Sakshi Dixit

AI Governance encompasses the tools and techniques used for effective management and monitoring of processes. If governance has flaws, then the organization is at risk of financial and legal damages. Also, there is a risk of reputation damage if the outcomes are biased. These threats can be overcome if AI governance is excellent. It will also boost confidence in the AI systems due to transparency and accuracy. AI Governance team has the responsibility of a culture of Responsible AI in the organisation AI Governance must have its own metrics and measures. · Transparency: they should be clearly explainable · Ability to Detect Biases: Mitigate them immediately · Proper incident Response: Proper actions to be take · Third party Audits: Audits should be done to review data handing practices and point out any flaws · Inventory of all AI systems in use: Maintain them · Risk assessment: perform detailed risk assessment · AI compliance committee: will look into AI Governance activities

The role of a Master black belt in a company is to evaluate and investigate the processes in a company and then further direct the course of action in processes where there is defect. The MBBs have a deep knowledge of the processes of a company and dictate the strategy for the direction to be taken. AI team’s approach is more data driven and they would want to look for automation of the processes. They would want to analyze the data and identify patterns and give insights which the MBBs might have missed. If they work together, they will lead to more optimized processes, better decision making and a more optimized process. MBBs can contribute by: · Sharing Process expertise: They have deep knowledge of processes. · Guiding strategically: They can guide the AI team with organizational goals. · By Handling Change Management: By helping the teams to adapt to AI driven processes. · Understanding of context: Ensuring that AI solutions are practical and relevant. AI Teams can contribute by: · Automation: They are experts in Automation. It can help to automate repetitive tasks. · Predictive modelling: They can use the Predictive models to forecast the potential issues. · Simulation and optimization: they can simulate the new processes for MBBs to test before implementing them actually. · Data Analysis: They can use data analysis tools to identify patterns and anomalies that the MBBs might have missed. How MBBs and AI Team can work together: 1. MBBs and AI teams should try to learn from each other and always stay updated on the latest technologies, trends and best practices. 2. They should use and iterative approach where the solutions are continuously improved based on the feedback. 3. They should clearly understand each others’ roles and responsibilities so that there is no conflict and each team can contribute effectively.

The efficiency of Processes in a Company often defines its success in terms of better customer experience, faster services and a better quality The traditional methods of improvement of processes involves digitalization and rule-based automation; but with growing business complexity these approaches can struggle. In these cases, AI driven approach can be used. With machine learning and generative AI organisations can analyse vast amounts of data to continuously improve the processes and find out the inefficiencies. This would have been impossible with the traditional approach. As a result, AI could be used not just to improve work processes but to reshape how the work is getting done. It will help systems to get smarter with time and not just make them to run faster. To find out the Processes that are good for AI driven approach · Discover the processes that give greatest potential for AI driven gains For eg : processes that show delays or bottlenecks or repetitions · Select processes that will give genuine impact on the finances The benefits of AI integration could be · Increased efficiency · Reduced errors · Better customer experience · Cost reduction · Better decision making due to use of data analytics Examples in which processes could be reimagined with AI could be · E-commerce · Manufacturing and supply chain management · Health care So, if Companies are looking at achieving long term growth, improve decision making , give a better experience to their customers and stay ahead in today competitive digital landscape then I think such companies should definitely start to reimagine their processes with AI instead of looking at improving it with a traditional approach.

In the Improve phase of the DMAIC cycle, we try to implement the solutions to address the root causes of the issues that are pointed out in the Analyse Phase. All changes that are required to improve the process are executed in this phase It can be done by · Developing/testing solutions · Optimizing parameters in the process · Establishing SOPs to reduce the variations · Improve process performance The activities involved could be: · Finding the solutions to address the root causes that are pointed out in the analyze phase · Prioritizing the potential solutions · Implementing the right solutions · Pilot testing on a smaller scale before implementing the solution on a larger scale · Creating an SOP · Measuring the implemented solutions so as to track the improvements Choosing between more coders or better testing tools for a software company that is tackling with an issue of slow bug fixes the approach could be · Better training to existing coders · Selecting the best solution depending on the cost criteria · Monitoring if bugs are fixed faster by applying more coders for a particular project instead of acrros the company · Company has to consider solution depending on what approach is more sustainable My approach would be to train the coders with latest technologies and using better testing tools so that lesser bugs are encountered. This seems to be a more sustainable approach rather than increasing the number of coders. This will also result in resistance to change .

In DMAIC analyse phase of Six sigma data that has been gather in a previous phase (for eg measure phase) . It can help to find out places where improvements are needed. The analyse phase will concentrate on finding out why a certain issue is occurring. It uses various statistical tools to analyse data and find reasons for the problems.Since it focuses on finding the underlying cause of a problem it can be used to separate the real cause from the noise .Careful sampling is needed for the success of the analyse phase. To separate the real causes from the noise so as to prevent mistakes we can combine critical thinking, analysis and observation. Investigation of potential causes and looking into the patterns and isolating the variables can lead to better analysis. Repeatedly asking the WHY questions can help to drill down the problem Also quickly jumping to conclusions and ignoring the obvious or ignoring the big picture can lead to pitfalls. Advanced tools like ANOVA , Regression and hyposthesis tesing can be used

