Work

Context

Deciding a family vacation usually means a messy spreadsheet, a dozen browser tabs, and one person doing all the research. Package deals and self-planned trips are hard to compare honestly, and the rest of the household rarely gets a structured voice in the decision.

Problem

Travel sites are built for browsing and booking, not deciding. There's no clean way to see the true cost of a package versus planning the same trip yourself, weigh the factors that actually matter to your family, and get everyone's input before committing.

System Design

Joyage is a progressive web app built around a structured decision framework: trips are scored across seven customizable factors that each family weights to their own priorities, true costs for package deals and independent arrangements sit side-by-side, and every household member votes on options with a simple love/like/pass mechanism. Free to use, no payment information required.

AI's Role

• Provides an objective AI assessment of each vacation option alongside the family's own scoring
• Supports the decision rather than making it — the framework and the family stay in control

Why It Matters

Vacations are one of the biggest discretionary purchases a family makes, and most are decided on gut feel and sales pressure. Joyage turns that into a transparent, collaborative decision the whole household participated in.

Status

In progress — "Joyage" is a working title and may change

Context

Resumes show what someone has done. They don't show how someone solves problems — the decisions, dead ends, and course corrections that portfolios hide. As AI becomes the way work gets done, that gap gets worse: the most valuable skill is how you steer, verify, and orchestrate AI, and no hiring signal captures it.

Problem

There's no standardized way for employers to evaluate how a candidate works with AI, and no way for candidates to prove it without handing over private conversations and raw work sessions.

System Design

Thinking MRI is a candidate-controlled benchmark platform. Candidates connect GitHub, projects, and AI work sessions; the system extracts derived signals only — raw conversations stay private, and candidates approve what employers see. Work is scored across eight dimensions (AI Steering, Output Judgment, Orchestration, Verification, Problem Framing, Systems Thinking, Communication, Learning Agility), rendered as a layered cognitive map with percentiles against an operator benchmark. Employers define role-specific thresholds and see candidates ranked by fit for that role — never as universal rankings.

AI's Role

• Analyzes real AI work sessions to derive assessment signals from how problems were actually solved
• Translates messy work activity into a standardized eight-dimension framework
• Powers role-fit matching against employer-defined thresholds instead of keyword filters

Why It Matters

This is a concept I'm proud of because I believe it's where hiring is going: evaluating the process of thinking with AI, not just the artifacts. It reframes the resume for an AI-native workforce while keeping the candidate in control of their own data.

Status

Concept — a working demonstration of where I see the future of hiring

Context

Our church's FUGE camp handed parents everything as printed PDFs — schedules, packing lists, policies, and the week's Bible study material. During camp week, none of that is easy to use from a phone, and parents have no window into what their camper is actually studying each day.

Problem

Static PDFs bury the information people need in the moment. Parents couldn't quickly find logistics, and there was no way to follow along with the daily devotional content their kids were walking through at camp.

System Design

I converted the camp's PDF materials into a mobile-friendly web app: daily devotional reflections tied to the week's Psalm 23 "Good Shepherd" curriculum, real-time announcements for meals and evening activities, an interactive packing checklist, the daily schedule, camp policies, and search so anything is findable in seconds.

AI's Role

• AI-assisted extraction and restructuring of the source PDFs into organized app content
• Accelerated the build from raw documents to working app via Lovable
• The content itself stays human-authored — AI handled conversion and speed, not the message

Why It Matters

This is what I mean by practical systems: take real-world source material a community already depends on, and turn it into software people can actually use during the week it matters. Parents walk through the same passages as their camper instead of a folder of printouts.

Status

Working app — built from the camp's printed PDF materials

Context

Life skills usually get taught as lectures, worksheets, or disconnected apps. I wanted something my son could inhabit instead: a simulated senior year where work, money, friendships, and choices all push on each other like they do in real life.

Problem

Most educational products isolate subjects and flatten consequences. Budgeting, social choices, jobs, time management, and social development end up feeling like separate lessons instead of one connected system, which makes the learning easier to forget.

System Design

Two Thunder Wolves Academy is one project built as two connected surfaces: a 90s-style dashboard for schedule, money, relationships, phone, and daily decisions, plus a 3D school world where the same student walks around, talks to people, and takes on missions. The two halves share one student model and pass state between them, so choices in one surface carry consequences into the other.

AI's Role

• Accelerates iteration across UI, architecture, and implementation details
• Helps document the system so future sessions can resume cleanly
• Supports rapid prototyping while Brad stays focused on the educational design

Why It Matters

This turns life skills into lived consequences instead of lectures. Instead of isolating learning into static content, it lets a student explore, interact, make choices, and see how those choices ripple across everyday life.

