LEADERSHIP INSIGHTS

Prompt Engineering: Getting Better Results from AI

Prompt engineering is the ability to design clear and structured inputs that guide AI tools to produce useful outputs. As AI becomes part of everyday work, the quality of results depends heavily on how instructions are given. This hot topic explores how prompt engineering improves outcomes, supports better thinking, and reduces risks when using AI.

KB logo
Nawal Missi
Skills Coach | Mon 20 Apr
Share
Prompt Engineering: Getting Better Results from AI

AI tools are increasingly used across organisations to support tasks such as writing, research, planning, and analysis. While these tools offer significant efficiency gains, their outputs are highly dependent on how they are instructed. A key principle has emerged: the quality of output is shaped by the quality of input. Prompt engineering refers to the structured design of inputs that guide AI systems to produce relevant and accurate responses. Research into large language models demonstrates that even small variations in phrasing and structure can significantly influence outcomes (Brown et al., 2020). This highlights that effective use of AI is not solely a technical capability, but a reflection of how clearly users define problems, provide context, and communicate expectations. As AI becomes more embedded in everyday work, prompt engineering is increasingly recognised as a core skill that supports accuracy, consistency, and informed decision-making.

Prompt engineering can be understood as a form of structured communication with AI systems, where the user provides instructions that shape how the model interprets and responds to a task. Unlike traditional programming, where logic is explicitly defined, prompt engineering relies on language, context, and examples to guide behaviour. This has led to it being described as a form of “programming with language”, where the clarity and structure of instructions directly influence performance (Reynolds and McDonell, 2021).

The importance of prompt design is grounded in how large language models operate. These models identify patterns in the input they receive and generate outputs based on those patterns. Research shows that providing structured prompts or examples, known as few-shot prompting, can significantly improve accuracy and consistency (Brown et al., 2020). This reinforces that AI systems do not inherently “understand” tasks in the way humans do but instead rely on the quality of guidance they are given.

The effectiveness of prompt engineering is particularly evident in everyday workplace applications. AI tools are commonly used to draft communications, summarise information, generate ideas, and support decision-making. In each of these contexts, poorly designed prompts can result in outputs that are vague, misleading, or incomplete. Conversely, well-structured prompts that clearly define the task, provide context, and specify expected outcomes are more likely to produce relevant and reliable results.

Research into prompting methods highlights several characteristics associated with effective prompts. Clear and specific instructions reduce ambiguity and help the model focus on the intended task. Providing context ensures that outputs are aligned with purpose rather than generic responses. Structuring prompts, for example by breaking tasks into steps or specifying formats, has been shown to improve reasoning and output quality (Wei et al., 2022). Furthermore, prompt engineering is inherently iterative, requiring users to refine and adapt inputs based on the outputs generated (Liu et al., 2022).

Despite its benefits, prompt engineering is often applied inconsistently. A common limitation is the assumption that AI systems will infer meaning or intent without sufficient detail. This can lead to outputs that appear plausible but contain inaccuracies or unsupported assumptions. Guidance on human-AI interaction emphasises the importance of clarity, feedback, and evaluation when working with AI systems, highlighting that users remain responsible for interpreting and validating outputs (Amershi et al., 2019).

There are also broader risks associated with the use of AI that prompt engineering alone cannot resolve. Large language models can reflect biases present in training data, generate incorrect or fabricated information, and lack transparency in how outputs are produced. Research into foundation models identifies these risks as significant considerations, particularly in contexts where outputs inform decisions or are shared with stakeholders (Bommasani et al., 2021). As such, prompt engineering should be understood as a tool for improving outputs, rather than a substitute for critical thinking or validation.

Ultimately, prompt engineering represents a shift in how individuals interact with technology. Rather than simply using tools, users are required to think more deliberately about how they define tasks, structure information, and communicate expectations. This positions prompt engineering not as a technical skill in isolation, but as an extension of core capabilities such as problem-solving, communication, and analytical thinking.

Select a task you regularly complete using AI, such as writing or summarising information. Create two versions of a prompt: one basic and one structured with clear instructions, context, and expected output. Compare the results and identify how changes in the prompt influenced accuracy and usefulness. Use this to refine your approach and improve future outputs.

Prompt Engineering Checklist
Effective prompt engineering requires clarity, structure, and critical evaluation. This checklist supports the development of prompts that generate accurate, relevant, and reliable outputs when working with AI tools.

Before using AI for any task, review your prompt against this checklist and refine it to ensure clarity, context, and structure. After generating an output, critically evaluate its accuracy, relevance, and potential risks before use. Capture what worked well and refine your prompt over time to build a consistent and reliable approach.

