docs/solution_video_script.md

HireTrace: Solution Video Walkthrough Script (≤5 Minutes)

micro1 Agentic Workflows Hackathon Tagline: "Every recommendation traces back to evidence."

---

Video Outline & Timing

Segment	Time	Screen Visual	Narration & Key Points
1. Problem Framing	0:00 - 0:40	• Architecture diagram & fragmented candidate docs (JD, CV, interview notes, assessment report, RFC)	• "Hiring teams evaluate candidates across disconnected silos: CVs, interviews, coding assessments, and project docs." • "Reviewing each in isolation causes teams to miss cross-source contradictions or overweight single signals." • "HireTrace introduces evidence-first assessment: answering not 'Should we hire?', but 'How well does the evidence support the role, and where does it disagree with itself?'"
2. Zero Cost & Local Architecture	0:40 - 1:05	• Terminal showing Ollama running qwen2.5:3b at localhost:11434 • Network audit showing $0.00 external API calls • Architecture diagram showing Pydantic repair loop & 3x self-consistency voting	• "Hard architectural constraint: $0.00 cost." • "Zero paid API calls, zero cloud subscriptions. All inference runs locally via Ollama (qwen2.5:3b), and all retrieval uses local faiss-cpu." • "To ensure local 3B open-weights reliability, HireTrace enforces JSON-schema constrained decoding with Pydantic self-repair loops and 3x self-consistency majority voting with tie-break fallbacks."
3. Baseline A & B Comparison	1:05 - 1:45	• Code walkthrough of /baseline/rubric_scorer.py and /baseline/naive_llm.py	• "We benchmark against two realistic baselines:" • "• Baseline A (Deterministic Resume Rubric): A deterministic rubric scoring Open Source (0–35), Self Projects (0–30), Production (0–25), Tech Skills (0–10), and Bonus Points (0–20). Fast, but blind to cross-source contradictions." • "• Baseline B (Naive Single-Prompt LLM): Concatenates all documents into local Ollama in one prompt. While it can produce apparently grounded individual claims, it lacks the cross-source verification machinery needed to reliably detect contradictions."
4. The Centerpiece Case Walkthrough	1:45 - 3:00	• HireTrace Interactive Dashboard (http://127.0.0.1:8080) • Hovering over candidate dots on the Interactive 2D Quadrant Canvas (showing real-time tooltips & crosshairs at 70/70 thresholds) • Selecting Alexander Sterling (case_15_deceptive_centerpiece) • Side-by-side discrepancy diffs with verbatim quote highlighting and '🔍 View in Dossier' jump navigation • Priority Questions panel with '📋 Copy All Questions' one-click export	• "Here is our centerpiece demo: Alexander Sterling." • "On paper, his CV looks stellar: 8+ years experience, 250 GitHub stars, claiming: 'Led migration of legacy monolithic core to Apache Kafka for a 7-person team.'" • "Baseline B assigns Alexander 85.0 and misses the deception entirely. But HireTrace's decomposed multi-agent pipeline catches it:" • "1. Requirement Mapping Agent extracts 5 core requirements from the JD." • "2. FAISS Retrieval Layer indexes all evidence spans across CV, interview, and project docs." • "3. Cross-Source Verification Agent isolates 5 critical discrepancies across tenure and project authority:"     • Discrepancy 1 (Tenure): CV claims 3.5 years at FinFlow; interview notes prove he joined ~18 months ago.     • Discrepancies 2–5 (Leadership & Authority): CV claims he led the 7-person Kafka migration and authored the master architectural blueprint; Project RFC documents prove Dr. Robert Vance was Principal Architect/Lead and Alexander was a junior contributing member writing Python serialization adapters. • "Notice our new 'View in Dossier' button: clicking it jumps directly to the exact source tab and highlights the raw text." • "4. Claim Critic Agent verifies 100% exact substring containment in raw sources, distinguishing asserted facts from synthesized inferences." • "5. Recommendation Writer Agent plots him on our 2D Quadrant: Role Fit (82.7/100) vs. Evidence Consistency (0.0/100) -> [REVIEW REQUIRED]." • "Recruiters click 'Copy All Questions' to immediately get an interview debrief template for panel review."
5. Audit & Governance Tab: Fairness, Calibration & Defense	3:00 - 4:00	• Switching to '🛡 Audit & Governance' tab • Highlighting the 4 audit cards: EEOC Fairness, Claim Grounding, Uncertainty Calibration, Adversarial Defense	• "In enterprise hiring, compliance and governance are non-negotiable. Our new Audit & Governance tab exposes live telemetry:" • "• Algorithmic Fairness & Parity: Audited under EEOC Uniform Guidelines (4 CFR Part 60) across 44 counterfactual candidate dossiers and 11 demographic groups. Yields 0.00 pts score drift and 1.0000 Disparate Impact Ratio (EEOC compliant)." • "• Evidence Grounding & Critic: 100% quote containment, 100% citation span validity, 66.7% claim grounding on 15 synthetic cases." • "• Uncertainty Calibration: Brier score 0.2281 and Expected Calibration Error of 23.9% across confidence bins." • "• Adversarial Defense: 100% containment across 8 evaluated attack vectors on synthetic benchmarks (prompt injection, delimiter escapes, conversational jailbreaks, and credential/metric fabrications)."
6. Evaluation Benchmark & Closing Hot Take	4:00 - 5:00	• Benchmark matrix tab • 50-case benchmark results • Final hot take slide	• "Across our expanded 50-case benchmark suite spanning 5 engineering domains:" • "• Spearman Rank Correlation (ρ): Baseline A (0.579) -> HireTrace Agent (0.816) (95% CI: [0.446, 0.983])." • "• Contradiction Detection: 100.0% precision, 100.0% recall, 1.000 F1 (zero false alarms on clean controls)." • "• Reviewer Time Saved: Under our standardized cognitive reviewer-effort model, estimated review time falls from 18.0 min to 3.5 min (80.6% estimated time saved)." • "Closing Hot Take: 'Verification establishes consistency, not physical truth.' If a CV and interview agree, that proves internal consistency across documents — not physical truth. That is why automated agents must never make autonomous hiring decisions, and why HireTrace traces every claim to evidence for human reviewers."

---

Production Tips for Recording

1. Resolution: 1920x1080 (1080p).
2. Terminal: Run python -m ui.server 8080 and show the clean web UI at http://127.0.0.1:8080.
3. Tabs to Demonstrate:
   • Tab 1: Candidate Assessment (Scatter quadrant canvas with crosshairs and hover tooltip, Alexander Sterling centerpiece, Priority Questions + Copy button).
   • Tab 2: Discrepancy Diffs (Side-by-side quote highlight and 'View in Dossier' button).
   • Tab 3: Dossier Viewer (Multi-doc tabs).
   • Tab 4: Benchmark Matrix (Spearman rho, Brier score, ECE).
   • Tab 5: Audit & Governance (EEOC fairness, grounding fidelity, adversarial defense).
4. Ollama: Confirm Ollama daemon is running with qwen2.5:3b or running in offline mock mode ($0.00 cost).