Context-Augmented Code Generation: How Product Context Improves AI Coding Agent Decision Compliance by 49%

TL;DR

This paper introduces a benchmark for measuring AI coding agents' decision compliance with product decisions and shows that augmenting agents with product-context retrieval significantly improves compliance from 46% to 95%.

Contribution

The paper presents a new benchmark for decision compliance and demonstrates that integrating product-context retrieval greatly enhances AI coding agents' adherence to product decisions.

Findings

Augmented AI agents achieve 95% decision compliance.

Baseline agents achieve 46% decision compliance.

Product-context retrieval is crucial for decision adherence.

Abstract

AI coding agents powered by large language models can read codebases and produce functional code, but they routinely violate team-specific product decisions that are invisible in the source code alone. We introduce a controlled benchmark measuring decision compliance, the rate at which an AI coding agent follows established product, design, and engineering decisions, across 8 realistic software engineering tasks containing 41 weighted decision points. We compare a baseline configuration (Claude Code with codebase access only) against an augmented configuration that adds Brief, a product-context retrieval system providing spec generation, mid-build consultation, and retrieval of recorded decisions, persona pain points, customer signals, and competitive intelligence. On identical prompts and the same repository, the augmented configuration achieves 95% decision compliance versus 46% for the baseline, a 49 percentage point improvement. Per-decision analysis reveals that the baseline achieves 100% compliance on decisions visible in the codebase and 0-33% on decisions requiring product context, suggesting that product-context retrieval is a key driver of the improvement. We release the benchmark repository, all 16 pull requests, and scoring harness for independent reproduction.