Status

In progress — active educational simulator spanning dashboard and 3D school

Context

Casting is fragmented, inefficient, and heavily manual — especially for indie filmmakers and emerging talent. Actors struggle to understand what they're right for, while productions spend time filtering noise instead of finding fit.

Problem

Traditional casting platforms rely on static profiles and keyword searches, which don't reflect real-world fit, availability, or context. Both sides lose time, and good matches are missed.

System Design

I designed CastIQ as a data-driven casting platform that structures talent profiles, project requirements, and availability into a system that can be reasoned about — not just searched.

AI's Role

• Analyze role requirements beyond simple keywords
• Help talent understand alignment with roles
• Reduce friction in discovery without replacing human decision-making

Why It Matters

CastIQ isn't about automating casting decisions — it's about making better conversations possible by improving signal on both sides.

Context

Public safety dive teams operate in high-risk environments where readiness, training, and compliance aren't optional — but the systems supporting them are often outdated or fragmented.

Problem

Tracking certifications, training dives, readiness, and compliance is often manual, inconsistent, and reactive. That creates risk where there shouldn't be any.

System Design

ORCA | ONE was built as an operational system that centralizes diver readiness, training history, and compliance status into a single, authoritative source of truth.

AI's Role

• Flagging gaps in training or certification
• Identifying patterns in readiness over time
• Supporting leadership with clearer situational awareness

Why It Matters

This system supports real teams doing real work, where clarity and preparation directly impact safety.

Context

AI is moving faster than most organizations can meaningfully track. The conversation is often polarized — either hype-driven or fear-driven — with little grounded analysis.

Problem

There's no simple way to monitor how AI is affecting roles, workflows, and systems over time without drowning in noise.

System Design

AI Watchtower was built as a signal aggregation and analysis platform designed to surface trends, impacts, and early warnings — not predictions.

AI's Role

• Aggregate and summarize signals across domains
• Detect emerging patterns
• Support human interpretation rather than replace it

Why It Matters

AI Watchtower exists to support informed decisions, not hot takes — especially as AI continues to reshape work and systems.

Context

Homeschooling families often lack access to practical, experience-based learning — trades, outdoor skills, arts, farming — that traditional classrooms don't offer. Meanwhile, skilled community members are willing to share their knowledge but have no easy way to connect with families nearby.

Problem

There's no simple, trust-first directory for families to discover local mentors offering in-person, hands-on learning experiences. Existing platforms are either too complex (scheduling, payments, reviews) or focused on online tutoring, missing the human, community-driven connection entirely.

System Design

A public mentor directory with filtering by skill, location, age range, and format. Mentor profiles with inquiry submission for parents. A Skill Request Board where families post learning wishes and others express interest. Manual admin approval for all mentor listings — trust over speed. Built with React, Tailwind CSS, and Lovable Cloud for the backend (database, auth, storage, edge functions).

AI's Role

• Generates the social media preview (OG) image for the platform
• Powers the development workflow (code generation, iteration, deployment via Lovable)
• Intentionally NOT used for matching, recommendations, or content moderation in V1 — human oversight is a core principle

Why It Matters

Children learn best through real experiences with real people. Neighbor Learning puts community trust and human connection first — no algorithms, no ratings, no payments. It's a return to how learning used to happen: from the people next door.

Context

Modern society is critically dependent on digital knowledge, which is predominantly cloud-based. This creates a severe vulnerability: in scenarios like grid collapse, natural disasters, EMPs, or conflicts, essential information becomes inaccessible precisely when it's most needed. Last Light AI was built to address this, providing a resilient, offline repository of human survival knowledge.

Problem

The primary problem is the fragility of digital knowledge in grid-down scenarios. It mitigates the single point of failure inherent in cloud-dependent information systems, ensuring access to vital data even when Google, YouTube, and emergency services are unavailable. Unlike static digital libraries, it offers an interactive AI that can reason through specific survival queries, providing actionable advice rather than just raw data.

System Design

Frontend built with React, TypeScript, and Vite for high-performance development. Styled with Tailwind CSS for responsive, utility-first design. Hosted on Vercel for global availability. A clean, component-based architecture designed for speed and future extensibility, focusing on a "Local-First" philosophy for eventual offline integration.

AI's Role

• Powers the entire development lifecycle, including code generation, rapid iteration, and automated deployment via Lovable
• Generates high-quality visual assets, including OG images and thematic illustrations
• Assists in structuring and indexing the 512GB survival knowledge base for efficient retrieval by local models
• Intentionally NOT used for real-time matching or content moderation — human oversight is a core principle of trust and reliability

Why It Matters

When infrastructure fails, knowledge shouldn't fail with it. Last Light AI ensures that critical survival intelligence remains accessible, interactive, and useful — regardless of connectivity.