Overview

A large manufacturing plant wanted continuous, real-time visibility from devices on the shopfloor through to supply-chain systems, automated supplier visibility during MRP runs, and ML/LLM-driven procurement intelligence — all while meeting a strict availability target (>98%) for production-critical equipment. Sorim.AI delivered an edge-first platform that ingests device telemetry, synchronizes plant + SCM + enterprise data, and applies open-source LLMs to surface buying patterns and negotiation insights for procurement teams.

Problem statement

"Embed software to connect external device data and continuously monitor devices remotely to ensure availability above 98%. 

Automate 2 & 3-tier supplier visibility during MRP runs. 

Automate device data, plant data and enterprise data to ensure plant and operation availability is high." 

• Intermittent device connectivity and long detection-to-repair times. 
• Lack of automated supplier visibility during MRP — manual follow-ups and frequent stockouts. 
• Siloed plant and enterprise data that prevented predictive insights and rapid troubleshooting. 
• Need to avoid heavy changes to existing PLCs and ERP while still modernizing data flow. 

Challenges

• Intermittent telemetry & legacy protocols: Many machines spoke OPC-UA/serial and produced noisy telemetry. 
• Latency & reliability: Central cloud polling caused delayed alerts and missed events during network issues.
• Supplier visibility: 2nd/3rd tier suppliers weren’t part of the MRP loop; manual checks caused BOM shortages.
• Data fusion: Merging high-velocity device streams with ERP/SCM transaction data in near-real time.
• Actionable intelligence: Transforming raw telemetry + supply signals into procurement negotiation insights and operator-actionable alerts.

Solution Overview

Implementation approach & timeline

• Phase 0 (2 weeks): Discovery, protocol inventory, MRP workflow mapping.
• Phase 1 (8 weeks): Edge agents + data pipeline PoC on 5 lines; basic dashboards and alerting.
• Phase 2 (10 weeks): ERP/SCM connectors, MRP automation, supplier querying; deploy to pilot plant.
• Phase 3 (12 weeks): LLM fine-tuning, procurement UI, rollout to additional sites, SLA hardening. 

Total pilot → production: ~5 months. 

Impact / Results  

• Availability improved: Plant equipment availability increased from ~97.1% to 99.1%, meeting and exceeding the >98% target. 
• Unplanned downtime reduced: ~40% reduction in unplanned downtime due to faster detection and remote remediation.
• MRP success & fewer shortages: Automated 2/3-tier visibility cut MRP exception handling by 25%, materially reducing emergency orders.
• Procurement savings: LLM-assisted supplier insights and negotiation playbooks produced ~8–12% average procurement cost savings for targeted commodity groups. 
• Faster content-to-action: Mean time to acknowledge critical device alerts reduced from hours to 15 minutes with edge detection + push notifications. 
• Operational efficiency: Maintenance crew utilization improved (fewer repeat trips) and spare-part inventory optimized.

(Results are aggregated from the Sorim pilot program across the initial production site and early rollouts.)

Sorim Value Proposition

• Edge expertise: Minimizes latency and maintains continuity during network issues.
• ERP/Supply-chain aware: We don’t replace ERP — we augment MRP runs with real-time supplier insight and automated exception handling.
• Explainable LLM outputs: LLM suggestions are accompanied by provenance (which PO, which lead-time datapoint, and which market signals) so procurement can act with confidence.
• Operational focus: We pair predictive detection with operator workflows — not just dashboards — so alerts drive immediate, measurable action.