Introduction
Geltre is Nichols AI's flagship model and the first Orienting Model. It selects the task-relevant evidence from large, noisy state before a decision model or LLM sees it.
state + task + evidence budget → exact source references
Geltre does not generate prose, make the downstream business decision, or invent missing facts. Its job is narrower: determine which supplied evidence deserves attention while preserving exact provenance.
Why orientation?
AI applications often ask one expensive model to locate evidence, decide what the evidence means, and reason or generate an answer. Geltre separates the first job so downstream compute can operate on a smaller, more relevant state.
Geltre asks: what matters?
A bounded model such as JEV chooses.
An LLM reasons when needed.
Deterministic code executes.
What Geltre returns
{
"evidence": [
{"ref": "log:2", "relevance": 0.992}
],
"model": "geltre-serviceops-linear-v03"
}
Every returned ref must exist in the state supplied to Geltre. Unknown references are rejected.
Developer preview
Geltre is proprietary Nichols AI model infrastructure. The hosted developer preview is initially scoped to the validated ServiceOps route while broader cross-domain robustness remains under evaluation.