Blog - Notes from the team

Short pieces on retrieval, MCP, self-hosting, and the parts of enterprise AI that keep coming up in customer calls.

Frontier models or your own GPUs? What each costs in 2026

Published

Closed frontier models still lead on capability but open-weight models you can run yourself are closing the gap. Here is what each option might cost a large company in November 2026: API tokens, rented GPUs and owned hardware, priced side by side.

Read more

Why a chat UI is the wrong wedge for enterprise AI

Published

Branded ChatGPT clones look like the obvious product, but they're the wrong layer to compete on. The wedge is the knowledge layer underneath, and the open standard that connects it to whatever AI client your team already uses.

Read more

Hybrid retrieval, plainly explained

Published

Dense vectors find things by meaning. Sparse search finds things by exact words. A re-ranker decides which of those candidates actually answer the question. Here is what each step does, and what it costs to skip.

Read more

Want to see Laminae on your own documents?

Based and hosted in

  • Frankfurt
    Frankfurt am Main
    Germany