Lean & Agile Systems Engineering Requires Value Stream Management to Shorten Engineering Cycles

Automation is key to shorter systems engineering cycle times. AI drives automation. Together with the principles of Lean, systems thinking and DevOps they build the foundation for agile systems engineering. The basic concept for accelerating product innovation is the value stream: people, processes and technologies to improve the value flow from idea to delivery to the customer.

In this article we discover the process of identifying and optimizing value streams in cyber-physical systems like cars, and we demonstrate an agile systems engineering Q&A session with the new #ChatGPT assistant of #OpenAI with surprising results.

There's no higher value proposition in the whole body of Lean than the notion of a value stream and value stream management is a label that's kind of recently been applied to making that value stream work efficiently.— Dean Leffingwell 2

The Value Stream is Not in the Ivory Tower

Interesting discussion, but no visible result. This is what happens when practical relevance is missing. Processes designed in the ivory tower usually do not survive contact with reality. Yet the solution sounds quite simple. Jim Womack, co-author of Lean Thinking, never tires of repeating it.1?

Firstly, find a product, as small as possible and sense making for the start. Chances are, you can easily find one on the company website. Secondly, gather all the people, processes and tools involved in getting that product from concept to delivery to the customer (yes, it can be quite a lot people, reducing could be a good next step). Thirdly, map the value stream and conduct all discussions for improvement with this practical reference and let the people that are doing actually the work find and implement ideas for optimization. This is essentially in line with the concept of the Gemba Walk and the five principles of Lean as shown in figure 1 below.

It is not surprising when the number of people involved in an end-to-end value stream exceeds 250, even for a small (sub-)product. That is your autonomous end-to-end team. Far from the ideal agile team size of about seven (two-pizza teams). In addition to rethinking the modular architecture, the use of focus teams that have no other tasks, automation also offers opportunities to reduce the team size. Reviews and approvals, for example, can be replaced with an automated definition of done. All necessary competencies and decision-making power should be distributed to fewer and dedicated people in the team.?

Automation, with test in the loop, brings speed to design, build, test, deploy, daily business decisions, and management.— Joe Justice

Even if this seems difficult from a compliance point of view, companies like Tesla show that it is also possible to work with agile teams and short engineering cycles for safety-relevant systems.

I see Value Stream Management as the application of people, process and technology to improve the flow of value from ideation to customer delivery.— Richard Knaster 2

While it might seem impossible to get to a team size of seven, at least a significant reduction is usually possible. Even if 50 people out of 250 are still needed after the first steps, this is a number that can act better in the value stream as an agile release train.?

Further approaches to reduce cycle times are discussed in the three articles The Seven Drivers of Flow, The Metrics of Flow and Take the Value Stream Walk.

Q&A Session with the new OpenAI driven Chatbot ChatGPT

It's absolutely amazing what AI can do these days. Most of it is under the hood and we don't see it. But even if the AI model is not meant to optimize value streams, the answers below show the potential and are of surprising quality. #chatgpt #openai

What is value stream management?

Chatbot: Value stream management is a process of analyzing and optimizing the flow of materials and information required to bring a product or service from its initial conception to the customer.

What are the activities of value stream management?

Chatbot: The activities of value stream management include identifying and mapping the current state of the value stream, analyzing and optimizing the flow of materials and information, and implementing and monitoring improvements.

What is an end to end value stream in systems engineering?

Chatbot: An end to end value stream in systems engineering is a process that starts with the customer's need and ends with the customer's satisfaction. It includes all the activities that are necessary to deliver a product or service from the customer's initial request to the customer's ultimate satisfaction. This includes activities such as requirements gathering, design, development, testing, and deployment. The goal of an end to end value stream is to identify and eliminate waste and improve efficiency.

What is lean and agile systems engineering?

Chatbot: Lean and agile systems engineering is an approach to systems engineering that focuses on delivering value quickly and efficiently. It emphasizes collaboration, continuous improvement, and customer feedback. The aim is to reduce waste and increase efficiency in the development process. Lean and agile systems engineering is based on the principles of Lean and Agile software development, which emphasize iterative development, rapid prototyping, and customer feedback.

How can cycle times be shortened in systems engineering?

Chatbot: Cycle times can be shortened in systems engineering by focusing on the customer's needs and requirements, streamlining processes, and using automation. Additionally, teams can use agile and lean principles to reduce waste and speed up the development process. Finally, teams can use tools such as version control and continuous integration to ensure that changes are tracked and deployed quickly.

How to measure flow in systems engineering?

Chatbot: Flow in systems engineering can be measured by tracking the time it takes for a feature or product to move from the customer's request to the customer's satisfaction. This can be done by tracking the time it takes for each step in the process, such as requirements gathering, design, development, testing, and deployment. Additionally, teams can use tools such as version control and continuous integration to ensure that changes are tracked and deployed quickly.

Are there other flow metrics that can be applied in systems engineering?

Chatbot: Yes, there are other flow metrics that can be applied in systems engineering. These include lead time, cycle time, throughput, and defect rate. Lead time is the total time it takes for a feature or product to move from the customer's request to the customer's satisfaction. Cycle time is the average time it takes for a feature or product to move through each step in the process. Throughput is the rate at which features or products are completed. And defect rate is the number of defects per unit of work.

Which methods can be used to analyse value streams?

Chatbot: Methods that can be used to analyse value streams include process mapping, process analysis, and value stream mapping. Process mapping is a visual representation of the steps in a process. Process analysis is a systematic examination of the process to identify areas of improvement. And value stream mapping is a tool used to identify and eliminate waste in a process.

How to improve the efficiency of a value stream in systems engineering?

Chatbot: The efficiency of a value stream in systems engineering can be improved by focusing on the customer's needs and requirements, streamlining processes, and using automation. Additionally, teams can use agile and lean principles to reduce waste and speed up the development process. Finally, teams can use tools such as version control and continuous integration to ensure that changes are tracked and deployed quickly.

What does Flow mean in the context of a systems engineering value stream?

Chatbot: Flow in the context of a systems engineering value stream refers to the rate at which features or products are completed. It is a measure of how quickly a feature or product moves from the customer's request to the customer's satisfaction. It can be measured by tracking the time it takes for each step in the process, such as requirements gathering, design, development, testing, and deployment.

Can a Gemba Walk help to improve a value stream?

Chatbot: Yes, a Gemba Walk can help to improve a value stream. A Gemba Walk is a process in which a team walks through the value stream to observe and identify areas of improvement. During the walk, the team looks for ways to reduce waste, improve efficiency, and increase customer satisfaction. By doing a Gemba Walk, teams can gain a better understanding of the value stream and identify areas for improvement. Finally, the team should implement the improvements and measure the results.

The discussion is not to what project is being done or who's working on what but what are we delivering to whom, how good are we at that, how quick are we at that and what do we need to do next to enhance the total value delivered by this construct.— Dean Leffingwell 2?

Recommended Reading: Take the Value Stream Walk

Further approaches to reduce cycle times are discussed in the three articles The Seven Drivers of Flow, The Metrics of Flow and Take the Value Stream Walk.

______________

References

1 Take the Value Stream Walk: Observing and Questioning Your Value Stream is Not a One-Time Affair, Frank Schultheiss 2022, https://www.dhirubhai.net/pulse/go-see-observing-questioning-your-value-stream-affair-frank/

2 Accelerating Time to Market with Value Stream Management and SAFe, DevOpsTV 2021, https://youtu.be/S07FbC4JxO8