GigMe
Practice job interviews, find out which of your skills hold up, and track which applications get replies.

Current status
Live career coaching and job market beta at gigme.ngi.video; verified in single-user mode with public market rollups and free account sign-in.
Overview
Interactive career copilot and job-market intelligence beta that tests your real-world strengths, runs realistic practice interviews, surfaces high-fit roles with hybrid search, and tracks which applications earn human replies.
Why it was built
Job boards flood people with keyword-matched listings without telling them which skills they are actually missing or whether their application strategy is working.
Why it helps
Guides you through focused modes for career discovery, mock interviews, skill practice, and application tracking, while aggregating public role and compensation signals.
What you can do
- Coaching modes: Auto-Calibrate, Mock Interview, Skill Coach, Career Desires, References, and Role Triage
- Verified skill profile that separates tested strengths from self-reported resume claims
- Hybrid role and compensation market explorer with explainable match badges
- Single-user verified coaching loop with public market rollups at gigme.ngi.video
Interpretable Ranker v2.8, Scout DAWRI Write Receipts & Counterfactual Why-Here
Separates tested skill assessments from self-reported resume claims, enforces NBER empirical attainability multipliers, and backs every AI coach mutation with a one-click Undo database receipt.
Verified Skill Assessments & NBER Attainability Multipliers
Separates tested skill_assessments from self-reported claims, applies empirical callback-decay factors for years-short and seniority reach-down, and locks ranking stability via SHA-256 Kendall-Tau golden snapshots.
Dual-Gate Assistant Write Receipts with One-Click Undo
Cross-checks every Scout sentence claiming a profile or filter update against committed database mutations, stripping unbacked claims and rendering an interactive Undo receipt token on real writes.
Punctuation/Acronym Guards & Preference-Aware Recall Ladder
Preserves C++, C#, .NET, Go, and AI via exact symbol and word-boundary guards, then widens zero-hit queries across 4 deterministic stages without re-probing rejected role families.
Counterfactual Score Breakdown & NASA-TLX Cognitive Lockout
Shows base score, multiplicative adjustments (attainabilityGap, seniorityReachDown, compHeadroom, freshnessBoost), and open eligibility gates across 6 coaching modes with a 0.68 NASA-TLX Socratic lockout.
Inspect NBER empirical attainability multipliers and one-click database write Undo receipts
88 → Attainability ×0.85 → Seniority gap ×1 = 75% Matchprofile.min_compensation_usd · Updated $160,000 → $185,000Ranker v2.8 attainability math & DAWRI write receipts vs. keyword floods & hallucinated saves
Standard job search strips '+' from 'C++', matches 'writer' inside 'Underwriter', inflates match scores when 1 of 11 skills match, and lets chatbots claim profile updates that never hit the database.
// Keyword board + unverified assistant
query("C++ Go writer") -> matches "C", "Google", "Mortgage Underwriter"
score = 1 / 1 matched skill = 95% Match (ignores 10 missing skills & VP gap)
assistant: "I updated your salary floor to $185k!" (0 DB writes committed)GigMe preserves C++/C#/.NET/Go tokens, weights verified skill assessments by NBER callback-decay multipliers in whyHere badges, and strips any Scout mutation claim lacking a committed DB write receipt.
// GigMe Ranker v2.8 + Why-Here + DAWRI Receipt Verifier
guards: symbolIlike=["C++"], acronymBoundary=["\yGo\y", "\bwriter"]
whyHere: Base 84 × 0.85 (1 yr short) × 1.08 (<72h fresh) = 77% Match
dawri: committedWrites=[{ field: "target_salary", next: "$185k" }] -> [Undo]0.7635 → 0.951 (+0.1875 · Sharpness +51.6% · PSNR 44.54 dB)Negation parity & evidence verifiedInteractive walkthrough
Step through how GigMe works without creating an account or installing local dependencies.
Entry & problem context
Maturity: Live in productionJob boards flood people with keyword-matched listings without telling them which skills they are actually missing or whether their application strategy is working.
Interactive career copilot and job-market intelligence beta that tests your real-world strengths, runs realistic practice interviews, surfaces high-fit roles with hybrid search, and tracks which applications earn human replies.
Shared platform architecture sandbox
Test the live cross-language single source of truth shared across TypeScript, Python, and Rust.
Evidence grounding & negation parity check
RejectedPolarityFlip (grounded: false, overlap: 1)clarify (confidence: 0.425)Dual-gate write receipt verifier (DAWRI) & FTT math healer
trueNo profile changes were committed in this turn.142, σ 133.5515, gist positive_ev_with_downsideRemote or hybrid? · Target salary floor? · Company stage? (lockout: false)Semiotic Brand Identity & Federated SoC Governance
Peircean Brand Mark, Multi-Size Squint Test & 3-Tier SoC Boundary
sonar_spotlightprivate_commercial (max tier: internal_commercial)100.0% (non-redundant >15%) · Retired symbol trap: Clear (0 retired symbols)Engineering Velocity & Open-Source Hygiene
Synced from @brbrainerd and @vox-foundation via the GitHub GraphQL API (GET /api/github/stats).
Single-file full-stack programming language and Rust compiler that generates database schemas, server routes, and typed clients from one declaration.
Interactive political economy simulator with ECS civic rights, institutional modeling, policy levers, and multi-regime scenarios.
Interactive 3D macaque brain atlas and stereo surgical view planner rendered in browser WebGL.
Single-binary Rust and React kiosk shell for Raspberry Pi digital photo frames with remote mobile upload.