When GenAI tools like ChatGPT initially emerged, we were all astounded by their utility, even in the absence of formal instructions on their usage.

Over time, the concept of prompt engineering began to surface, signifying the art of crafting effective questions. 'Prompt'—referring to an instruction given to an artificial intelligence program—was second place in Oxford's 'Words of the Year' for 2023, trailing only behind 'RIzz' announced just before Christmas.

As we progress, prompt engineering is evolving into a more intricate discipline, prompting businesses to contemplate how to cultivate their organisation's proficiency in crafting prompts.

In this blog post, we'll briefly look at both basic and advanced aspects of prompt engineering before exploring the strategies necessary to nurture organisational expertise in prompt utilisation.

Exploring Basic Prompt Engineering

For those unacquainted with prompt engineering, consider the following examples to grasp its essence:

Weak prompt: "Tell me about change management."

Improved prompt: "Describe the necessary change management strategies for implementing new technology in the aerospace industry."

It's evident that providing specificity yields superior results. Moreover, there exists a myriad of effective prompts we might initially overlook, including:

• "Offer examples illustrating how to approach ____."
• "Feel free to seek clarification through questions before responding."
• "Imagine yourself in the role of the CFO."

Undoubtedly, fostering employees' foundational prompt engineering skills is crucial for optimizing the potential of Generative AI.

Advancing Prompt Engineering: Transitioning to Sophistication

In recent times, we've surpassed the realm of basic prompts, venturing into a realm of heightened sophistication. Rather than viewing prompts merely as questions, we propose conceptualizing them as briefings akin to those provided to consultants.

A briefing might look like this:

Define the goal: I need a detailed step-by-step plan to convince my CFO that increasing pay will reduce turnover.

Describe your situation: I’m new in the job and need to visible win. I want to do something to show I’m business savvy.

Give the context: We have four small but fashionable hotels in Austin, Texas. Our turnover is always about 20% higher than industry norms. Not only does this affect recruitment and training costs; I think it shows up in customer satisfaction. –

Explain what you want the output to be: Can you give me three different ways of approaching this? Show step-by-step in bullet points how I might make the pitch to the CFO.

This kind of advancing prompting technique not only gives impressive results, it helps us reframe our understanding of just what kind of entity a GenAI is.

Chain-of-Thought Prompting: A Strategic Approach

An advanced technique gaining traction is "Chain-of-Thought" prompting, which diverges from the conventional method of posing a single question. Instead, it involves guiding the GenAI through a sequential thinking process, akin to collaborative problem-solving with a peer.

Picture initiating a discussion with a colleague: "Let's tackle this systematically. First, let's outline what we understand about the situation..." and proceeding step by step.

Remarkably, this method can be replicated when interacting with a GenAI. You give the AI model one prompt after another, with each prompt building on the one before it. This keeps the model on track, giving you greater control of the output.

Is Advanced Prompt Engineering Necessary?

While the need for sophisticated prompt engineering may not be universally applicable, it's crucial for every individual within an organization to possess fundamental knowledge of basic prompt techniques. Access to essential tools like conversational Generative AI should be democratized to enhance productivity and foster innovation across all levels.

Now, let's address the practicality of sophisticated prompt engineering. Do we truly require increasingly advanced techniques in this domain?

Admittedly, for most individuals, advanced prompt engineering may seem unnecessary, much like the intricate features of Excel that many users seldom utilise.

However, for the organisation as a whole, overlooking advanced prompt engineering equates to overlooking the full potential of GenAI. It's imperative to have individuals who recognize that certain situations warrant leveraging the complete capabilities of our GenAI tools, yielding superior outcomes.

Emphasizing Communities of Practice

Consider this: while basic statistics can be learned through conventional means like courses or textbooks, prompt engineering is an evolving discipline, continually shaped by practice and innovation. Staying current in this realm is challenging when undertaken individually.

Therefore, organisations must foster communities of practice, where motivated individuals learn from one another, collectively advancing the organisation's proficiency in areas like prompt engineering. The Learning and Development department is ideally positioned to spearhead this initiative.

By establishing and supporting communities of practice, L&D can facilitate knowledge exchange and skill enhancement, addressing evolving domains such as prompt engineering more effectively. This approach requires minimal intervention and can be seamlessly integrated into existing workflows.

While it's plausible that GenAI might eventually surpass human capabilities in prompt engineering, until that point, it's essential to empower human employees to develop internal expertise and capabilities.

In essence, let's provide the necessary support and encouragement for your employees to cultivate expertise in prompt engineering, ensuring that your organisation remains at the forefront of AI utilization. Contact us via email at info@digitalbricks.ai to schedule a complimentary consultation and explore how we can help your teams stay competitive.

‍