A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development
This work addresses the problem of unreliable agentic AI for WebGIS development by reframing LLM limitations as structural governance problems, demonstrating improved code quality and maintainability.
Agentic AI frequently fails in WebGIS development due to five LLM limitations. This paper proposes a dual-helix governance framework and implements it as a 3-track architecture (Knowledge, Behavior, Skills) to stabilize execution. Applying this to a WebGIS tool, the governed agent refactored a 2,265-line codebase, achieving a 51% reduction in cyclomatic complexity and a 7-point increase in maintainability index.
WebGIS development requires rigor, yet agentic AI frequently fails due to five large language model (LLM) limitations: context constraints, cross-session forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these challenges as structural governance problems that model capacity alone cannot resolve. We implement the framework as a 3-track architecture (Knowledge, Behavior, Skills) that uses a knowledge graph substrate to stabilize execution by externalizing domain facts and enforcing executable protocols, complemented by a self-learning cycle for autonomous knowledge growth. Applying this to the FutureShorelines WebGIS tool, a governed agent refactored a 2,265-line monolithic codebase into modular ES6 components. Results demonstrated a 51\% reduction in cyclomatic complexity and a 7-point increase in maintainability index. A comparative experiment against a zero-shot LLM confirms that externalized governance, not just model capability, drives operational reliability in geospatial engineering. This approach is implemented in the open-source AgentLoom governance toolkit.