Puneet K

Robotic process automation (RPA) is a preconfigured software instance that uses business rules and predefined activity choreography to complete the autonomous execution of a combination of processes, activities, transactions, and tasks in one or more unrelated software systems to deliver a result or service with human exception management. . Features of RPA are Works at the server level, independent of human intervention (unattended automation). Fully automates end-to-end processes. Scalable across multiple systems and departments. Ideal for structured, rule-based processes. Robotic desktop automation (RDA): computer application that makes available to a human operator a suite of predefined activity choreography to complete the execution of processes, activities, transactions, and tasks in one or more unrelated software systems to deliver a result or service in the course of human initiated or managed workflow. It can also be called as agent-assist automation, assistive automation, in-line automation. It Operates on an individual's desktop. Features of RDA are Requires human intervention (attended automation). Best suited for tasks where decision-making and manual oversight are needed. Limited scalability Below are the different stages for designing an automated tool or a robot Discover; Structured approach to review process landscape and identify best candidates for automation Design - Simple rapid engagement approach to understand the process and design and implement an automated solution Manage - Central deployment and management of automations with key governance controls and strong change management Run- Automations execute the business processes they are designed to perform while being monitored Engage -Communicate with business process teams to ensure the process is performing and exceptions are reported Measure - Reporting of utilization and impact of automation We have to make choice between RPA and RDA at the discovers stage itself. This is also illustrated by the diagram below If the process requires frequent human interaction, RDA is preferable. If the process is rule-based and can be fully automated without human input, RPA is the better choice. If scalability is a priority, RPA is more effective. If process mapping accuracy is a concern then we should start with RDA to refine the workflow before transitioning to RPA. The issue of complexity of the data can still be handled by RDA through below means Modular Design: By dividing complex processes into smaller, reusable modules, RDA can address different parts of a workflow independently, making it easier to manage and update specific components without affecting the entire process. Conditional Logic: RDA tools allow for "if-then" statements and decision points within the workflow, enabling robots to adapt to changing situations and make choices based on specific conditions within the data. Data Extraction and Manipulation: RDA can extract relevant data from various sources, clean, transform, and manipulate it as needed within the workflow, handling complex data structures and calculations. Application Integration: By integrating with diverse applications and systems, RDA can automate cross-platform processes, pulling data from one system to perform actions in another, even if they have different interfaces. Looping and Iteration: RDA can repeat certain steps within a workflow based on defined criteria, making it suitable for handling repetitive tasks with variable data input. Error Handling: Advanced error handling mechanisms allow robots to identify and recover from potential issues during execution, automatically retrying steps or notifying users when necessary.

A moonshot idea is an ambitious, groundbreaking concept aimed at achieving something that seems nearly impossible but could revolutionize an industry, society, or technology if successful. Moonshot ideas typically involve high risk, out of the box thinking, and possible significant investment in research and development. For an idea to be called as Moonshot Idea it should have the below statistics: 1. Radical Innovation – It shouldn't be a simple fix rather it should be revolutionary, unimaginable, or undoable. It should be transformative in nature and not BAU 2. Based on principle of high risk * High reward- While risk will be eminent in terms of investment of time and money, reward won't be certain however if it is successful then rewards to be multiple x of investment made. 3. Should involve cutting-edge technology or scientific breakthroughs. 4. Global Impact – If successful, it can change the world / industry Being in finance, I often encounter the challenges of external payments being prone to fraud and not safe. In the new digitized world, I would like to explore the idea of AI in smart payment. So far use of LLM in payments is rare and yet to have confidence from finance community. Various checks which I would potentially have to do for moonshot idea are : Technological Feasibility Is LLM matured enough to handle topics are payments whereby robots also struggle to keep the fraud risk down despite the pre-defined criteria Any organization who has experimented this in past and what were the outcomes and reasons for failure No human touch environment possibility thereby eliminating risk of internal fraud/ Fully automated AI enabled Human less Data Management Team. AI Powered Tools / Metrices Current accuracy % and error rate – May be even factor analysis could help in here Real Time payment incoming pairing alert from recipient server which if not provided would lead to stoppage of payment, ( Host to host) Possibility of block chain based decentralized fraud detection network across different regulatory environments Regulatory & Compliance considerations – Payment laws. Network limitations/ VPN regulations and country specific restrictions like China, Brazil etc. Cost of Prototype ( MVP) and final product needs to be justified. ( Business Value Analysis skills learnt during MBB Course will be truly tested) Simulation environment and test cases from one of the BUs / regions/ geographies Scaling up strategy- Partner with existing player or produce inhouse Exclusive use or sale in the market. As we can see there could be number of considerations which are to be made before we embark on journey of a moonshot idea.

