David Wolf · Project Use Case
AI SECURITY · PRODUCT SECURITY · RIVERBANKS / INTERNAL PRODUCT
RiverBanks / Internal Product
CORE Behavioral Interview Intelligence Platform
A behavioral interview and self-discovery platform built from 6,000+ interview questions, 30,000 company analyses, STAR scoring, NLP clustering, LLM...
Built CORE as a behavioral interview intelligence and career self-discovery platform around the dimensions Character, Objectives, Relationships, and Execution. The system uses large-scale interview-question mining, company...
Client
RiverBanks / Internal Product
Engagement Type
Internal product and research buildout
Period
2023–2026
Role
Principal Architect / Behavioral Intelligence Architect / AI Coaching Systems Designer
Focus Areas
Behavioral Interview Intelligence, CORE Framework, STAR Scoring, Interview Question Mining
The Research Narrative
Strategic Problem
The challenge was turning scattered interview preparation into a measurable coaching system. Behavioral questions vary by wording, company, role, and interviewer, but many map to deeper recurring themes. The...
What David Did
Defined CORE as Character, Objectives, Relationships, and Execution: four high-level dimensions for behavioral self-discovery and interview storytelling.
What Became Clearer
Created a structured behavioral interview intelligence platform rather than a generic interview-prep prompt library.
Consulting Proof
This is evidence of turning messy security telemetry into explainable dashboards, alert-quality improvements, and executive-ready operating views.
The Context
CORE is the self-discovery and behavioral-interview platform. It is distinct from EMPOWER: EMPOWER is the psychometric/personality engine, while CORE focuses on interview intelligence, STAR evidence, story structure, question taxonomies, practice loops, and candidate self-narrative. The system draws from OSINT interview questions, large-scale company analysis, normalized job application/interview questions, clustering, factor analysis, spaCy/NLP, LLM reasoning, and LLM-based scoring.
The Challenge
The challenge was turning scattered interview preparation into a measurable coaching system. Behavioral questions vary by wording, company, role, and interviewer, but many map to deeper recurring themes. The platform needed to identify those themes, classify questions, elicit useful stories, evaluate answers, and improve candidate responses through feedback loops without producing robotic template answers.
What I Did
- •Defined CORE as Character, Objectives, Relationships, and Execution: four high-level dimensions for behavioral self-discovery and interview storytelling
- •Collected and normalized 6,000+ OSINT behavioral and interview questions
- •Analyzed roughly 30,000 companies, with approximately 13,000 making the quality cut for downstream use
- •Normalized tens of thousands of job application and interview questions into reusable question families and competency themes
- •Used NLP clustering, factor analysis, spaCy-style text processing, and LLM reasoning to group questions into deeper behavioral dimensions
- •Designed eight buckets, four paired domains, and five subfacets per facet to structure the interview intelligence model
- •Created a 200-question instrument for extracting candidate evidence, motivations, patterns, decisions, conflicts, achievements, failures, and learning moments
- •Built STAR-based scoring logic for Situation, Task, Action, and Result quality
The Outcome
Created a structured behavioral interview intelligence platform rather than a generic interview-prep prompt library.
Research Outcomes
Signal Quality
Improved the trustworthiness of operational security signals
Operational Clarity
Translated complex security data into clearer operating views
Stakeholder Visibility
Made technical risk and status easier to explain
Operational Impact
Turned raw telemetry into actionable security intelligence
Capabilities Demonstrated
Dashboard Development
Operational and executive views
Telemetry Normalization
Consistent and trusted data
Security Analytics
Signal investigation and event analysis
IAM / Access Control
Identity telemetry and access insights
SIEM Alert Debugging
Noise reduction and signal validation
Executive Reporting
Security data translated for leadership
Operational Reporting
Actionable views for security operations
Public-Safe Evidence
Shareable insights without sensitive data
Key Deliverables
- •CORE behavioral intelligence framework
- •6,000+ interview-question corpus
- •30,000-company analysis pipeline with 13,000 quality-filtered companies
- •Normalized application/interview question taxonomy
- •NLP clustering and factor-analysis workflow
- •Eight-bucket behavioral model with four paired domains and five subfacets
- •200-question self-discovery instrument
- •STAR answer scoring workflow
Tools & Technologies
Consulting Translation
The reusable pattern is not Disney-specific: normalize fragmented security telemetry, debug low-signal alert behavior, build trusted operating views, and give leadership evidence they can act on without exposing sensitive systems.