I design, build, and scale enterprise SaaS, from agentic AI and API platforms to Azure architecture and Microsoft 365. A decade of turning messy, regulated problems into secure systems that ship.
Not model training or research. The engineering that makes AI useful in production: MCP servers, model configuration, retrieval, and agent orchestration. The model is maybe 20% of the job; the system around it is the other 80%. That's the 80% I do.
I generate and ship Model Context Protocol servers that expose existing systems as safe, typed tools, like the IMS MCP I built to bring AI tooling to parity with a core insurance platform's API surface.
Multi-provider setups across Claude, OpenAI, Gemini, and local Ollama, with fallback chains and per-task selection tuned for cost, latency, and reliability instead of one model for everything.
Designing multi-step agent workflows: planning, tool calls, and orchestration, with the guardrails and observability that make them dependable in production. The thinking behind FleetRun.
Retrieval, vector memory, and document intelligence embedded where teams already work, from in-browser vector memory to NLP chatbots and Microsoft 365 document automation.
Eleven custom Model Context Protocol servers give my agents typed, governed access to the tools a real software business runs on. The models run on hardware I own and route per task, so cost and latency stay under control.
AI lesson planning for K-12. Plans, worksheets with answer keys, and differentiated ELL/IEP versions from one prompt, aligned to all 50 states plus Common Core & NGSS.
Bible study & daily devotionals. A cross-platform web + mobile experience (Next.js 16 + Expo) for faith communities to study, reflect, and stay consistent.
Run entire agent fleets as one team. Assign roles, delegate tasks, and watch Claude-powered agents collaborate in real time through MCP, with BullMQ workers and cron jobs on infrastructure I own.
A quieter way to fall asleep. Sleep stories and seamless soundscapes narrated in soft, real voices, in a beautifully crafted React Native app built to be drifted off to.
When I'm not shipping product, I'm building at the edges: local AI, voice interfaces, even an OS from scratch. 2,156 contributions in the last year across 63 repos.
A browser-local recreation of "Her": speech-to-speech LLM with in-browser vector memory. ~2GB of models, zero server, fully private.
A voice assistant with 1940s British charm. Wake-word, Silero VAD, Whisper STT, and a plugin skills system: a voice layer over Claude CLI.
A from-scratch Unix-like OS: 25k+ lines, custom kernel, TCP/IP stack, VFS, and a macOS-style GUI. Runs ARM64 & x86_64, boots Doom.
A retro AI terminal inspired by Alien: CRT aesthetics, 7 themes, multi-provider (Ollama / OpenAI / Gemini / Claude) with a sci-fi knowledge DB.
A multi-source live stream aggregator that brings all your favorite streams into one unified place. Built with Next.js.
FleetRun, Kovu, NativeBlox, brain, MCP servers & more. Explore them all →
2014 → now · enterprise SaaS across healthcare, finance, legal & insurtech
Building agentic AI and the API platform behind a modern insurance stack, including IMS MCP servers that bring AI tooling to parity with the core platform's APIs.
My product studio. A solo founder shipping AI-powered tools for teachers, faith communities, and beyond: TeachStack, FaithWise, FleetRun, and DreamTide.
Leading engineering and technology strategy as co-founder.
Azure and Power Automate platform work, plus Microsoft 365 / SharePoint consulting.
Modernized legacy healthcare systems into microservices, improving uptime and deployment speed by ~40%. Built SPFx solutions across Azure and REST APIs.
Where it started: full-stack product engineering on PHP & SQL for a camp management platform.
Senior software engineer, AI specialist, and Microsoft 365 consultant with 10+ years designing, building, and scaling enterprise SaaS across healthcare, finance, and legal tech.
I specialize in full-stack development (React, Node.js), cloud architecture on Azure, and custom SharePoint SaaS for the legal industry, streamlining case management, document automation, and compliance.
I'm passionate about applied AI, from NLP-driven chatbots to AI-powered document intelligence inside Microsoft 365. Alongside delivery, I love mentoring engineers and turning complex regulatory requirements into secure, scalable systems.
colleagues & leaders I've worked with
Andrew is a talented developer with strong proficiency in client-side development. He showed great initiative diving into AI-based coding, quickly grasping complex concepts and applying them effectively. A dedicated and skilled engineer who would be a valuable addition to any team.
Andrew pairs deep technical range with a rare ability to translate messy business requirements into clean, shippable solutions. He's pragmatic, fast, and genuinely a pleasure to work alongside. He is the kind of engineer who makes the whole team better.
I worked alongside Andrew at CampSite, where he consistently shipped high-quality full-stack work and raised the bar for the product. He combines strong engineering instincts with real ownership. Exactly the kind of builder you want on a team scaling a SaaS platform.
Andrew brings real depth in AI and platform engineering to Balance Partners. He moves fast, thinks in systems, and turns ambitious ideas into reliable software. A genuine asset to any technical organization.