Closing the AI/ML Loop at the Edge with SLMs on
summary
Describes a deployed stack that runs small language models at the edge with FactoryTalk Optix for operator UI, FactoryTalk DataMosaix as the contextual data layer and AWS for cloud services, tying LLM agents to physics-aware models that push setpoint changes to PLCs. Claims include a tire-line vision loop holding a seal tolerance between 9 and 3 mm, a food‑and‑beverage pilot that cuts one research FTE by ~55%, matches replacements for 70% of inventory, and saves ~10% unplanned downtime via edge anomaly detection.
AI-written summary · about
chapters (7)
- 0:00From automation to autonomy
- 1:02AI modeling and use cases
- 2:53Integrating AI into operations
- 4:22Data platforms and edge cloud
- 4:58Semantic data and agent frameworks
- 8:30Agentic architecture overview
- 9:05Practical applications and ROI
related talks
28mNavigating LLM deployment: Tips, tricks, and techniques
36mProduction-Ready AI Agents: From LLMs to Small Language Models
40mSurviving the Agentic Hype with Small Language Models
29mThe Evolution of LLMs: From Imitation to Reasoning
24mBuilding Real-Time AI Decision Systems with LLMs
42mOpen Source LLMs — Powering AI Accessibility and Innovation
20mSecure, private LLMs in your cloud with Anyscale Endpoints
31mWhat problems should enterprises actually trust an LLM to solve?