Background: With the increase in the application of Artificial Intelligence, there is an urge to find ways to increase the development speed of these systems (time-to-market). Because time is one of the most expensive and valuable resources in software development. Faster development speed is essential for companies to survive. There are articles in the literature that states the factors/antecedents for improving the development speed in Traditional Software Engineering. However, we cannot draw direct conclusions from these factors because development in Traditional Software Engineering and Artificial Intelligence differ.

Objectives: The primary objectives of this research are: a) Conduct a literature review to identify the list of factors that affect the speed of Traditional Software Engineering. b) Perform an In-depth interview study to evaluate whether the listed factors of Traditional Software Engineering can be applied in accelerating the development of AI systems engineering.

Methods: The method chosen to address the research question 1 is the Systematic Literature Review. The reason for selecting Systematic Literature Review (SLR) is that we follow specific well-defined structure to identify, analyze and interpret the data about the research question with the evidence. The search strategy Snowballing is the best alternative for conducting SLR as per the guidelines are given by Wohlin. The method chosen to address the research question 2 is an In-depth interview study. We conduct interviews to gather information related to our research. Here, the participant is the interviewee, who may be a data scientist or project manager in the field of AI and the interviewer is a student. Each interviewee lists the factors that affect the development speed of AI systems and rank them based on their importance using Trello.

Results: The results from the systematic literature is the list of papers that are obtained from the snowball sampling. From the collected data, factors are extracted which are then used for the interviews. The interviews are conducted based on the questionnaire that was prepared. All the interviews are recorded and then transcribed. The transcribed data is analyzed using Conventional Content Analysis.

Conclusions: The study identifies the factors that will help accelerate the development speed of Artificial Intelligence systems. The identified factors are mostly non-technical such as team leadership, trust, etc. By selecting suitable research methods for each research question, the objectives are addressed.