Factor Analysis is often used to the reduce the challenges of complex data. It identifies the variables which are not apparent ( latent or underlying) which explains the cause of variances in data. It doesn't identifies number of individual variables rather it groups variables into a s a smaller set of factors and draws patterns which makes the relationship more understandable & obvious. This calculated reduction or selective approach helps in identifying core drivers of the varability and eliminates redundant information. Factor analysis work in the following manner : 1. Examines and Identify Correlations among multiple observed variables. 2. Extract underlying Factors by grouping highly correlated variables. 3. Interpret Factors basis variables it relies highly on. 4. Reduce Dimensions of variables while retaining the most significant information. Practical Example in a Lean Six Sigma Project Scenario: Reducing Customer Complaints in a customer grievance Center A Lean Six Sigma team is analyzing customer complaints in a call center to improve service quality. They collect survey responses on 10 different service attributes: 1. Response Time 2. Agent's behaviour 3. Call Resolution 4. Clarity of Information 5. Subject Matter Knowledge of the Agent 6. Call Hold Time 7. Service Process Efficiency 8. Ease of Reaching the agent 9. Follow-Up Effectiveness 10. Call Escalation Applying Factor Analysis The analysis reveals that these 10 attributes can be grouped into three main factors: Factor 1: Service Efficiency (Response Time, Hold Time, Ease of Reaching agent) Factor 2: Agent Performance (Agent behavior, Knowledge, Call Resolution) Factor 3: Process Effectiveness (Follow-Up Effectiveness, Call Escalation, Clarity of Information) Lean Six Sigma Benefits Simplifies analysis: Instead of analyzing all the 10 variables separately, the team focuses on three key drivers. Prioritization of improvements: If Factor 1 (Service Efficiency) has the highest impact on customer complaints then that becomes a focus area, and the efforts will be done to improve it. Reduces redundant efforts: The team avoids fixing individual variables separately and instead works on holistic improvements in identified factors. By using factor analysis, the Lean Six Sigma team can streamline the problem-solving process, leading to more effective decision-making and efficient resource allocation

Gantt charts contribute to effective project planning and monitoring through Clear Project Visualization One of the biggest advantages of Gantt Charts is that they provide a visual representation of the project timeline. Project Managers get a complete view of the following: Determine when tasks start and end. Identify overlapping activities. Track overall project progress at a glance. Better Task Management & Scheduling - Gantt charts enable project managers to break down complex projects into manageable tasks which makes it easier to allocate resources, set deadlines, and prevent scheduling conflicts. Improved Team Collaboration Gantt charts also facilitate collaboration which suggests that project managers and team members get a shared view of the project which teams can work on more efficiently: Understanding important roles and responsibilities Learn how tasks connect to others Keep everyone aligned with the necessary project goals Identifying Dependencies & Bottlenecks Projects often have interdependent tasks. Such as Task A must be completed before Task B could begin. These Gantt Charts map the dependencies which prevent delays and help team members to proactively address shortcoming and bottlenecks. Tracking Progress & Meeting Deadlines With real-time progress tracking, project managers and teams can ensure they are on schedule. When tasks are delayed, its impact on the entire project is made visible which allows fast adjustments. Optimizing Resource Allocation – Helps distribute resources effectively while preventing overload. Enhancing Communication – Ensures teams and stakeholders have a shared project overview. Various Strategies which project managers can use to overcome the limitations of Gantt charts in a dynamic and complex environment are 1. Incorporate Agile Methodologies – Combine Gantt charts with Agile frameworks like Scrum or Kanban for greater flexibility. 2. Break Down Large Projects – Implement a Work Breakdown Structure (WBS) for easier tracking. 3. Leverage Advanced Software – Use tools like MS Project or Asana for real-time updates. 4. Regularly Update the Chart – Ensure it reflects the latest project developments. 5. Integrate Risk Management – Include contingency plans to accommodate unexpected changes. 6. Utilize Dependencies and Critical Path Analysis – Adjust schedules dynamically based on critical tasks. 7. Adopt a Hybrid Approach – Combine Gantt charts with other planning techniques to match project requirements.

