I'm a computer science student at Arizona State University and the founder of Thesis, an operating layer for early companies.
I build the product myself, from the workspace to the agent that reads across issues, docs, and inbox. The work is the same record: planning, writing, and the agent that sits on top of it.
I also research neural network compression through ASU's FURI program. Computer science at Arizona State University, 2025–2029. Diploma, VPMP Polytechnic.
TypeScript · Next.js · React · Python · PyTorch · Node.js · Firebase
Planning, writing, review, and an AI agent in one place.
thesisapp.coCompany building is at an inflection point. Artificial intelligence is fundamentally reshaping how products are planned, built, and shipped, and how small teams stay aligned while they do it.
AI increases what a founding team can create, but it also raises the bar for clarity and coordination. At Thesis, we are building the tools for this era: a purpose-built system where people and agents operate together in one shared, structured environment.
Thesis unifies issues, projects, initiatives, inbox, documentation, and an AI agent that reads across the company. Instead of stitching together five products and losing context in the gaps, teams get one operating layer: fast, keyboard-first, and designed for craft.
Thesis is built by Atlas. We started from a simple belief: early companies deserve software that matches how they actually work. Tight loops, high ambition, and zero patience for tools that get in the way. We care deeply about speed, taste, and the quiet details that make software feel inevitable.
We're a small team focused on the long game: making Thesis the default operating layer for the next generation of companies. If that resonates, we'd love to build with you.
Designed and deployed a multi-tenant file management platform using Next.js and MongoDB. Supports concurrent users with JWT role-based authentication and real-time sync. Optimized caching strategies for 35% faster retrieval.
Next.js · MongoDB · JWT · Node.js
Cloud Security / AI
Designing an AI-powered IAM decision engine analyzing 10+ behavioral risk signals per authentication attempt. Built a supervised ML model trained on simulated datasets of 5,000+ login events, targeting <200ms latency and 85% anomaly detection accuracy.
AWS · Machine Learning · Python
Mobile App Development
Developed and deployed an Android application integrating Java and Firebase for real-time data sync across 1,000+ tasks and notes. Enhanced UI performance and optimized database queries to significantly improve user experience.
Java · Android · Firebase · UI/UX
I read everything. The fastest way to reach me is email.