                       
          Clarity        
                 
  • Define the task precisely, avoiding vague or open-ended language that could lead to inconsistent outputs.
  •          

          Context

                 
  • Provide sufficient background, purpose, and audience to ensure the response is relevant and appropriately framed.
  •          

          Structure

                 
  • Organise the prompt logically, breaking complex tasks into clear steps or instructions where needed.
  •          

          Output

                 
  • Specify the expected format, level of detail, and style to guide consistency in responses.
  •          

          Assumptions

                 
  • Identify and minimise assumptions by explicitly stating constraints, definitions, or boundaries.
  •          

          Validation

                 
  • Critically assess outputs for accuracy, completeness, and alignment with the original task before use.
  •          

          Iteration

                 
  • Refine prompts based on results, recognising that effective prompting is an iterative process.
  •          

          Risk Awareness

                 
  • Consider potential bias, inaccuracies, or ethical concerns within the output and how they may impact decisions.
  •          

          Ownership

                 
  • Take responsibility for how outputs are interpreted, used, and communicated within your context.
  •          

          Reflection

                 
  • Capture effective prompts and lessons learned to improve consistency and efficiency over time.
  •          

Related Post

Applying AI in the Workplace: Tools, Decision-Making, Human Judgement and Decision Support
Insight

Applying AI in the Workplace: Tools, Decision-Making, Human Judgement and Decision Support

AI is often presented as a fast route to better decisions, smarter work and efficiency. The evidence is more cautious. Organisations may invest heavily but still report limited business gains, partly because implementation needs more than technology alone (Reim et al., 2020). AI can support knowledge management by speeding up information collection and interpretation, but it struggles with tacit knowledge and can amplify problems in decision-making rather than reduce them (Trunk et al., 2020). This means responsibility does not disappear when AI is introduced. It shifts. Leaders and teams need transparency about how outputs are produced, literacy to choose appropriate applications, and training to interpret results responsibly. Cultural alignment also matters, because AI changes work practices and can trigger resistance and ethical concerns.

KB logo
Jay Dehaan

Wed 15 Apr

The importance of theory in coaching: A lifelong journey, not just a skill
Insight

The importance of theory in coaching: A lifelong journey, not just a skill

This question is understandable. Coaching is not just about acquiring a set of tools, it’s about developing a way of thinking, being, and relating to others. While practical application is essential, understanding the theoretical foundations of coaching is what sets truly transformational coaches apart.

KB logo
Abz Salloum

Thu 20 Feb

Using AI to Improve Productivity and Reduce Manual Effort
Insight

Using AI to Improve Productivity and Reduce Manual Effort

Advances in artificial intelligence are transforming how work is performed across sectors, with growing interest in its ability to improve efficiency and productivity (Naqbi, Bahroun and Ahmed, 2024). Generative AI in particular enables the autonomous creation of content such as text, images, and data outputs, supporting a wide range of professional activities (Naqbi, Bahroun and Ahmed, 2024). Its use is associated with automating tasks, improving data analysis, and assisting decision-making processes (Naqbi, Bahroun and Ahmed, 2024). However, productivity gains are not automatic. Research shows that outcomes depend on how technologies are implemented and combined with existing workflows and systems (Bughin, 2026). While AI can improve task execution and reduce manual effort, its effectiveness is shaped by organisational design, supporting tools, and how work is structured (Bughin, 2026). Understanding these conditions is critical to using AI effectively in practice.

KB logo
Jay Dehaan

Mon 20 Apr

Trusted by over 700 organisations
and more than 2,000 learners

“The quality of support I have received from my coach has been extremely high. His coaching is considered, tailored and aligned to my personal experience, career stage as well as my day-to-day balancing of responsibilities. My apprenticeship has helped to bolster my confidence that I am taking a reasonable approach with some challenging clients.”

“The apprenticeship with KnowledgeBrief was transformative, improving my leadership, strategic decisions, and confidence. I gained skills in planning, change management, financial acumen, and stakeholder engagement. Completing with distinction, I secured a new contract and expanded my consultancy.”

“The coaching course through KnowledgeBrief was well-structured, balancing theoretical and practical knowledge. The platform is easy to navigate, providing access to support and promoting a solid understanding of coaching fundamentals. The resources provided have been comprehensive.”

“KnowledgeBrief has great content and is detailed in the area I am developing in. The system is very clear and easy to use and navigate. Thanks to my Skills Coach for his support and guidance. I apply my course knowledge and experience, such as team performance, leadership styles, and the Eisenhower Matrix, to manage tasks effectively.”

“The apprenticeship has greatly enhanced my understanding of strategic work and how different areas of the organisation operate. It has boosted my confidence to ask questions and take on senior-level tasks. Studying has pushed me out of my comfort zone, showing me my capabilities and improving my overall performance.

“The support has been timely and professional and, since starting, I have increased my knowledge through the online platform and workshops. I'm covering subjects like business understanding, communication, and operational plans - which has boosted my confidence. I have thoroughly enjoyed the experience and would recommend it.

“As a result of this apprenticeship, I have gained confidence at work. I've developed key skills in project management, communication, and technical processes, and have improved my performance through focused feedback. I am now better prepared to contribute to the team's goals and tackle future challenges.”

“I have seen positive work improvements using what I’ve learnt about leadership, communication, and decision-making. I highly recommend the easy-to-use KnowledgeBrief platform with visual progress tracking, extra resources, and valuable information.”

“This journey has strengthened my strategic vision, stakeholder management, team and organisational influencing skills, and, most importantly, my confidence in communication. The structured learning and the tailored guidance has proven invaluable in giving me direction and purpose as a senior leader.”

“This course improved my performance by helping me create strategies, demonstrate values, develop my team, identify growth areas, and gain leadership principles like communication, conflict resolution, and strategic thinking. I highly recommend it to anyone looking to strengthen their leadership abilities and make an impact.”

Equip your employees with the skills to increase results

If you would like to discuss how we can create your Leadership and Management Training Programmes, please get in touch