Best practices are the lessons learnt from previous engagements and sometimes hard way. However a lesson becomes practice only once it gets repeated or followed. Hence for a practice to be called as practice adoption is the key. While best practices are widely available, only a few companies achieve world-class excellence because success depends not just on knowledge but on execution Mindset / culture- Some organizations / leaders don't believe in best practices as they feel "one size doesn't fit all" Which I might be true in some cases as every best practice cannot be copy pasted and it requires some customization however sometimes customization might appear to be more time consuming / expensive hence these Organization go for start from the scratch approach which leads to deprivation of benefit of "learn from others mistakes". Strong Leadership is crucial in driving change. Companies that embed a culture of continuous improvement and innovation are more likely to sustain excellence Discipline for Execution- For any practice to be successful, discipline for execution is desirable. Gap between understanding and execution can render best practices ineffective. Many organizations fail due to lack of follow-through, accountability, and structured implementation. Long Term focus instead of low hanging fruit or short-term grind would yield better results in case of adoption of best practices. Sometimes best practices are considered as short cut and in initial stages itself, it gets dropped and momentum is lost hence persistence is key. Strategic Resource Allocation – Implementing best practices often requires investment in technology, training, and process improvements. Companies that prioritize short-term profits over long-term excellence may fail to sustain their initiatives.

