SELECTED PERSONAL PROJECTS / 2026EL SALVADOR · REMOTE COLLABORATION

I build tools, stories, and small systems that make room to create.

I'm Santy — an independent builder working across AI, video, software, and creative experiments. From homestead storytelling to local-first tools, I make things I genuinely want to use.

After years in operations, I want my time to go toward making things. These are actual projects: some working, some experimental, all honest about their current stage.

See the projects ↓Short PDF overview ↗
Based in the Bunker. Built independently. Still exploring.
Original footage from Santiago's KM51 land project
KM51 / ORIGINAL FOOTAGE
FROM A REAL PROJECT · NOT STOCK ART

I build from the Bunker, then take the ideas into the real world.

The work

What I'm actually building

A personal workshop in three parts: creative media, useful products, and local AI systems. See what each really does.

01 / Media & storytelling

01 / 08
Authentic frame from a KM51 long-form rough-cut video, still awaiting final edit review
KM51 / LONG-FORM EDITING

From raw footage to an episode

This starts with unedited camera footage from the land. The goal is to organize it into a coherent long-form story for YouTube, Facebook or another full-episode channel—not just pull out highlights.

RAW FOOTAGEEDIT / REVIEWROUGH EPISODE
CURRENT STAGEWorking rough-cut pipeline
What I built and how I contributed

What the system does: Original-footage cataloging, proxy and audio prep, transcripts, edit decisions, draft sequences, review exports and owner approval.

My role: I define the story, editing priorities and review criteria, then direct AI-assisted work and test the results.

Evidence and limits: Multiple long-form rough cuts and episode packages exist on the F: drive. Final music, audio review and publish approvals are still case-by-case.

What this project taught me: The rough cut is only one milestone. Music, real dialogue, pacing, and review still matter.

02 / 08
Original KM51 vertical video frame used in short-form review
AI CLIPPING / REPURPOSING

One finished video, new short-form opportunities

This is a different job. Take a finished long-form video—including content from an established YouTube channel—and turn it into short clips that can stand alone or lead viewers back to the full episode.

FINISHED VIDEOSELECT / REFRAMESHORT CLIPS
CURRENT STAGEFunctioning clipping workflows
What I built and how I contributed

What the system does: Transcript-based candidate selection, ranking, vertical reframing, burned captions and review before release. The general clipping tool and KM51-specific clipper have distinct goals.

My role: I specify how a good clip should behave, which audience it serves and how much manual editing the pipeline should replace.

Evidence and limits: General and KM51 clipping apps passed local health checks; rendered vertical clips are on disk. Unlimited, end-to-end unattended publishing is not claimed.

What this project taught me: A short made to drive people to a full video needs different scoring than a self-contained clip.

02 / Applications & interactive products

03 / 08
Screenshot of Clockleaf offline hours tracking app
CLOCKLEAF / ANDROID APP

A simple time clock without the monthly bill

An offline-first time tracker for recording work, projects and earnings—built from the frustration of needing a subscription for a simple tool.

CURRENT STAGEDevelopment beta
What I built and how I contributed

What the system does: Product rules, time-entry screens, project rates, Android packaging and testing. No live billing or commercial release yet.

My role: I set the product direction, requested changes, tested rate behavior and shaped the pricing concept.

Evidence and limits: Android debug APK, recorded 44/44 isolated web tests and separate on-device verification.

What this project taught me: Details like project-specific pay rates have to behave predictably; even small rules change the experience.

04 / 08
Screenshot of Pulse Jump rhythm platformer
PULSE JUMP / BROWSER GAME

An idea you can actually play

An original side-scrolling rhythm game shaped through rapid experimentation: jumps, double-jump routes, spikes, floor dips, pits, traps, platforms and speed portals.

CURRENT STAGEPlayable web beta
What I built and how I contributed

What the system does: Gameplay direction, progression changes, browser/mobile simulation and iterative prototypes.

My role: I define the feel of the game, request mechanics, review versions and make the call on what changes next.

