ZORO: Active Rules for Reliable Vibe Coding

2026-04-16

AI Summary

Existing rule specifications in vibe coding are passive, making them difficult to trace, verify, or iteratively refine. This work proposes ZORO—an interactive interface deeply integrated with coding agents—that anchors rules throughout the entire coding workflow. ZORO injects rules during the planning phase, requires agents to provide verifiable evidence of rule compliance during implementation, and enables users to deliver in-situ feedback for continuous rule-set refinement. By transforming static rules into an active control mechanism, ZORO achieves unprecedented verifiability, intervenability, and evolvability of rules, significantly enhancing human-AI alignment. Experimental results demonstrate that ZORO leads agents to adhere more rigorously to prescribed rules, while user studies confirm that developers adjust their behavioral patterns and cognitive strategies once rules are made explicit.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Human-Robot Interaction
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

Rules files (e.g., AGENTS.md, CLAUDE.md) are the primary mechanism for human-agent alignment when developers vibe code. However, they remain passive: it is not immediately apparent when rules are being used or followed, or how to improve them. To transform rules from passive text into active controls, we introduce ZORO, an interactive interface that integrates directly with a coding agent and anchors rules to every step of the coding process. After an agent generates an initial plan, ZORO enriches the plan with rules, enforces the rules during implementation by requiring the agent prove that each rule was followed, and allows users to provide in-situ feedback when they are unsatisfied with a rule application to evolve the ruleset. A technical evaluation shows that coding agents follow rules more with ZORO than without. A user study demonstrates a change in people's behavior and cognitive strategies when rules are at the forefront of vibe coding. We discuss how making rules active in agentic systems unlocks broader opportunities for human-agent alignment in coding settings and beyond.

Problem

• vibe coding
• human-agent alignment
• rules
• coding agents
• passive rules

Innovation

• active rules
• human-agent alignment
• vibe coding
• interactive interface
• rule enforcement