My Road to i80

The Spark

I love to cook. Not by the book, but with intuition, memory, and whatever ingredients are at hand. Over the years, I have built a rich personal archive: dishes invented on the fly, surprising flavor combinations, and moments of improvisation captured in photos, notes, and conversations.

Then, in January 2023, I encountered ChatGPT. I was blown away by its ability to answer questions and generate ideas. I would ask about cuisines, techniques, or flavor pairings, and the responses were impressive. But when I asked, “How did Alex cook sea bass with miso?”, the reply came through as: “I don’t have access to Alex’s personal cooking history.”

For all their brilliance, large language models (LLMs) did not know my stories. They could not access the unique experiences, preferences, and memories that make me who I am.

The Turning Point

That is when it hit me: what if I could build an AI that feels like an LLM but knows what I know? Not a generic model trained on the internet, but a personal system capturing my cooking stories, thought processes, and unique way of seeing the world.

I imagined an AI that could answer, “What would I have cooked with those ingredients?” or even “How would I have approached that problem?”, not based on generic data, but on my own lived experience.

This led me to the idea of a private knowledge agent: not just a chatbot, but a system that can understand a question, search trusted knowledge, decide how to respond, and stay grounded in the right context.

Beyond Cooking

While building the cooking agent, I thought about a hotel project I had worked on before. The problem was the same: a wealth of internal knowledge (policies, procedures, local expertise, guest preferences) that no general AI could access or understand.

That is when I realized cooking was just the beginning. The same gap exists wherever knowledge lives in people’s own stories, notes, and experience, not on the internet.

From Agents to Apps

In 2026 I rebuilt i80 Agent with AI writing the code. That changed what I could build: Trovel, Retirement Planner, Pickleball Together, and, at Dynasign, QRSign.

Now I am exploring where agents go next, including MCP, a new standard that lets AI assistants like ChatGPT and Claude work directly with your apps, without you having to open them.

Why “i80”

The name comes from Interstate 80, a highway I used to live near in Salt Lake City. Always the same road, sometimes a different destination. That is what this became: one road, many destinations.

A Living Journal

I keep track of the journey here: the projects I build and the notes on what I learn.