Abstract
An artificial intelligence (AI)-driven self-adapting remediation system is proposed herein. The proposed system can facilitate iterative, validated remediation with real-time state adaptation, as well as learning-enhanced prescription ranking under multi-dimensional constraints and intent-centric, standards-based multi-modal translation. Thus, the proposed system represents a fundamental advancement in network remediation technology by combining AI-driven intelligence with deterministic safety validation through the Model Context Protocol (MCP) framework. The integration of Large Language Model (LLM)-based command generation, risk-aware planning, adaptive configuration intelligence, and MCP-based validation creates a novel solution that addresses the critical limitations of traditional network remediation approaches while providing robust safety guarantees through established external validation tools.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Bahl, Rohit; Mistry, Mrulay Sureshbhai; Burman, Ronnit Roy; Lavana, Hemang; and C White, David, "INTELLIGENT NETWORK REMEDIATION SYSTEM WITH ADAPTIVE PRESCRIPTIONS", Technical Disclosure Commons, (May 20, 2026)
https://www.tdcommons.org/dpubs_series/10189