Evidence and limits: 25 configured stages, two original tracks and published browser-test evidence. Real handset feel still needs validation.

What this project taught me: Simulation tests can check timing, but the feel of a game still needs real hands-on playtesting.

Try the playable beta
05 / 08
HAMMR.Service marketplace · product concept
HAMMR / SERVICES MARKETPLACE

Connecting customers with people who can do the job

A local-services marketplace concept for El Salvador where customers post work, contractors bid, and an admin can oversee requests and payments.

CURRENT STAGEMVP codebase
What I built and how I contributed

What the system does: Customer, contractor and administrator flows, bidding, acceptance, chat and wallet/commission logic.

My role: I define the opportunity, user flows, business logic and feature priorities.

Evidence and limits: React Native/Expo and FastAPI/MongoDB source and project specifications exist. This is not presented as a public commercial launch.

What this project taught me: A marketplace is more than a listing page: trust, bidding, chat, commissions, and local payment realities all affect the flow.

03 / AI assistants & coordination

06 / 08
Sierra local assistant icon
SIERRA / PERSONAL AI ASSISTANT

An assistant that knows what I'm building

Sierra is my personal AI assistant and coordination interface. Her job is to keep context, help me think through the work and connect decisions to the tools that can carry them out.

CURRENT STAGELocal assistant project
What I built and how I contributed

What the system does: Text and voice interfaces, retained context, coordination code and local status checks.

My role: I set the expectations, personality, capabilities and what useful assistance should actually feel like.

Evidence and limits: Sierra's Python application, voice launcher, state files and smoke tests exist locally. Individual integrations need ongoing verification.

What this project taught me: A useful personal assistant needs continuity and context, not just a good answer in a single conversation.

07 / 08
Original AI Council project icon
AI COUNCIL / MULTI-AGENT DECISIONS

Different perspectives. One clear decision.

The Council isn't Sierra. It's a separate structured discussion and approval system for role-based input, documented recommendations and owner-gated decisions.

CURRENT STAGEBounded local MVP
What I built and how I contributed

What the system does: Role registry, recorded sessions, approvals, handoffs, provenance and SQLite audit records.

My role: I designed the collaboration model and decision rules, with final approval kept in my hands.

Evidence and limits: Standalone AI Council codebase, database schema and tests exist. The complete integration with all live agents remains unfinished.

What this project taught me: Multiple agents need defined roles, traceable recommendations, and a clear owner-approval process.

08 / 08
DEX↓LOCAL TOOLS↓VERIFIED OUTPUTSWorkflow illustration · not a live dashboard
DEX / LOCAL EXECUTION & BUNKER

Taking ideas from a chat to the actual computer

Dex is the execution side of the setup. The Bunker is the wider local workspace holding projects, tools and shared context. They aren't the same as Sierra or the Council.

CURRENT STAGELocal tooling in progress
What I built and how I contributed

What the system does: Local inspection, bounded agent execution paths, Codex-based experiments, repo tools and workflow integration.

My role: I determine what should be automated, approve the scope and verify whether the work actually happened.

Evidence and limits: Local Dex and Bunker components are present. Execution permissions differ by tool path; a fully autonomous reliable agent is not yet claimed.

What this project taught me: Delegating a task is not the same as verifying it finished; the system must show what actually happened.

Why I do it

Creating is the point. AI is a way to get there.

My background taught me to notice bottlenecks. What I enjoy is turning those problems into something real. I lead the product vision, work with AI-assisted tools, check what was actually built, and keep improving it.

  1. Find something useful, interesting or frustrating enough to fix
  2. Map out a usable first version
  3. Direct AI-assisted development, media work or prototyping
  4. Test real outputs and keep improving the result
Currently exploring

The workshop is still open.

Turning more of the Bunker into reliable systems, improving KM51's episode editing, and continuing to explore original software, games, and creative workflows. Each new experiment is a chance to make something useful—not another excuse to stay busy.