Implementing Robotic Process Automation for meeting Product Safety Stewardship Processes– Few cases studies

I have involved in couple of assessments over the adaptation of Robotic Process Automation for meeting Regulatory Compliance. It was a detailed analysis of existing processes for the RPA potential. I would like to share the some of the experience from the exercise.

white laptop computer on white desk
Photo by on

To begin with you need do the process discovery. Identifying or discovering the process for a potential automation is very critical for successful automation projects. A mix right knowledge of business processes along with capabilities of diverse RPA Tools is critical for the process discovery exercise. Usually it helps to conduct process discovery workshops with key stakeholders comprising of Business Analysts, RPA Architects and Developers to disaggregate each process and identify the automation potential. The detail steps include i) Listing down the processes to be validated for automation ii) identify the consideration consisting of technical & process landscape iii) give relative weightages of the consideration based on experience iv) compute the score for overall automation tools. Some of the questions considered for assessment include complexity of the activity, tactical/operational / strategic nature of the activities, stability of the application which is being tried to be automated, volume of the activity and other criteria like FTE, process standardization or reengineering requirements, is used based on experience. Some of the RPA Tool vendors also provide process discovery tools for assessing the automation potential.

Once the list of automation potential is identified choose the best case for a Proof Of concept which can be used to buy in stakeholder confidence. For EHS, SAP EHS already offers streamlined process which automate the stewardship activities, but in real nature the organizational processes are not completely automated and significant manual effort is used to manually work on different activities to compile the information. Some of the processes include for example, vendor SDS management process, Assessment & Processing of report shipping orders where different reasons of SDS failure can be identified and based on it data creation request or business decisions can be automated, similarly another area is around automating poison centre notification procedures, which to begin seem too regulatory to be risk to be automated but has significant savings. Other processes like manual SDS shipment, DG management, SDS authoring and other block managements, depends on the organizational maturity level in product stewardship activities, which are proprietary in nature to be discussed here.

Regarding the tools section for automating the scenarios there are many tools available in the market which have simple automation capabilities to built in artificial intelligence capabilities via Microsoft Azure integration or Python coding capabilities. It needs detailed assessment to choose the right tool. But many researches and analysis reports from Gartner for example, suggest having a mixed landscape for tool selection as best features are spread across multiple vendors and it is valuable to have a mix tools. SAP also released its product on Intelligent Process Automation using RPA, details of which can be found in Open SAP course scheduled during September 2019. Contextor eLearning  videos are available in YouTube



Operationalizing AI/ML Models using Service Delivery

As you must have noticed that Development of Machine Learning / AI projects largely aligned to specific groups inside the organization. Those who have specialized skills handle the development, testing and operationalization of the components. In deed this way of managing AI/ML projects offer benefits to the organization due to its specialized nature, it also poses barrier for the rapid transitioning of the organization to develop other innovative developments.

code coder coding computer
Photo by Pixabay on


Android based application for rapid detection of biotic / abiotic stress in Agricultural plants

Some two decades back when my sister, Meera was working for her Doctoral Thesis titled “ Gene Identification and Extraction for Salt Stress in Paddy Plants”, I was super excited with the topic as I knew salt stress tolerant species will help a lot to farmers. It continues to be a hot topic even today given that majority of agricultural lands are susceptible to either drought or salt stress due to both biotic (like Sudden Death Syndrome) and abiotic factors (Iron deficiency Chlorosys).

Photo by sohail na on


Applications of TensorFlow, Soil Moisture and NoIR sensors for Plant Health monitoring

For the past many days my wife has been complaining that her sacred plant (Tulasi – Scientific Name – Ocimum sanctum) is getting dried up due to intense heat. Thanks to urban heating effect. She tried many ways of managing the plant but her busy schedule always hinder in getting real time view of the moisture level and other conditions. I was teased to find a solution to resolve this given that I spend time with IoT and Data Science or Big Data jargons. I tried a variety of tools starting with Moisture sensors, NoIR for NDVI calculation to TensorFlow based image classification to come of with solution.

closeup photo of sprout
Photo by PhotoMIX Ltd. on


Virtual Assistant for Real Time Agricultural Insights – An example using Jasper, Alexa & Google AIY

On Day to day basis farmers needs weather insights as well as storage conditions at various storage units. They need real time insights on different agriculture related information. One of the options is for a tailored virtual assistants which can interact with users and internet sites on a regular basis giving insights. In this blog I tried to give an overview of different virtual assistants which are available both commercially and also open source level and how to develop/tailor one based on user needs.

windows_IoT (more…)