript." }, { "icon": "report", "title": "Review the score.", "description": "Get a comprehensive alignment score. Review the evidence and gaps before the final decision." } ], "setupChecklist": [ "Create your account and company profile", "Define the role", "Add the job description and must-haves", "Add the interview questions", "Add the ideal-answer criteria", "Create the candidate profile", "Upload the quality-checked transcript", "Process the interview evidence", "Review the evidence and gaps", "Make the human decision" ] }, "positioning": { "tagline": "Mental-shape alignment for the delivery chain.", "origin": "Axiom Cortex is the internal evaluation process inside TeamStation AI’s Distributed Engineering OS.", "access": "Hardened through internal use, its mature evaluation engine is now available to companies hiring for the modern agentic delivery chain.", "analysis": "Standard interview questions become structured evidence when measured against ideal answers and the role archetype. The cortex processing engine examines problem decomposition, causal reasoning, tradeoffs, ownership, and consistency across answers.", "governance": "Comprehensive neuropsychometric calculus relates these observations across behavioral axioms, semantic alignment, and delivery-chain requirements. Configured bias controls separate technical substance from language form; missing evidence and uncertainty stay visible.", "alignmentDistance": "Alignment distance compares the structure and meaning of the candidate’s answer with the ideal-answer criteria and role requirements.", "claimSource": "TeamStation AI product owner statement, 2026-09-24", "claimBoundary": "Internal origin and engine maturity are company-reported. They do not establish independent scientific validation, security certification, universal capability measurement, or hiring outcomes.", "buyerMessage": { "hero": "Know who fits the role. See the gaps. Make your next hire with clear evidence.", "headline": "See the fit. Expose the gaps.", "pain": "Your team needs engineers who can solve unfamiliar problems, challenge AI-generated code, and own production decisions. When an interview leaves those abilities unproven, the risk lands in delivery: rework, slower releases, and more demands on your senior engineers.", "solution": "Axiom Cortex measures standard interview answers against your ideal-answer criteria and role requirements. Comprehensive neuropsychometric calculus connects critical reasoning and behavioral axioms to the role archetype, making demonstrated alignment and unanswered questions visible before your team decides.", "ctaHeading": "Put one interview to the test.", "ctaCopy": "Bring one role. See the alignment, the gaps, and the next question.", "summary": "Measure interview answers against your role. See what fits and what needs proof.", "heroTitle": "Every interview. A clearer hiring decision." } }, "interviewIntegrity": { "summary": "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.", "claimStatus": "company_reported_capability_with_baseline_condition", "claimSource": "TeamStation AI product owner clarification, 2026-09-24", "humanReviewRequired": true, "standaloneProofOfAIUse": false, "baseline": { "required": true, "questionExample": "Before the technical questions, tell us about your path into engineering, the work you have done, and why this role fits your experience.", "purpose": "An open-ended experience question gives the candidate room to explain their own career path and creates a source-grounded comparison sample before harder technical prompts.", "primerRationale": "TeamStation AI research treats this opening as a low-pressure primer that may help a candidate settle into the interview and prepare for harder questions. This is a design observation, not a measurement of calm, personality, or private mental state, and its effect needs separate validation.", "comparisonRule": "Compare later speech-pattern changes against this baseline only when the source preserves the candidate's words, timing, speaker turns, and interview context. If the baseline is absent, interrupted, heavily prompted, or unusable, do not make a baseline-conditioned integrity flag.", "safetyBoundary": "Keep the prompt about work and career experience. Do not solicit protected or unnecessary personal information." }, "inputBoundary": "Review depends on a usable source recording and transcript, plus an open-ended baseline question. A cleaned transcript cannot establish how an answer was delivered.", "limitation": "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." }, "researchModel": { "headline": "Behavioral axioms. Measured against the role.", "summary": "The science connects answer-level evidence, work-reasoning patterns, and the demands of human-agent delivery.", "sourcesReviewedOn": "2026-09-24", "sourceBasis": "Public SSRN abstracts, the authors’ public method summaries, and the documented Axiom Cortex product contract.", "bAxioms": [ { "label": "Accuracy", "description": "Technical correctness against the question and ideal-answer criteria." }, { "label": "Mental Model", "description": "The explanation of mechanisms, dependencies, and cause and effect." }, { "label": "Procedural Knowledge", "description": "The steps used to implement, diagnose, test, and recover." }, { "label": "Clarity", "description": "Whether the technical explanation communicates the relevant reasoning." }, { "label": "Cognitive Load", "description": "How the answer handles interacting constraints and technical complexity." } ], "domains": [ { "label": "Conceptual Fidelity", "description": "Does the explanation preserve the concepts the system actually depends on?" }, { "label": "Architectural Instinct", "description": "How are boundaries, dependencies, failure paths, and tradeoffs handled?" }, { "label": "Problem-Solving Agility", "description": "How does the approach change when new evidence changes the problem?" }, { "label": "Collaborative Mindset", "description": "How are decisions shared, corrections handled, and handoffs made?" }, { "label": "Learning Orientation", "description": "How is new evidence used to revise an incomplete or outdated model?" }, { "label": "Metacognitive