GLiDE Capabilities

GLiDE evaluates caller-defined outcomes instead of generating prose. This page summarizes its technical behavior and boundaries. For a first request, start with Call GLiDE.

​

Decision capabilities

• Evaluate a string, object, or array supplied as shared state.
• Ask one or more named questions against that state.
• Use Noul for yes/no probabilities.
• Use Choice for one unordered option from a caller-defined set.
• Use Score for one level on an ordered rubric.
• Receive probabilities and confidence for every answer.
• Reason over arithmetic, code traces, dates, policies, exceptions, and related facts in the supplied state.

GLiDE first makes a fast assessment and spends additional reasoning on uncertain decisions. Each question is evaluated independently against the same state.

​

Confidence and uncertainty

The answer tells you what GLiDE concluded. confidence tells you how clearly the leading outcome separated from the alternatives. A low-confidence answer is not necessarily incorrect. It means probability mass is spread across outcomes. Tune action and fallback thresholds on representative data rather than assuming a universal cutoff.

​

Limits

• Each rendered prompt—state plus one question—must fit within 40,000 tokens.
• Choice requires 2 to 255 options.
• Score accepts up to 255 levels.
• Every question is single-label. There is no multi-label primitive.
• One request evaluates one shared state; multiple questions belong under questions.
• usage.input_tokens sums internal passes across questions and can exceed 40,000 even when each rendered prompt fits.

​

Unsupported request shapes

• /v1/systemone does not stream.
• It does not accept a batch of independent states.
• It does not currently accept fine-tuned deployment IDs.
• Extra top-level request fields are rejected.
• Choice cannot contain only one option.

​

Evaluation

On Decision Index 0.2.1, GLiDE scored 64.81 compared with Jev’s published 57.91, leading all five evaluation areas and 31 of 38 benchmarks.