Agentic AI

2026-05-13 · Source: Artificial Intelligence (AI) articles · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Internet of Things (IoT) & Connected Devices · Depth: Intermediate, medium

Summary

Intel and AIREV evaluated the OnDemand Agentic AI platform on Intel® Core™ Ultra Series 3 processors, demonstrating a shift from reactive to autonomous critical infrastructure operations. The platform, tested on a Dell XPS 16 with an Intel® Core™ Ultra X7 358H (Panther Lake) processor using the Qwen3 8B language model at INT4 quantization, showed real-time edge performance. The GPU path achieved a Time to First Token of 125 ms and Time to 10 Tokens of 538 ms, while the NPU path offered lower inter-token latency at 32.2 ms/token compared to the GPU's 41.3 ms/token. OnDemand features four layers: Physical Infrastructure, Real-Time Connectivity via MQTT, an Agentic AI Core for intelligence and automation, and Human Interaction for governance. It supports deployments in environmental monitoring, energy optimization, and predictive maintenance, enabling systems to understand intent, take action, and self-protect without constant human intervention.

Key takeaway

For operations professionals managing critical infrastructure, Agentic AI offers a path to autonomous, cognitive operations. You can deploy edge-based solutions like OnDemand today to enhance environmental monitoring, optimize energy, and enable predictive maintenance. This shift allows your team to focus on policy and strategy, while agents handle real-time execution and maintain audit trails for accountability.

Key insights

Agentic AI transforms reactive infrastructure into autonomous, goal-driven systems at the edge.

Principles

• Agents reason, plan, and act autonomously.
• Human-in-the-loop governs agent policy.
• Edge deployment ensures real-time safety.

Method

The OnDemand platform integrates physical infrastructure via MQTT, uses an Agentic AI Core for intelligence and automation, and provides human interaction for policy and oversight.

In practice

• Start with environmental monitoring for safety.
• Optimize energy consumption with intelligent agents.
• Implement predictive maintenance for ROI.

Topics

• Agentic AI
• Critical Infrastructure
• Edge AI
• OnDemand Platform
• Predictive Maintenance
• MQTT Protocols

Best for: AI Engineer, AI Architect, Operations Professional

Related on AIssential

• Agentic AI will force a rethink at the network edge — Agentic AI demands a converged edge computing and networking architecture for autonomous, real-time, and secure distributed operations.
• From backend support to AI orchestrators: Reimagining the way the Digital Workplace team operates — Agentic AI orchestrates complex IT workflows, transforming manual Digital Workplace operations into scalable, autonomous systems with human oversight.
• Edge AI for Smart Cities — Agentic AI at the edge transforms smart cities into cognitive cities by enabling real-time sensing, reasoning, and autonomous action.
• How agentic AI helps heal the systems we can’t replace — Agentic AI can modernize critical legacy systems by learning their real-world behaviors and acting as a stable, synthetic API.
• Agents don’t know what good looks like. And that’s exactly the problem. — Agentic AI excels at behavioral tasks but lacks judgment for complex architectural and operational challenges.
• How to Plan Agentic AI Deployment for Chip Design — Agentic AI is fundamentally transforming semiconductor design by enabling autonomous, intent-driven design orchestration at scale.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence (AI) articles.