Iberdrola enhances IT operations using Amazon Bedrock AgentCore

2026-02-10 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Cloud Computing & IT Infrastructure, Software Development & Engineering · Depth: Advanced, long

Summary

Iberdrola, a major utility company, has transformed its IT operations in ServiceNow by implementing AI agents built on Amazon Bedrock AgentCore. This solution optimizes change request validation, enriches incident management with contextual intelligence, and simplifies change model selection using conversational AI. The architecture features a layered design with Agentic AI resources, an Inference layer for LLM access, and a Data layer for operational information. Key components of Amazon Bedrock AgentCore, such as AgentCore Runtime, Memory, Gateway, Identity, and Observability, provide serverless compute, session isolation, standardized tool integration, authentication, and monitoring. This approach has significantly reduced processing times, enhanced data quality, and accelerated ticket resolution across Iberdrola's departments, demonstrating a scalable and secure enterprise AI deployment.

Key takeaway

For CTOs or VPs of Engineering evaluating AI agent deployments for IT operations, Iberdrola's success with Amazon Bedrock AgentCore offers a compelling blueprint. Your teams can achieve significant productivity gains and improved data quality in areas like change and incident management by adopting a managed, serverless agent runtime. This approach minimizes infrastructure complexity and accelerates the delivery of production-grade AI agents, allowing your engineers to focus on agent logic rather than underlying infrastructure.

Key insights

AI agents on Amazon Bedrock AgentCore streamline IT operations, enhancing change and incident management.

Principles

• Layered architecture separates operational concerns.
• Managed primitives accelerate enterprise AI deployment.
• Contextual continuity is crucial for multi-step workflows.

Method

Iberdrola uses a layered architecture with ServiceNow as input, a MicroGateway for routing, and a data layer for ETL. Agents are deployed via AgentCore Runtime, leveraging LangGraph for orchestration and pgvector for semantic search.

In practice

• Use LangGraph for agent orchestration.
• Implement pgvector for semantic search in databases.
• Configure explicit logging to Langfuse for monitoring.

Topics

• Amazon Bedrock AgentCore
• Agentic AI
• IT Operations Automation
• Large Language Models
• Multi-Agent Systems

Code references

• pgvector/pgvector

Best for: CTO, VP of Engineering/Data, Director of AI/ML, MLOps Engineer, AI Engineer, AI Architect

Related on AIssential

• Powering agentic AI sales strategy with Amazon Bedrock AgentCore — Orchestrating specialized AI agents with a unified interface significantly reduces cognitive load and improves operational efficiency.
• AWS Bedrock Agents: The Beginner’s Guide — AWS Bedrock Agents provide a managed platform for building and deploying AI agents with integrated orchestration and security.
• Build an AI-Powered Equipment Repair Assistant Using Amazon Bedrock AgentCore — Amazon Bedrock AgentCore enables building RAG-powered AI assistants for complex equipment diagnostics and repair.
• Build and Run Your Own AI Agent in the Cloud — AgentCore provides managed AWS services for deploying and operating framework-agnostic AI agents, complementing agent frameworks like Strands.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.