Generative AI
LLM-powered applications, RAG pipelines, AI chatbots, and intelligent automation tools built with any language model API or open-source model.
All
EvidenceLens: A Self-Hosted Biomedical Search Engine with Hybrid Ranking and Conflict-of-Interest Transparency
EvidenceLens unifies 20+ fragmented medical literature sources into a single hybrid-ranked interface, surfaces author conflict-of-interest badges from public CMS Open Payments data, and runs answer synthesis entirely on the user's own inference key — zero recurring backend cost.
STORM DAT: Automating Government Document Compliance So Analysts Can Focus on What Matters
A web-based application for automating government document compliance, reducing manual review time and improving accuracy.
Mindfulness Coach: Building a Fully Offline, On-Device AI Coaching App with React Native and Google MediaPipe
A deep dive into the architecture and engineering of a privacy-first mobile mindfulness coach that runs entirely on-device using React Native and Google MediaPipe's on-device LLM capabilities.
ComfyUI Workflow Iterator: Engineering Systematic A/B Testing for Generative AI Pipelines
A production-grade Python extension for ComfyUI that transforms ad-hoc image generation into a disciplined, reproducible experimentation platform.
Splitting Atoms in a Word Document: Surgical Run Manipulation and Real-Time Audio Normalization
A deep dive into the algorithms that power STORM DAT's document annotation and audio normalization engines, revealing how to transform complex data structures in place without corruption.
Automating AI Agent Diagnostics with n8n on TrueNAS Scale
A deep-dive tutorial demonstrating how to deploy n8n—a powerful, self-hosted workflow automation tool—to automatically monitor and alert on AI agent failures within your unified infrastructure.