> ## Documentation Index > Fetch the complete documentation index at: https://infercrane.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Inference decisions > Deterministic SLO policies, evidence-based recommendations, and explicit unknowns. # Inference decisions InferCrane compares persisted, reproducible benchmark evidence against an explicit deployment SLO policy. It does not ask an LLM to choose infrastructure, mutate a deployment automatically, or invent missing price and capacity measurements. ## Define the acceptance envelope Set at least one threshold. Omitted metrics are unconstrained; configured metrics fail closed when the corresponding benchmark signal is missing. ```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}} infercrane slo set qwen-prod \ --ttft-p95 250 \ --latency-p95 1200 \ --error-rate 0.01 \ --output-tokens-second 30 ``` Hourly cost is accepted only when benchmark cost metadata includes an authoritative source and observation timestamp. InferCrane does not convert unavailable pricing into zero. ```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}} infercrane slo get qwen-prod --output json infercrane slo delete qwen-prod ``` ## Evaluate persisted evidence Collect comparable AIPerf measurements, then request a recommendation: ```bash theme={"theme":{"light":"github-light-default","dark":"vesper"}} infercrane benchmark qwen-prod infercrane recommend qwen-prod infercrane recommend qwen-prod --history --output json ``` Every evaluation persists its status, algorithm version, canonical input digest, immutable benchmark provenance, exact compatibility state, selected and rejected candidates, violated constraints, missing evidence, and current bounded capacity disclosure where available. Candidates must reference the active immutable model artifact and the same canonical benchmark workload as the newest observation. InferCrane will not rank unlike models, request shapes, or concurrency profiles as though they were interchangeable performance samples. A recommendation is advisory. It never provisions resources, changes the DeploymentSpec, or substitutes hardware. Apply a selected configuration explicitly after reviewing its evidence. ## Unknown is a useful answer InferCrane returns `unknown` when a configured metric, qualification record, or required cost signal is unavailable. Capacity is disclosed as available, constrained, unavailable, or unknown with an expiry. Stale evidence becomes unknown; it is never retained as live stock. The same policy and canonical evidence snapshot reproduce the same output. This supports audit and CI review without turning the recommendation into an opaque optimizer.