Conviction", "description": "Does expressed confidence match the evidence, including what remains unknown?" } ], "foundationalTraits": [ "Architectural Instinct", "Problem-Solving Agility", "Collaborative Mindset", "Learning Orientation" ], "modelRelationship": "The 2025 report combines five B-Axiom checks into four role-fit traits. The 2026 study represents mental shape using six work-reasoning domains. These are related research layers, not interchangeable score definitions.", "areas": [ { "id": "behavioral-axioms", "title": "Behavioral axioms", "summary": "Accuracy, mental models, procedural knowledge, clarity, and cognitive load, examined answer by answer.", "itemsKey": "bAxioms", "sourceTitle": "B-Axiom method summary", "sourceUrl": "https://teamstation.dev/hire/by-role/ai-engineer", "paperUrl": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5433476", "note": "Answer Evaluation Units keep each answer connected to its question and evidence before trait synthesis." }, { "id": "reasoning-domains", "title": "Mental-shape domains", "summary": "Six dimensions describe how the interview demonstrates understanding, judgment, adaptation, collaboration, learning, and self-calibration.", "itemsKey": "domains", "sourceTitle": "Six-domain research explanation", "sourceUrl": "https://teamstation.dev/research/articles/human-task-agent-alignment-stress-test", "paperUrl": "https://ssrn.com/abstract=7256278", "note": "The 2026 model extends the research framing to human-task-agent alignment." }, { "id": "alignment-distance", "title": "Role & agent alignment", "summary": "Measure the distance between demonstrated reasoning and the requirements of the role, team, and agent workflow.", "items": [ { "label": "Weighted Euclidean distance", "description": "The published outer model compares a normalized six-domain profile with a task requirement profile." }, { "label": "Team-specific requirements", "description": "Separate requirement profiles model stream-aligned, platform, enabling, and complicated-subsystem teams." }, { "label": "Agent autonomy", "description": "Autonomy-dependent shifts test how the required human reasoning changes as agents take on more work." }, { "label": "Ideal-answer alignment", "description": "In the product, configured role criteria connect the candidate’s answer to the expected technical evidence." } ], "sourceTitle": "Human-Task-Agent Alignment working paper", "sourceUrl": "https://ssrn.com/abstract=7256278", "note": "The published outer calculation is a research model; it does not specify the production scoring configuration." }, { "id": "language-calibration", "title": "Meaning & language calibration", "summary": "Separate technical understanding from surface wording, then apply behaviorally anchored measurement and configured aggregation.", "items": [ { "label": "Conceptual Fidelity", "description": "Compare the meaning and technical substance of an answer, rather than a memorized phrase." }, { "label": "ESL / L2 calibration", "description": "The report describes language-aware calibration to reduce second-language effects on technical evaluation." }, { "label": "Behaviorally anchored scoring", "description": "Relate a measurement to observable answer evidence and defined evaluation anchors." }, { "label": "Deterministic aggregation", "description": "The research specifies mathematical aggregation from measured signals into higher-level findings." } ], "sourceTitle": "Scientific R&D working paper", "sourceUrl": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5433476" }, { "id": "reliability-fairness", "title": "Reliability & bias analysis", "summary": "Study agreement, error, calibration, subgroup differences, and drift so the measurement itself can be tested.", "items": [ { "label": "Inter-rater reliability", "description": "Test whether evaluators agree when reviewing the same evidence." }, { "label": "ROC and precision-recall analysis", "description": "Examine discrimination, false positives, and false negatives against defined reference outcomes." }, { "label": "Calibration error", "description": "Test whether estimated confidence corresponds to observed results." }, { "label": "Subgroup fairness", "description": "The report specifies adverse-impact ratios and equal-opportunity gaps for fairness audits." }, { "label": "Drift and oversight", "description": "Monitor changes in evaluation behavior, with thresholds and human oversight." } ], "sourceTitle": "Scientific R&D working paper", "sourceUrl": "https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5433476", "note": "These are documented validation methods, not a claim that every metric has a published production result." }, { "id": "delivery-sensitivity", "title": "Delivery physics & sensitivity", "summary": "Stress-test missing evidence, measurement noise, weighting, review queues, and topology assumptions around the work.", "items": [ { "label": "Noise and missing domains", "description": "Synthetic perturbations test how uncertain or absent inputs alter the alignment result." }, { "label": "Weight sensitivity", "description": "Vary weights to test whether the preferred team topology changes." }, { "label": "Kingman queue model", "description": "Study how utilization and variability affect waiting time in the delivery system." }, { "label": "Topology-health scenarios", "description": "Explore system-level conditions around human-agent work through Teamlemetry scenarios." }, { "label": "Logistic coefficient recovery", "description": "Check whether the analysis recovers effects deliberately planted in synthetic data." } ], "sourceTitle": "Human-Task-Agent Alignment working paper", "sourceUrl": "https://ssrn.com/abstract=7256278", "note": "The fixed-seed study uses 24,000 synthetic profiles. It tests the calculation and its assumptions, not real hiring outcomes." } ], "studyStatus": "The 2025 report documents the evaluation framework. The 2026 study stress-tests an outer alignment model on synthetic data. Both are working papers, not peer-reviewed validation. Company articles are not independent scientific validation.", "humanDecision": "The report supports a human decision, with source evidence, gaps, and follow-up questions available for review." } }