Background: The Patient Empowerment through Predictive Personalised Decision Support (PEPPER) integrated system is designed to provide personalised bolus advice for people with Type 1 diabetes (T1DM). The system delivers insulin dosing decision support based on case-based reasoning (CBR), coupled with a safety system, which includes predictive glucose alarms, low glucose suspend for insulin pump users, and personalised carbohydrate recommendations. We aimed to assess proof of concept and feasibility of the PEPPER safety system. Methods: This is a Phase 1 non-randomised open-labelled 8-week study to assess the safety system outcomes (without CBR-based insulin dosing decision support). Eight adults with T1DM on multiple daily injection of insulin (MDI) participated. Following two weeks of unblinded continuous glucose monitoring (CGM, Dexcom G5), participants completed six further weeks using CGM with the PEPPER safety system active. Baseline outcomes derived from the run-in period were compared with end-point. Results: Participants were (median (interquartile range)) aged 38(31.8-53.5) years, with a diabetes duration of 22.5(18.0-26.5) years and HbA1c 63(57-66) mmol/mol. Percentage time in hypoglycaemia (<3.0mmol/l) significantly decreased from 0.82% at run-in to 0.33% at endpoint (p=0.02), with a significant increase in percentage time in target (3.9-10.0mmol/l; p=0.027). The total number of alarms to carers significantly decreased (p=0.005). There was also a reduction in number of carbohydrate recommendations. Conclusions: The PEPPER safety system is safe and feasible to use as a component of the overall system and to integrate with the PEPPER adaptive bolus calculator. The data suggest that the PEPPER safety system has the potential to enable improvements in hypoglycaemia and percentage time in range.