Key Risk Indicators (KRIs) are essential metrics for managing processes by monitoring and tracking potential risks, thereby enabling early intervention. These indicators support organizations in identifying and mitigating risks before they become severe, which in turn aids in minimizing potential adverse impacts. KRIs enhance proactive risk management, improve foresight on emerging risks, bolster decision-making processes with timely and pertinent information, and facilitate the development of effective risk mitigation strategies. Additionally, they are instrumental in optimizing processes, reporting risks to stakeholders, benchmarking against industry standards, and fostering a strong risk management culture within organizations.Key Risk Indicators (KRIs) serve as valuable tools in managing processes by preemptively identifying potential risks that could negatively affect outcomes Key Performance Indicators (KPIs) focus on measuring success against predefined goals. While KPIs are pivotal for monitoring performance and are more straightforward to measure, KRIs offer an early warning system, allowing for proactive risk management and strategic decision-making. However, the implementation of KRIs presents challenges, including the difficulty in choosing appropriate KRIs, the risk of overemphasizing potential threats at the expense of performance, and the need for expert knowledge to effectively manage these indicators. Despite these challenges, KRIs play a critical role in enhancing risk management, strategic decision-making, transparency, accountability, and preparedness for emerging risks. It's essential for organizations to balance the focus between KPIs, which are directly linked to operational and strategic achievements, and KRIs, which focus on potential risks, to ensure a comprehensive approach to process monitoring and management. Examples of KRIs: Cybersecurity: Tracking the number of unpatched vulnerabilities in an organization's systems or the number of phishing attempts detected. Supply Chain Risk: Monitoring the concentration of suppliers or the length of time it takes to receive shipments. Financial Risk: Tracking the number of overdue accounts or the percentage of loans in default. Operational Risk: Monitoring the number of safety incidents or the number of customer complaints. Compliance Risk: Tracking the number of regulatory violations or the number of overdue regulatory reports. KPI Examples: Sales: Number of new customers acquired, average customer lifetime value, sales revenue growth. Marketing: Website traffic, social media engagement, conversion rates. Finance: Net profit margin, return on investment, debt-to-equity ratio. Operations: Production output, efficiency, cost per unit. Human Resources: Employee turnover, employee satisfaction, training completion rates.

Business Process Reengineering (BPR) and Lean Six Sigma are two methodologies aimed at improving organizational efficiency, but they differ in their scope, focus, approach, and implementation. *BPR is a strategic, holistic approach aimed at completely overhauling organizational processes to align with strategic goals and enhance customer value, often requiring significant investment in resources and technology. It involves mapping current processes, identifying inefficiencies, and designing new, more effective processes. *Lean Six Sigma is more focused on improving specific processes within a defined scope to eliminate waste, reduce process variation, and improve quality. It uses a data-driven, statistical approach using the DMAIC cycle (Define, Measure, Analyze, Improve, Control) and requires less investment compared to BPR. *While BPR seeks transformative, dramatic improvements by redesigning entire processes, Lean Six Sigma aims for incremental, continuous improvements within existing processes, focusing on reducing defects and ensuring process consistency. In short, BPR is about doing better things by creating new and efficient processes whereas Lean Six Sigma is about doing things better within the framework of existing processes. Suitable applications for Lean Six Sigma : · Areas of the business that experience the longest task completion times, frequent complaints · Areas of the business that require substantial employee support · Areas of the business that display monthly quality defects in products or incur costly mistakes, appear the most chaotic, present significant risks · Areas of the business that vulnerable to reputational damage or demonstrate a need for crisis management to meet deadlines. Suitable applications Business Process Reengineering (BPR) · BPR is recommended for scenarios demanding radical improvements in efficiency, quality, speed, and service. · Situations with significant inefficiencies, where outdated or complex processes lead to bottlenecks and resource wastage. · BPR is ideal for making fundamental changes rather than incremental improvements, aiming at innovation and gaining a competitive edge. · Applicable across various industries, BPR strategies can streamline processes, reduce costs, enhance quality, and increase speed and agility in sectors such as manufacturing, healthcare, retail, finance, and public administration.

AI is trained to predict based on past patterns and might not verify the facts and understand the context .It would be better to verify from sources for critical decisions and do some cross questioning. AI might not understand the human sense as it wouldn't know what is true or false.It responds only as what seems correct to it based on training data. It might be giving outdated or incorrect medical advice without understanding the backgound of the patient or it might misquote Misquoting historical events(bias) or give incorrect advice on laws as there could be training limitations . Even the best models could be trained using imperfect data extracted from the internet or other sources of information which might be outdated. As a User we should always keep in mind that confidence does not mean accuracy. Its always better to not rely completely on AI in critical situations.

I thinks humans are responsible when AI goes wrong because humans are responsible for deployment of AI systems. 1)The reason could be due to inadequate testing and lack of proper oversight and insufficient training of the AI model 2)AI systems using machine learning take time to develop their understanding and deploying them without sufficient knowledge pool could prove hazardous 3)AI tools should be used by humans keeping in mind their limitations, and not blindly depend on them for critical decisions. eg: completely depending on AI for medical diagnosis could prove risky

The Goal clashing scenario will come into picture when AI is not able to decide which rule to prioritize. For eg. in an automatic car driving case AI can get confused with safety and efficiency in certain situations . In such cases human and AI collaboration in decision making or monitoring the performance of the AI in various situations and evaluating its behavior to handle goal clashes can prove useful . While designing the AI system goals and priorities should be clearly defined so that there are no clashes and the desired outcome can be delivered easily.