One forward pass.
Calibrated decisions across every slot.
Turn declarative .json.tmpl schemas into zero-shot Decision Policies that unmask up to 8 choice, boolean, or ordinal score slots simultaneously in ~135–265 ms on a warm GPU—returning exact per-option probabilities and pre-fusion normalized hesitation (raw_normalized_entropy) across Decision Studio, MCP, REST, and Go.
templates/support_triage.json.tmplStop decoding JSON punctuation one token at a time.
Autoregressive models spend sequential forward passes emitting braces, quotes, and field names with uncalibrated verbalized confidence. dgem places masked decision slots directly in the prompt and unmasks all of them in a single forward pass.
Autoregressive JSON Decoding
O(T) Sequential Stepsdgem Single-Pass Slot Denoise
O(1) Step · ~135–265 ms Warm GPUFour primitives, one calibrated decision loop.
Author a declarative .json.tmpl policy, unmask up to 8 slots in one diffusion pass, gate Stage 2 cascades on pre-fusion hesitation, and serve over Studio, MCP, HTTP, or CLI.
{
"schema": {
"instructions": "Triage the customer support ticket.",
"questions": [
{ "id": "department", "type": "choice",
"options": [{"name": "billing"}, {"name": "technical"}, {"name": "account"}] },
{ "id": "sentiment", "type": "score", "levels": ["calm", "frustrated", "furious"] }
],
"samples": {{ default 1 .samples | toJson }}
},
"state": { "ticket": {{ default "No ticket text" .ticket | toJson }} }
}vertexE[r] = 3.84 · p(exact)=0.86E[r] = 3.41 · p(exact)=0.58X-DGem-Backend: vertex_firstsupport_triage.json.tmpl (0.4 ms)/v1/systemone (~155 ms warm GPU)H_raw=0.062 < 0.16 → 200 OKNormalize across K. Always gate before fusing priors.
Raw Shannon entropy (H = -∑ p_i ln p_i) grows with option count ln K: a 2-option boolean gate maxes out at 0.693 nats while a 52-option choice reaches 3.951 nats. dgem normalizes hesitation onto [0, 1] via raw_normalized_entropy = H / ln K and separates Stage 2 cascade gating from empirical prior fusion.
- Scale-free hesitation bands —
< 0.16 Clear(fast-path exit),0.16–0.50 Somewhat unsure, and> 0.50 Very unsureacross anyK. - Pre-fusion cascade gate — try switching the simulator to
alwayswith lowp_top: an un-gated strong prior artificially depresses post-fusion entropy below0.16! dgem gates Stage 2 strictly on pre-fusionraw_normalized_entropyand fuses priors with--prior-gate-mode hesitant(decisionindex.FusePriorWithGateMode). - Wide-option catalogs (
K > 26) — combine--labels az_aa/az_lower(up to 52 options),--bracket-size 20two-stage tournaments, or--shortlist-topk M(decisionindex.PriorLogitsShortlist).
Six production decision patterns, three live code views.
Select any domain below and toggle between its declarative .json.tmpl schema, CLI / REST invocation, and structured JSON receipt.
Author once. Call from Studio, MCP, REST, CLI, or Go.
Click any caller interface or GPU/Metal target below to trace its execution path and copy its launch command.