Technical Research & Engineering

GLOBAL INTENT COMPANY

Interactive technical environment for machine learning, scientific instrumentation, computational systems, experiments, and project evidence.

Developed independently by founder and researcher Cory Tortorici. Source code, controlled experiments, null results, architectural iterations, and public research logs are made inspectable across all project nodes.

Source Repositories

Laboratory Chronology

LATEST FROM THE LAB

Recent empirical findings, architectural iterations, and null results surfaced directly from active research logs.

Active laboratory research log entries with timestamped records are available in the full research log.

Interactive Spatial Knowledge Graph

EXPLORE THE RESEARCH

Navigate the connected network of research projects, architectural pipelines, and domain clusters in real-time 3D.

Rotate • Zoom • Click Nodes to Unfold

60 FPS

Tier:

Focused on resumeBUILDER (Agent Rez) • Orbiting sub-nodes active

Domains:

SPATIAL FOCUS:resumeBUILDER (Agent Rez)•Shipped Software

GitHub Live App

Shipped SoftwareKind: softwareShipped Software[RESUME-BUILDER-APP]

resumeBUILDER (Agent Rez)

GI-Company/resumeBUILDER

A local-first, privacy-focused resume engineering platform featuring real-time document layout, F-Pattern visual hierarchy analysis, AI bullet point optimization via Groq SDK, multi-format parsing (Word DOCX, PDF, LinkedIn), headless Chromium PDF generation via Puppeteer, and Stripe subscription billing.

Software Purpose & Scope:Provide a fast, privacy-respecting career documentation suite that optimizes resume content for human recruiters and applicant tracking systems using verified visual ergonomics and AI refinement.

Structural Overview

Built with Next.js 15 App Router and React 19. Combines an instant client-side document layout preview, an F-Pattern cognitive visual hierarchy heatmap overlay, server-side Groq Llama 3.3 70B bullet point rewriting via STAR methodology, serverless headless Chromium PDF generation, and multi-format document ingestion.

Canonical Source Artifact

GitHub Repository

Primary Source CodePublic

GI-Company /resumeBUILDER

Canonical public source repository: Next.js 15, Groq AI bullet rewriter, Puppeteer PDF export, and Stripe billing.

Canonical GI-Company Source

LIVE DEMO VIEW SOURCE

Design Invariants & Principles

[1]Local-First Privacy: Resume draft data remains in browser local state; external APIs receive only the bullet text requested for rewriting.

[2]Cognitive Layout Optimization: Incorporates recruiter scanning eye-tracking research (F-Pattern) to position high-value accomplishments.

[3]High-Fidelity Document Export: Headless serverless Chromium guarantees identical PDF rendering regardless of the user browser engine.

System Components

Real-Time Resume Composer

Modular document section editor with drag-and-drop reordering and synchronous keystroke layout preview.

F-Pattern Visual Hierarchy Scanner

Calculates recruiter eye-tracking gaze paths and typography contrast ratios directly on the resume canvas.

Groq STAR-Method AI Rewriter

Restructures weak bullet points into high-impact Situation-Task-Action-Result metrics via Groq Llama 3.3 70B.

Document Ingestion Pipeline

Parses existing resumes from Word (.docx via Mammoth), PDF (pdf-parse), or LinkedIn profile exports into structured JSON.

Headless Chromium PDF Exporter

Generates pixel-perfect, vector-sharp print PDFs using serverless Chromium (@sparticuz/chromium-min) and Puppeteer.

Stripe Monetization & Subscriptions

Manages tiered subscription plans, checkout webhooks, and download quota enforcement.

Technology Stack

Next.js 15 (App Router)React 19 & TypeScriptTailwind CSSGroq SDK (Llama 3.3 70B STAR Rewriter)Puppeteer & @sparticuz/chromium-minMammoth.js (Word DOCX Ingestion)pdf-parse (PDF Text Extraction)Stripe BillingPostHog AnalyticsResend Email API

Technical Decisions

Upgraded to Next.js 15 App Router with React 19 for optimal server action performance.

Leveraged Groq ultra-low-latency inference for sub-second bullet point suggestions.

Maintained strictly within the Shipped Software domain as applied product engineering.