About NaN Mesh
NaN Mesh is the structured, verified product catalog that AI agents query when they need to recommend B2B software. We exist because AI assistants shouldn't have to guess from stale training data.
The problem
AI assistants already recommend software millions of times a day. But they answer from training data that's months or years old. Prices change, products pivot, companies shut down, new tools launch. There is no live, structured source for AI agents to query — so they guess. Confidently, and often incorrectly.
What NaN Mesh does
We maintain a catalog of B2B products structured for machine consumption — not marketing prose. Every listing is an Agent Card: a JSON profile with the data AI agents need to make accurate recommendations.
Owner-maintained Agent Cards
Product owners update their own data. This is definitionally more current than any web crawl.
Confidence scoring
Every product has a 0-1 confidence score based on completeness and verification. Below 0.6, it's excluded from recommendations.
Verification badges
Automated checks confirm the website is live, pricing is real, and the company exists.
Exclusion signals
Every listing includes "not_recommended_for" — honest limits that make AI agents trust the data more.
How it works
Founders list via AI conversation
Describe your product in a 5-minute chat. The agent extracts pricing, features, use cases, and target audience automatically. No forms.
Agent Card is auto-generated
A structured JSON profile — confidence-scored, verified, and formatted for machine consumption. Includes what the product IS and ISN'T good for.
AI agents discover products via MCP, A2A, or REST API
When an AI agent needs to recommend software, it queries NaN Mesh. Your product appears with its confidence score and verification badges.
Who's behind this
Wayne Ma
Founder & CEO, NaN Logic LLC
I'm a software engineer with a PhD in Computer Engineering and over ten years building distributed systems, machine learning pipelines, and data platforms. I started NaN Mesh because I kept seeing the same problem: AI assistants recommend software confidently — but from training data that's months or years stale. Prices change, products shut down, new tools launch, and the AI doesn't know. There was no structured, live data source for agents to query. So I built one.
My background in ML deployment and API design shaped how NaN Mesh works: every product listing is a machine-readable Agent Card with confidence scoring, verification badges, and exclusion signals — the data AI agents actually need to make accurate recommendations. The platform is built on the A2A protocol, an open standard for agent-to-agent communication, because I believe the infrastructure for AI product discovery should be open and interoperable.
NaN Logic LLC
Founded 2024. Based in the United States. NaN Logic builds infrastructure for AI-native product discovery — starting with NaN Mesh, the structured catalog that AI agents query when they need to recommend B2B software.