I build practical AI applications, product prototypes, and workflow automation.

My background combines web development, design, client communication, and end-to-end project delivery. I am now focused on turning real operational problems into usable AI-powered products: framing the problem, designing the workflow, integrating services, testing the result, and iterating with users.

A deterministic, offline, read-only four-Agent decision-system reference implementation. It demonstrates frozen independent votes, a paper-only lifecycle, a canonical timeline, public-field projection, provider-neutral model contracts, local fallbacks, and a fake-transport safety lab.

I defined the product rules, Agent roles, decision and permission boundaries, public/private separation, and acceptance gates. The repository explicitly documents coding-Agent assistance instead of implying that every line was written manually.

Evidence: automated tests, deterministic fixtures, validation scripts, CI, architecture and verification documentation

Stack: Node.js, JavaScript, HTML/CSS, REST-style GET-only API, GitHub Actions

An end-to-end web workflow that turns a user's idea into scripts and generation prompts, submits image or video jobs, tracks asynchronous status, and returns the final output.

My work includes workflow design, prompt logic, API integration, persistence, rate limiting, job handling, testing, and product iteration.

Stack: TypeScript, Next.js, React, Gemini, fal.ai, and VPS deployment

Disclosure: the source code and live demo are not currently public; this is a high-level project summary rather than a public verification claim.

• oss-readiness-checker — a CLI that evaluates repository readiness signals such as CI, documentation, contribution templates, security policy, and release practices.
• codex-skill-radar — a GitHub research workflow that tracks growing Codex skill and plugin repositories and produces Markdown reports and JSON snapshots.
• github-visualizer — a FastAPI, React, and Three.js experiment for turning public GitHub contribution data into a visual builder profile.

• Raftersecurity/rafter-cli#153 added rafter agent status --json across the Node and Python CLIs, including tests and shared CLI documentation.
• Raftersecurity/rafter-cli#159 added HashiCorp Vault token detection across the Node and Python scanners, including true-positive and short-token false-positive coverage.

• Application development: TypeScript, JavaScript, Next.js, React
• AI integration: prompt and Agent workflows, model APIs, asynchronous jobs
• Backend and data: API design, Node.js, Python/FastAPI prototypes, persistence and rate-limiting patterns
• Delivery and evidence: Git, GitHub Actions, tests, deterministic fixtures, validation scripts, documentation, and VPS deployment
• Product work: problem framing, workflow design, rapid prototyping, client communication, and iterative delivery

Problem framing → workflow design → prototype → integrate → test → iterate

I care about evidence over labels: clear ownership, reproducible results, honest capability boundaries, and documentation that another person or agent can continue from.

I am strengthening my portfolio around production-minded AI applications, evaluation, reliability, and user-facing product delivery.