Back to corpus
research noteexperiment writeup candidatescore 32

Voice Ordering System - Technical Documentation

The BrewsWithBeats voice ordering system uses a hybrid architecture combining: - **iOS 26 SpeechAnalyzer** for on-device transcription - **Semantic embeddings** for accurate menu matching - **Confidence-based clarification** for reliable order capture - **YAML constraints** for menu rule validation

Open full HTMLDownload HTMLCorpus JSONPaper schema

Full HTML reader

Read the full artifact

Open in new tab

Extracted abstract or opening context

The BrewsWithBeats voice ordering system uses a hybrid architecture combining: - **iOS 26 SpeechAnalyzer** for on-device transcription - **Semantic embeddings** for accurate menu matching - **Confidence-based clarification** for reliable order capture - **YAML constraints** for menu rule validation **Location:** `BWBCore/Sources/BWBCore/Voice/Embeddings/MenuEmbeddingService.swift` **Purpose:** Find menu items using semantic similarity instead of exact text matching. **How it works:** 1. Converts menu items to vector embeddings (300-dimensional) 2. Converts user's speech to a vector 3. Finds closest matches using cosine similarity 4. Combines with fuzzy matching for robustness **Configuration:** - Hybrid weight: 60% semantic + 40% fuzzy - Uses Apple's NLEmbedding (built-in, no external dependencies)

Promotion decision

What has to happen next

Attach run IDs, datasets, metrics, and reproduction commands.

Why this is not always a full paper yet

Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.