Capacity Planning is the process of balancing the resources available at a given point in time to that of demand for such resources. Capacity planning helps you identify potential areas for growth, which boosts investment returns, and maintains good employee morale. Planning your resource capacity is helpful when you manage several projects because it improves your chances of accomplishing them on schedule and within budget. Purpose of capacity planning could be various such as Preparing for future demand Determine efficiencies in current teams Appropriate allocation of resources Sometimes even to identify the NVA activities which can be eliminated Assess your risks. Will people burn out if we load in more work? What happens if we don’t meet demand? Calculate and quantify the risk of lower customer satisfaction if a project can’t start on time, or the cost of hiring and retraining employees if people quit. Types of Capacity Planning? Workforce Ensuring you have sufficient staff to handle your anticipated future workload is the goal of workforce capacity planning. Workforce capacity planning gives you information on whether you have the appropriate number of employees, skill set, and job roles to meet demand. Your workforce capacity plan can reveal when you have too few employees, providing you with the time and knowledge to hire more. Similarly, it can let you know when you have too many employees, so you can consider downsizing or moving them to another company department. Workforce capacity planning ensures you have the employees required to fulfill your organizational goals and that they are present in the appropriate place at the right time. Planning workforce capacity helps you deliver more initiatives on time and within budget while also delighting your customers and preventing worker burnout. Burning out your employees may result in increased turnover, more sick days, and decreased productivity. For ex, Below table suggests that time spent by two teams on almost identical tasks in Hrs. Row Labels Sum of Team B Yearly Efforts in Hours Sum of Team AYearly Efforts in Hours Communication 4517 3291 Division specifics - Team A 1090 Division specifics - Team B 332 Education 839 622 Idle time 1140 915 Internal meetings 2056 2865 Invoices, DDs, Credit Notes, Deposits 10896 8952 MJE 1348 727 Power user tasks 1046 650 Project hours 3572 1278 Recons 1257 430 System Enhancements 2074 Type 2 Invoices 1784 6971 Grand Total 30859 27792 We need to evaluate how many members in the team are and whether an 8 hour day would be sufficient for these activities or these are more than enough and accordingly we need to decide if there is excessive capacity available in the team which can be used for other activities or we need to cut down the team size. During this exercise we also get to know that team is spending lots of time on internal meetings which is typically classified as NVA. Project The second type of capacity planning ensures proper planning and funding of your various project needs. Project capacity planning helps you estimate the impact your objectives will have on your business. By providing a reasonable estimate of how much money you can and cannot afford for every project, you establish appropriate levels of spending for all future initiatives. This type of planning ensures you avoid overspending or underfunding and gives you the data to show how many projects you can feasibly complete in a given period. Most important is that the projects remain within budget while providing an accurate forecast, which will help the organization determine whether it handles its resources optimally. Project capacity planning can give you a competitive edge through more revenue, less competition, and better profits. Understand current capacity. What projects, using what people do we currently have under management? What extra time do people have to do more work? Project future demand. What projects are in our sales pipeline, how certain are they to close and when will they start. What skills will be required for those projects? Identify where additional capacity could come from. Can we work extra hours, develop new skills? Should we hire more people? Tool Tool capacity planning ensures you have adequate facilities to finish jobs, including equipment for an assembly line or machinery required to produce and distribute your product. Tool capacity planning ensures you utilize the best resources available by providing access to the most effective techniques and materials to execute your plans. Your tools should be practical and easy to use while providing the accurate information you need to make well-informed business decisions

While designing the Proof of Concept (PoC) for AI-driven chatbot to improve customer service to test its feasibility and alignment with business excellence goals, we must first decide on success criteria and also the key KPIS Success criteria might include: X % accurate responses generated by the Bot X % positive customer feedback on a scale of 1-10 X% reduction in support tickets or rerouting Focus on the critical components rather than building a full-scale solution. Define timeline, budget, and resources Determine assumptions that need validation. Choose the simplest possible implementation to validate the idea. Use low-code or prototype tools and possibly with a predefined set of responses Integrate existing systems/data where necessary. Conduct controlled testing with a small user group i.e with X number of customers for a limited number of days Measure accuracy of responses, resolution time and customer satisfaction scores through ther qualitative and quantitative feedback. Identify gaps, failures, or improvements needed. -Compare results against success criteria. Identify potential roadblocks or scalability challenges. Decide whether to proceed, pivot, or abandon the project. Summarize outcomes, insights, and recommendations. Demonstrate alignment with business excellence goals. Some of the risks which project leader must mitigate to ensure a smooth transition are Encountering technology-related problems in the development process Failing to reproduce lab results in the real world Struggling to scale AI systems across use cases Making erroneous assumptions about AI capabilities Solving the ethical challenges of AI adoption

Humans know more than they can explain. This justifies or explains Polanyi’s Paradox. In Today's world even though we are surrounded by the AI gadgets, a lot of tasks professions and activities are still out of scope for LLM. As long as we utilize them as enabler however their actual usage as a replacement of the human effort or brain is still far from reality. For a machine to accomplish a task it needs to be programmed first with the sequence of steps required to perform that task, after then the machine to precisely simulate these steps. However, if any of the steps is influenced or requires a human response then it won't be able to repeat all those steps. This will cause the machine to fail to replace humans. For example, A Doctor who is treating a mental health patient his / her actions , responses are generated by the actions of the patients in real time and is heavily influenced by expressions, emotions of empathy etc. This can never be replaced by AI as a person would want to talk to a human being rather than an AI generated machine or a code. A sports person performance. Her / his preparation can be influenced by AI but the performance. Creative Professions like Story writing, art and craft etc. where at any given time one would prefer an original art than machine generated. Leadership Skills / Jobs – The essential skills of motivation, empathy, , compassion which are a package in leadership positions cannot be imitated by a machine. We can program several situations and can also introduce Machine learning algorithms for next time however in current situation an employee would rather want to discuss / get influenced by a human instead of a machine. Overall, AI should be a good enabler in quite a few areas however its efficacy in generating similar and effective responses like humans is still questionable.

