About
An engineer building AI that makes everyday work easier.
I’m Sezer Yavuz. I build the workspace and runtime that let teams put AI to work on the tools they already use, plus the developer tools around it. The longer story is below.
Quick facts
- Based in
- San Francisco, CA
- Currently
- Founder, ModulexAI
- Previously
- Co-Founder, ThinkBuddy
- Studied
- Industrial Engineering
Story
I grew up in Turkey, studied Industrial Engineering, and pivoted to software early. Two startups in, the through-line is the same: building products that turn AI into engineering substrate people can rely on, not just demos.
What I do
I am a software engineer in San Francisco focused on AI systems. My current company, ModulexAI, is an AI workspace that comes pre-connected to a team's tools: a chat assistant that answers and acts on their data, plus a visual workflow builder with an AI copilot that builds the graph from plain language. The bet is that the bottleneck in AI automation is connection and setup, not the model, so we made connectivity the product. I work across distributed systems, the runtime that executes it all, multi-agent orchestration, and the developer experience around all three.
How I got here
I grew up in Turkey and studied Industrial Engineering at Istanbul Okan University, where I completed the program on a full merit scholarship with a 3.7 GPA and wrote my thesis on rule-based fuzzy systems for anthropometric data. Software was always the actual interest. Early roles at Creative Dock (a Prague-based venture builder) and ERC Barkod (industrial IoT) were where I learned to ship: building React frontends for a banking app, then real-time inventory algorithms over RFID and IoT sensor streams that cut processing time by 40%.
ThinkBuddy
In 2023, I co-founded ThinkBuddy. We built an AI productivity platform that unified 15+ leading AI models behind a voice-first interface. Over two years we grew it from concept to 20,000+ active users and 4,000+ paying subscribers. ThinkBuddy hit #1 on Product Hunt on February 27, 2024. The technical core was a RAG pipeline with an MCP server enabling context-aware multi-source AI responses, and a document intelligence layer that handled OCR, file parsing, and LLM-based extraction across many file formats.
ModulexAI
I started ModulexAI in October 2025. The thesis: most teams stall before AI does any real work, not on the model, but on the setup. Connecting each tool means an account, an API key, and glue code, and one credential per tool is never enough. So I made connectivity the product. ModuleX is an AI workspace that ships pre-connected to 200+ integrations, with ModuleX Key supplying managed credentials for premium tools (billed as credits) and many accounts of the same tool usable at once, so you can run several Gmail accounts through one assistant. It is one engine behind two surfaces: a chat assistant that knows your data and acts on it, and a visual workflow builder where an AI copilot, Composer, builds the graph from plain language. Under the hood it is a runtime that compiles those definitions to executable LangGraph statecharts; the same workflow runs in chat, on the canvas, or as a REST API with TypeScript and Python SDKs, built once and run anywhere.
Work history
- 2025 – Present
Building the AI workspace that comes pre-connected to 200+ tools: a chat assistant that answers and acts on a team's data, plus a visual workflow builder with an AI copilot that builds the graph from plain language. The thesis is that the bottleneck in AI automation is connection and setup, not the model.
- 2023 – 2025
Built and scaled an AI productivity platform from concept to 20,000+ users and 4,000+ paying subscribers, with a #1 Product of the Day on Product Hunt. Unified interface across 15+ AI models with voice-first interaction.
- 2021 – 2023
Software Engineer
ERC Barkod· IstanbulBuilt real-time inventory tracking over RFID and IoT sensor streams, plus the analytics pipeline aggregating live operational metrics across multi-site ERP deployments.
- 2021
Junior Software Engineer
Creative Dock· PragueBuilt React and TypeScript frontends for a digital banking product at a Prague-based venture builder.
Track record
Recognition
- 2026Product Hunt #6 Product of the DayModulexAI
- 2024Product Hunt #1 Product of the DayThinkBuddy
- 2023Generative AI Hackathon — 2nd placeNewsea
- 2021Tilburg University Challenge — 3rd of 80ISOLA
Education
BSc Industrial EngineeringIstanbul Okan University
Frequently asked
Questions, answered.
Who is Sezer Yavuz?
Sezer Yavuz is a software engineer based in San Francisco, California. He is the founder of ModulexAI, an AI workspace that comes pre-connected to a team's tools. Previously, he co-founded ThinkBuddy, an AI productivity platform that scaled to over 20,000 users and reached Product Hunt #1 in February 2024.
What is ModulexAI?
ModulexAI is an AI workspace that comes pre-connected to 200+ integrations. It pairs a chat assistant that answers and acts on your data with a visual workflow builder whose AI copilot, Composer, builds workflows from plain language. ModuleX Key supplies managed credentials for premium tools, and many accounts per integration run at once.
What was ThinkBuddy?
ThinkBuddy was an AI productivity platform that unified 15+ leading AI models behind a voice-first interface. It grew to 20,000+ active users and 4,000+ paying subscribers, and was named Product Hunt's #1 Product of the Day on February 27, 2024. Sezer was a co-founder from February 2023 to October 2025.
Where is Sezer Yavuz based?
Sezer Yavuz is based in San Francisco, California. He works on ModulexAI in a hybrid arrangement between SF and remote.
What is Sezer Yavuz currently working on?
Sezer is building ModulexAI, the AI workspace that comes pre-connected to your tools. The current focus is the ModuleX Key program for managed premium-tool credentials, deepening Composer's natural-language workflow building, and shipping the TypeScript and Python SDKs to early integration partners.
What is Sezer Yavuz's technical background?
Sezer's primary stack is Python, TypeScript, and Rust. His AI engineering work uses LangChain, LangGraph, the Model Context Protocol (MCP), retrieval-augmented generation, and vector search. On infrastructure, he works with PostgreSQL, Redis, pgvector, Docker, Kubernetes, and the major cloud providers.
How can I contact Sezer Yavuz?
The fastest way to reach Sezer is by email at s.ufukyavuz@gmail.com. He is also reachable on X as @sezerufukyavuz, on LinkedIn at linkedin.com/in/ufukyavuzz, and on GitHub at github.com/sezeryavuz.
Reach me
Email is the fastest way to get me. Building something agentic, want a second pair of eyes on architecture, or hiring for something interesting? s.ufukyavuz@gmail.com.