DentaCoPilot: An LLM-Augmented Next-Procedure Recommender for General Dentistry, Designed for Dentist Augmentation

Background. Commercial dental artificial intelligence in 2026 is overwhelmingly diagnostic: caries, calculus, periapical, and bone-level detection on radiographs. The clinically harder question that follows every diagnosis-given a patient's chart and most recent procedure, what should the dentist do next-remains unsolved at general-dentistry scale. The closest published system, MultiTP (Chen et al., 2024), is a CNN-RNN restricted to partial-edentulism cases and provides neither calibrated uncertainty, structured rationale, nor an evaluation that treats the model as decision support instead of an autonomous classifier. Methods. We introduce DentaCoPilot, a recommender that, given a structured chart, returns (i) a calibrated top-K probability distribution over Current Dental Terminology (CDT) codes for the next procedure,(ii) a verbalised confidence label, (iii) an explicit abstain flag when context is insufficient, and (iv) a chart-grounded rationale. We compare four classical baselines (frequency bigram, TF-IDF + logistic regression, XGBoost, MultiTP-style CNN-RNN) and six large-language-model (LLM) variants (Claude Haiku, Sonnet + chain-of-thought, Sonnet + retrieval, Opus + chain-of-thought, Sonnet + classical prior, Opus + classical prior) on a synthetic chart corpus of 500 patients (1,284 test examples). All LLM inference is routed through the local Anthropic Claude Code CLI; every call is logged for full audit. Results. On apples-to-apples evaluation, classical baselines reach 0.567 top-1 / 0.967 top-5; pure LLM variants trail at 0.267-0.467 top-1. Prompt-conditioning a Sonnet LLM on the classical baseline's top-10 candidates (M5) closes the gap: top-5 rises from 0.733 (pure Sonnet + chain-of-thought) to 0.933, matching classical baselines, while preserving rationale and abstention. Increasing the LLM backbone from Sonnet to Opus does not improve accuracy with or without priming. Calibration via temperature scaling and coverage-risk analysis is reported for the baselines. Conclusion. Prompt-conditioning a small LLM on a classical baseline's top-K is the most cost-effective LLM design we tested for next-procedure recommendation, and the design preserves the augmentation features that distinguish the system from an autonomous classifier. A pre-registered clinician-in-the-loop evaluation at the KLE Vishwanath Katti Institute of Dental Sciences (Belgaum, India) and a real-data evaluation on the multi-institutional BigMouth dental data repository are the next stage of work.