A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development

TL;DR

A dual-helix governance framework is proposed reframing challenges as structural governance problems that model capacity alone cannot resolve, and it is confirmed that externalized governance, not just model capability, drives operational reliability in geospatial engineering.

Abstract

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.

Figures (10)

• Figure 1: The Dual-Helix Governance Framework for Reliable Agentic GeoAI. The framework stabilizes execution through two orthogonal axes: persistent Knowledge Externalization and enforceable Behavioral Enforcement connected via validated Skills.
• Figure 2: The 3-track architecture operationalizing the dual-helix approach. Track 1 (Knowledge) and Track 2 (Behaviors) represent the governance axes, while Track 3 (Skills) provides stabilized execution patterns.
• Figure 3: Role separation as implementation mechanism. The Agent Builder maintains system structure while the Domain Expert executes project tasks. Explicit role switches prevent context contamination.
• Figure 4: The conceptual self-learning mechanism. As the agent performs tasks, it discovers, structures, links, validates, and persists new project context as auditable graph nodes. Figure \ref{['fig:selflearning-experiment']} illustrates how this cycle is operationalized in the experimental workflow.
• Figure 5: The FutureShorelines decision support tool showing a typical use-case for planning living shoreline installations parkinson_future_2024