DNF-2 — “Hey, Filler”: AI Assistant for Machine Maintenance.

Ask “Hey Filler” by voice or chat for the filler's prioritised health, quality, efficiency and abnormality status, with evidence and recommended next actions – predicts and prevents stoppages and defects, auto-corrects within approved limits and guides step-by-step troubleshooting. One-filler pilot. Today: - Filler data and alarms are fragmented and diagnosis relies on experts. Dashboards, alarms and TBM/CBM checks inform people but do not create one prioritised recommendation. - Teams react after a breakdown, defect or deviation, every shift and in the daily review.

- Less unplanned downtime, defects, MTTR and material loss. - Higher eUPS and speed. - Better labour productivity and M&I cost, towards Zero Defects.

- Operators - Maintenance - Quality - ME - IT/OT

- PLC/sensor history, alarms, breakdowns, defects - eUPS, speed, material loss - Maintenance records, CIL/centerlining/PMO3 and abnormality tags Note: Synthetic data could be potentially provided during the process, upon approval of the Nestlé team and in compliance with data law.

To be determined Note: Nestlé's current environment includes Microsoft Azure and Microsoft Copilot. Solutions that can work with this environment are welcome, and final integration and deployment requirements will be confirmed with the Nestlé team.