Saliou

In the Analyze phase, it's important to get vevery team member involve. Brainstorming / brainswritting to identify potentiel causes. Never assume always focus and based on facts. Group possible causes and confirm root causes with data some time additional data need to be collected for confirmation. most of the time Analyse and Improve need several iteration till the root cause can be identify. In the sales case simple 5 why could show that stockout is a consequence and not a root cause It's where AI could help getting real data more releable than historical.

Traditinnonally, ones will try to balance leading an lagging indicator like respectively number of patient arriving per hour and average waiting time for exemple running time series plot or triangulating different metrics. But using AI could turn the lagging to leading indicator by using realtime ploting and dynamic analyse. This will avoid acting late, using wrong data source or variation on sampling.

In this topic, I'll draw on my personnal experience in my company where several experiences have been tested. The first one was to form working groups to propose topics on identified problems and find solutions. Every six months, the three best topics were awarded prizes. The second was to set up idea nests where employees can submit ideas, which are then sorted and prioritized. One of the latest initiatives is intrapreneurship, where employees can propose innovation or renovation projects of new product. All of these initiatives raise questions among employees about the objectivity of the winners' choices, which can be subjective, which is why some employees prefer not to participate anymore. These questions and concerns can be easily addressed through artificial intelligence by implementing an AI Agent to collect, structure, and classify ideas by relevance.

Key Risk Indicator (KRI) can be used for process management. KRI are more leading where anticipation and mitigation of critical risk to business continuity. KPI or Key Performance Indicator could be consider as lagging because used for monitoring process against its goal. Companies are using KPI over KRI mostly because, - KPIs are more common - Easier to define - Easier to Monitor - Easier to link align with business goal like throuput, cost reduction and efficiency. Benefits of using KRI, - KRIs are more leading and predictive - KRIs give early warning and prevent disruption - reinforce companies resilience but KRIs have limitation, they are very difficult/ complex to define, difficulties to have benchmark data. Because they are leading it might difficult to have real time or available data, finally lack of experience and or expertize to interpret.

When designing AI interacting with human, it's important to integrat human thinking and behaving. Considering human impatience, answer should be like in normal conversation avoiding long waiting time. When it comes to the responses tones, voice should be natural no robotic and following the conversation that mean feeling like talking with friend or colleague dependent of the context. Professionnal to colleagues, causual and friendly when needed and managing frustration and emotion? Guiding and rephrasing when user's request are unclear or mistaking to get to the right question concerning the feedback style. To handle errors, do not blame, accompagn with empathy and giving confident to try again. being gratful For personnalization, let people choose different mode e.g. ( detail responses / concises one), anable learning human behavior along ustilisation for improvement and adaptation

Let's consider saltiness of a product as quality release crititeria. Ai answer with confident the quantity of salt to be added in the recipe. if the saltiness level is high or too low, consumer could reject to product which could lead to loss: - consumer trust, - market share - Punishment from autority of regulation.... To avoid this: - Prompt engineering with validation check in internal DB - Human validation or escalation to Human agent when answer is not found in the DB

In TPM one of the more impactful activity between AM and PM pilar is Tag negaciation, allocation and closing follow up. we create an App automatize the closing follow which should take in a consideration: - Equipement - Equipement location - Part of the equipement - Name of the responsible of the task - Start Date - Closure date If the ask is not closed in due date, AM, PM pilar lead and their line manager should receive an email saying that the tag allocated to (Name) was not completed in time. if a tag is completed and the same issue come back, the could not be completed without uploading a RCA first. this process could be reasonably be put in plays using: - scanning the equipement - choose the part of the equipement having the issue (picture) - prioritizing the issue - looking in the KB if the tag has been already solved - if yes verify if the RCA exist - if yes allocate the issue to RCA flow - if no allocated accordingly - close the the tag and save the RC - send recognision if timely completed coping AM, PM pilar lead and line manager - if not completed in time, send email to same group - generate statistics to ease decisions

The performance of rotary tablet press for pharma and Food application, is trigged by the density, moisture and the flowability of the product to be pressed. To define best parameter for high performance and quality, it’s important de follow: - The critical Raw Material for binding - The temperature and the moisture fort he activation of the binder In one part. In the other part record the machine parameters : - The pressing force applied to the product to shape it - The standard deviation of the pressing force - The weight - The height of the final product critical for the wrapping And at the end corolate machine parameter and product parmeter to define the best operational window for highest performance and quality. I think, training from cratch AI approach could be helpful to build a model driving a control loop for moisture adjustment

Let's take the example of E2E process going from a mixing of a set of ingredients to a Pressing and Wrapping machine. To press the mixt you have key parameters like the moisture and the temperature anabling the activation of the binder the mixt. to predict the behavior of the mixt during pressing and wrapping we need to monitor those parameter but it's lagging. What is more mindfull is to predict the moisture which can be use directly without waiting time for Moisture and temperature drop. For that the main ingredient carring moisture in the mixt are monitored manually by running analysis each hour and from there define the amount of water to be added in the mixt in order to get the desired moisture able to run perfectly in the pressing and wrapping line with higher performance and quality. AI could be trainned to control automatically critical ingredients moisture with close loop for the added water.

Online loan application. 1- Give your full name and your account number and the name of the account manager 2- Define the type of account, savings or current 3- Choose the desired loan category: Habitat Vehicle Social School 4- Define eligibility based on quality, analysis of entries and exits over the last three months 5- Transfer the request, get acceptance by the manager and summon the user to come, sign at the agency (handed over to the human) 6- After confirmation of the loan, send an email to the applicant to notify them of the availability of the loan

Nowadays, AI play big role in all live experience. In this sense, it could be used to increase accuracy and accelerate steps in lean six sigma. Going through DMAIC steps, it’s easy to establish that in the: - Define phase, AI could be used helping on problem statement establishment with SMART objective in a effective way; screening and analysing stakeholder for better management of their expectation and satisfaction. - Measure phase, AI could help automating data collection accurately elimination human bias and errors - Analyse phase, AI could be very effective in pattern detection and Root Cause Analysis while avoiding human bias and errors. - Improve phase, AI could as well help shaping a robust and power simulation model, and optimising algorithms for process improvement - Control phase, AI could help in very effective way on real time monitoring system setting, continuous learning and process adaption overtime and predicting failure with very accurate maintenance planning. All those advantages show us that AI is very linked to Lean Six Sigma and could help reduce DMAIC time while having accurate and sustainable results

In principe, reverse innovation start by focusing on needs and/ or exigence in developping products for low income markets and later fitted to others. nowaday companies put a lot of efforts on deleting unnecessary future in develelopped country product to reduce cost and make them accessible to low income markets. for exemple: GE developed an ultrq portable cardiograph for American Market low cost around 80% less than similar one originally build for Indian and China doctors.