Hi, I'm Naomi

I build AI and I still find it magical. I love the moment an idea clicks into something that can reason, help and surprise you.

For me, great AI isn't about being clever. It's about being genuinely useful to the people who trust it.

Follow me on 𝕚𝕟

✦

Prompt: "reason step by step"

text-to-image

Explore ↓

AI Work

Turning research into products people actually use.

Faves

Picked things I'm genuinely into.

Writing

Thoughts on AI, leadership, and where this is all going.

My Stack

The tools I reach for every day.

Latest Articles ↓

These are my notes and articles on design, development and life thinking.

Jul 27, 2026 · Large Language Models

Why LLMs Struggle With Tables

An interactive essay on tabular and relational foundation models, why token streams lose table structure, and how TabFM and KumoRFM read it natively.

The hallucination tax: enterprise AI outputs requiring human review, correction and verification without a governance layer

Jul 22, 2026 · Enterprise AI

The Hallucination Tax: When Enterprise AI Picks Speed Before Governance

Enterprise AI's hidden cost is the human labour of verifying and correcting AI output. The fix is a semantic and governance layer that gives models real context.

CORAL multi-agent framework where AI agents independently explore, share discoveries through long-term memory and co-evolve

Jul 18, 2026 · Multi-Agent Systems

CORAL and AI Agents That Co-Evolve

Most multi-agent systems are fixed-role teams. CORAL lets agents explore, learn and share through memory so they co-evolve, beating evolutionary methods 3-10x.

View All Articles

Kind words ↓

Mentees I've worked with on ADPList, a few of the notes that made my week.

Naomi Nour - building AI that's genuinely useful.