• Written by Azhar Aliyar, Director

In practice, a quality deployment of AsscherAi does not always get the data it needs, despite the system being designed to answer questions about an organisation's own data in real time. This is because the system relies on specific data from various sources, including inspection records, non-conformance reports, batch genealogy, and customer complaints, which are not always available or up-to-date.

The systems

A quality deployment of AsscherAi depends on data from several key systems. Inspection records, for example, provide critical information about the quality of products or services, while non-conformance reports help identify areas for improvement. Batch genealogy, which tracks the origin and movement of products, is also essential for tracing quality issues back to their source. Customer complaints, meanwhile, offer valuable insights into how products or services are performing in the field. A shift supervisor, for instance, might check the maintenance log to identify potential quality issues before they become major problems.

These systems are not just important for answering questions about quality; they are also necessary for identifying trends and patterns that can inform quality improvement initiatives. By analyzing data from these systems, organisations can gain a deeper understanding of their quality performance and make data-driven decisions to improve it.

What a missing system does to an answer

If one of these systems is missing or incomplete, the answers provided by AsscherAi may be inaccurate or incomplete. For example, if inspection records are not up-to-date, AsscherAi may not be able to provide a complete picture of quality performance. Similarly, if non-conformance reports are not properly tracked, AsscherAi may not be able to identify areas for improvement. This can lead to a lack of trust in the system and a failure to identify and address quality issues in a timely manner.

Most people assume that AsscherAi can simply fill in the gaps in the data, but this is not the case. The system relies on the data it is given, and if that data is incomplete or inaccurate, the answers it provides will be similarly flawed. This is why it is so important to ensure that all relevant systems are properly integrated and up-to-date.

The definitions that must be agreed

In order for AsscherAi to provide accurate and useful answers, there must be a clear understanding of the definitions and terminology used in the organisation. This includes definitions of quality metrics, such as defect rates or customer satisfaction scores. If these definitions are not agreed upon, AsscherAi may provide answers that are misleading or confusing. For example, if the definition of a "defect" is not clear, AsscherAi may include or exclude certain types of defects in its analysis, leading to inaccurate results.

Agreeing on these definitions can be a challenging process, especially in large or complex organisations. However, it is essential for ensuring that AsscherAi provides accurate and useful answers. By taking the time to establish clear definitions and terminology, organisations can ensure that AsscherAi is providing the insights they need to improve quality.

Quality problems that only surface later

Some quality problems may not be immediately apparent, but may only surface later in the production process or even after products have been delivered to customers. For example, a problem with a component may not become apparent until it has been in use for some time. AsscherAi can help identify these types of problems by analyzing data from production systems and customer feedback. By tracking quality metrics over time, AsscherAi can help organisations identify trends and patterns that may indicate a quality problem.

These types of problems can be especially challenging to address, as they may require significant changes to production processes or supply chains. However, by using AsscherAi to identify and analyze these problems, organisations can take proactive steps to address them and improve overall quality.

When AsscherAi is not the right choice

While AsscherAi can be a powerful tool for improving quality, it is not always the right choice for every organisation or every situation. For example, if an organisation is just starting to collect data on quality metrics, AsscherAi may not be able to provide useful insights until more data is available. In these cases, other approaches, such as manual analysis or quality control checks, may be more effective. Additionally, AsscherAi is not a replacement for human judgment and expertise, but rather a tool to support and inform decision-making.