Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming

TL;DR

This paper presents a lightweight pre-filtering model that uses real-time developer telemetry to predict code suggestion acceptance, significantly improving acceptance rates and reducing unnecessary LLM calls in programming environments.

Contribution

The paper introduces a novel, privacy-preserving pre-filtering approach that enhances LLM-assisted coding by predicting suggestion acceptance using only behavioral signals.

Findings

Acceptance rates nearly doubled from 18.4% to 34.2%.

35% of low-value LLM calls were suppressed.

Behavioral telemetry alone effectively improves system efficiency.

Abstract

Large Language Models (LLMs) are increasingly integrated into code editors to provide AI-powered code suggestions. Yet many of these suggestions are ignored, resulting in wasted computation, increased latency, and unnecessary interruptions. We introduce a lightweight pre-filtering model that predicts the likelihood of suggestion acceptance before invoking the LLM, using only real-time developer telemetry such as typing speed, file navigation, and editing activity. Deployed in a production-grade Visual Studio Code plugin over four months of naturalistic use, our approach nearly doubled acceptance rates (18.4% -> 34.2%) while suppressing 35% of low-value LLM calls. These findings demonstrate that behavioral signals alone can meaningfully improve both user experience and system efficiency in LLM-assisted programming, highlighting the value of timing-aware, privacy-preserving adaptation mechanisms. The filter operates solely on pre-invocation editor telemetry and never inspects code or prompts.