About Nessie

The origin

Nessie started when Anna hit the one-million-token limit in a Gemini conversation she'd been using as her primary thinking environment. Months of research and ideas became inaccessible overnight. The realization: your most valuable thinking happens in AI conversations, but it has nowhere to go.

We've rebuilt Nessie three times since then. Each iteration got one layer deeper into the real problem: your most important work is already happening across ChatGPT, Claude, Gemini, and every other AI tool you use. It just has no durable structure and no way for your agents to use it when they need it.

What we believe

• The trace is a new first-class data asset. Every AI conversation and agent run leaves a record of how the work actually happened - what was tried, what got thrown out, what broke, and why the call went the way it did, sitting right next to what it produced. That record used to evaporate. Now it is captured as a byproduct of the work itself, and it is the most honest account of how a company actually thinks.
• A company that mines its own record compounds. When your team can ask what it already decided and get the answer with the reasoning still attached, work stops starting from zero. The system gets a little sharper every time it is used, because every question asked and every answer corrected is one more thing it knows.
• Turning traces into usable context is our job. Raw traces are messy; the value is in the context distilled from them - kept structured, current, and queryable by the agents and tools you already use. You shouldn't have to maintain that context yourself. Connect your accounts, and the system handles the rest.
• Your traces stay yours. We keep them private to your team, never shared across organizations, and we don't train on your data. The models you rely on will keep changing; the record of how your company thinks is the layer they all plug into, and it should stay legible, portable, and yours.

The team

Anna Y. Zhang

CEO & Co-Founder

Yale '24. Previously built ML-powered features for billions of customers at Amazon's recommendation service, leading an experiment that demonstrated $200M/year of revenue impact. Has been obsessed with augmenting human cognition since high school, when she did neuroscience research at The Rockefeller University. Started Nessie after hitting the 1M-token limit in Gemini and losing months of thinking overnight.

Tiger Wang

CTO & Co-Founder

Yale '24. Previously engineered planetary-scale authentication systems at Amazon handling 40 billion requests per day, promoted in a Tier-0 org in record time. Shipped an Android app with 70k+ users at age 13. Researched Linux kernel security at Yale.

Backed by

…and a few angels.

Get in touch

We'd love to hear from you. Reach us at founders@nessielabs.com, or book a call with a founder: