The emergence of Prompt Engineering offers software developers a distinct chance to enhance efficiency. However, this opportunity only materializes when they possess the requisite skills to precisely define requests, maintain clarity in process management, and establish transparent policies shared with clients.
Prompt engineering, the process of crafting AI inputs for optimal outputs, also known as in-context learning, is swiftly becoming integral for software development firms. In a world where AI increasingly influences our professional landscape, individuals proficient in prompt engineering are indispensable.
According to McKinsey , approximately half of current work activities could be automated by 2030 to 2060, nearly a decade earlier than their earlier projections. They also suggest that gen AI and other technologies have the potential to automate work activities currently occupying up to 70 percent of employees time.
Harnessing this trend and capitalizing on the efficiencies facilitated by smart AI utilization can greatly advantage companies. Nonetheless, its crucial not to ignore certain challenges associated with this transition.
Head for Architecture and Technology at Global Kinetic , Dewald Mienie, One of the big challenges for software developers is getting stuck on an AI hamster wheel. Developers, especially less experienced developers, may ask ChatGPT to generate a piece of code. If the generated code is not exactly what they need, they get stuck in a loop refining the prompt in an effort to reach the right answer. In this case it would clearly have been easier to simply write or amend the code themselves. It takes some experience and insight to maximise the value from AI.
Mienie emphasizes the importance for developers to prioritize efficiency gains by striking the appropriate balance between AI utilization and manual coding. Experienced developers are better equipped to achieve this balance as they can compare their AI-assisted output with their previous methods.
He also cautions that large language models (LLMs), such as ChatGPT, may struggle with self-correction. In such cases, if an inexperienced developer requests something and later discovers an error in the response, asking for a correction could result in a loop of inaccuracies. With each correction, the requested element may be fixed, but a new mistake could be introduced. Without setting a time limit on this process, developers risk wasting time and escalating development costs.
Building accountability and security with robust policies
Mienie suggests that every business should establish an AI policy, with particular emphasis on its importance for software development firms.
Its vital to have an accountability clause in your AI policy. This means that every person who uses AI acknowledges that they are responsible for what the AI generated. As the user you must be able to validate what the AI has generated for you and be able to back it up with the necessary references. AI must always attract the same quality checks and balances as human-generated code, going through the same DevSecOps process including vulnerability scanning to ensure the code is secure. Thorough code reviews must continue. AI is simply there to accelerate the coding process and teams must be aware that, just as if they were writing the code themselves, they are responsible for the quality of the work submitted, he explains
A balanced, risk-based strategy for safeguarding intellectual property (IP) is essential, according to Mienie. Each scenario should be assessed independently, with AI employed only when suitable, ensuring constant protection of the clients IP. This is particularly critical in sectors like financial services, where code should never be divulged on a public platform such as an LLM. Additionally, Mienie recommends proactively sharing the companys AI policies with clients at the outset of any engagement to foster trust between partners from the outset.
The whole company can benefit from good prompt engineering
Mienie observes that AI is successfully employed across various industries to aid in ideation and marketing campaigns, enhancing efficiencies across multiple business domains. Even within these functions, the principles of effective prompt engineering remain applicable.
By giving the LLM information of your role as well as the kind of company you are working for you are giving it the context it needs to formulate an appropriate response. The AI can only provide a response based on the data it was trained on and therefore you need to augment this by providing the extra information in the prompt. At the same time, you need to be cognisant not to leak sensitive information as one is prone to provide more and more information to improve the response. Mienie shares Summing up, Mienie says prompt engineering has a gr