With my limited experience with LLMs and extensive experience with Excel and basis some experiments with continuous I felt that data quality of the output would primarily depend on the prompts. I am using Copilot for this. While results from excel are fine, Copilot results are quite patchy. For simple continuous data calculations like correlation didn't work and I had to review all output carefully and spotted multiple errors. Also, may be it was only for me as error, copilot only worked on files which were in share drive and share point. Locally saved excel file wasn't working with Copilot and basic feature like Auto save was to be enabled. When I tried this with Chatgpt. Below are the results Book1.xlsx Google Sheets Analyse data set ChatGPT said: ChatGPT The uploaded Excel file contains three sheets: Sheet1, Sheet2, and Sheet3. Which sheet would you like me to analyze, or should I analyze all of them? You said: Sheet1 ChatGPT said: ChatGPT The data in Sheet1 appears to have a header row shifted or extra blank columns. Here's the structure: Unnamed: 0 Name of the Employee Salary NaN A 2000 NaN B 2200 NaN C 2400 NaN D 2600 Would you like me to clean this data by removing unnecessary columns and correcting the header row? You said: Yes ChatGPT said: ChatGPT The data has been cleaned and now looks like this: Name of the Employee Salary A 2000 B 2200 C 2400 D 2600 E 2800 Would you like to perform any specific analysis or visualization on this data? You said: Calculate standard deviation ChatGPT said: ChatGPT It seems like I can’t do more advanced data analysis right now. Please try again later. If there's anything else you'd like to discuss or analyze, let me know! Above exercise took almost 10 mins and with no result Seems like LLM though can understand the language of the data however cannot interpret formats or relationships. Overall, I feel LLMs cannot give accuracy and reliability of complex excel products.

Being a project Manager, our endeavor should be to act in the interest of the organization. There is no set criteria whether we should always oppose the change or advocate for the change. Any kind of change which leads to a project could be influenced by following priorities Risk Mitigation/ Compliance requirement – In this scenario we must advocate and support the change as this is non-negotiable and has to be done. Most often in these cases the opportunity cost for not doing these projects is quite significant ( monetary or non-monetary) and its resistance wouldn't be appropriate. Revenue generation / Profit Impact- In these kinds of projects we need to calculate ROI and also % of success before we challenge / support the project. This is where we also used the techniques of Assumptions/ forecasting which we just learnt in previous sessions. Efficiency Projects – These are also in a way support the profit line of the organization however these should also be weighed in overall context of the organization. Sometimes the efficiency projects in one department can cause overload in other departments and can cause labor issues as well/. Hence the pros and cons must be fully analyzed and then a call needs to be taken. Self- reliance projects- These kinds of projects are a combination of revenue generation/ Efficiency/ aspiration & reducing vendor dependency projects. This is where we need to be challenging, and a thorough evaluation needs to be done. For ex. In my previous organization where we were in a risk management business and management decided that instead of taking an off the shelf solution, we will take the base one and will develop our own solution. This caused significant delays, bugs and issues in creation & implementation of the solution. Since it was inbuilt hence no vendor support or troubleshooting was available. It was more aspirational in nature and wasn't properly thought through. This gives us a learning that PM should be able to challenge the senior management and push for a thorough analysis especially in aspirational projects where executive decisions tend to take priority over business prudence.