About
We measure what AI tells engineers, and fix what it gets wrong.
Reference Grade began with a question a materials scientist couldn't stop asking: when an engineer asks an AI which material to use, where does the answer come from? We built the instrument to find out, first for real estate with Homiere, and now for the industry we came from.
People
Chris Dimitriou, PhD
Co-founder, Reference Grade · Co-founder & CTO, Homiere
Chris is a materials scientist who spent eight years developing polymers for consumer products at Nike, working alongside the world's leading material suppliers.
At Homiere he built Assay, the engine that measures what AI answer engines say and where they get it, and published controlled research on how those engines choose their sources. Reference Grade brings that instrument back to materials and manufacturing.
Principles
How we work
- Rates, not screenshots. One answer is an anecdote; we report rates across repeated runs.
- Evidence you can audit. Every number links to the answers and sources behind it.
- No manipulation. We make true information easy to cite, and nothing else.
- Claims backed by data. No property value ships without a TDS or test report behind it.
- Your data stays yours. NDAs are standard, and client data isn't used to train models.
Relationship
Reference Grade and Homiere
Same team, same engine, different industries. Homiere serves real estate professionals. Reference Grade serves material suppliers, chemical companies and manufacturers.
Built on Assay
Reference Grade runs on Assay, the AI-answer measurement engine we built and also run for Homiere, our product for real estate. Assay captures AI answers on a recurring schedule and traces their sources. It also verifies crawler activity from both sides: what an engine says it read, and what actually arrived at the server. It is the instrument behind our published research on how answer engines choose their sources.
- Where does a ChatGPT answer come from? Cache, index and live fetch in OpenAI's search stack, measured from both sides.
- When does the model look it up? Parametric knowledge, controlled retrieval and how answer engines arbitrate between them.
Start with evidence
See what AI tells engineers about your materials.
We'll run 25 of your customers' questions across three engines and show you who gets named, which sources get cited, and what's wrong. Free, in five business days.