Patterns

The reusable building blocks distilled from the corpus. Each one is a mechanism stated as takes X → produces Y, with the real sources it was found in. These are the ingredients you compose into an Enhancement.

SortNewest Most corroborated

Effectall read write external call transform

Typeall AI / ML data application interface infrastructure security operations other

Corroborationany 2+ sources

Showing 1–5 of 5 patterns

VAD-guided audio chunking

AI / MLtransform

AudioStream -> List<AudioChunk>

Segment an audio stream into batched chunks based on voice activity boundaries to enable parallel ASR processing and reduce silence-induced hallucinations.

Found in 2 sources

cache-aware streaming speech recognition

AI / MLtransform

AudioChunk, AudioContextState -> TextChunk, AudioContextState

Transcribe audio stream chunks sequentially while maintaining a rolling context cache to avoid recomputing historical sequence representations.

Patterns

VAD-guided audio chunking

cache-aware streaming speech recognition

context-compaction

action-conditioned-world-prediction

type-hint schema extraction