Lesson 1, Prompt Engineering Module
In this 30-minute session, we explored the foundations of effective prompt engineering using our 10/10/10 format: instruction, demonstration, and practice. The core focus was the CRAFT framework, a systematic approach to writing prompts that consistently generate high-quality AI outputs. We also examined common pitfalls that prevent people from getting the results they need, and introduced practical techniques for immediate improvement.
This session is part of our “Your Journey from AI Curious to AI Confident” programme, designed to equip Cambridge staff with practical AI skills they can apply immediately in their daily work.
What is the CRAFT framework?
CRAFT is a five-component framework that transforms vague requests into precise, effective prompts. Each letter represents a critical element:
Context provides the background and situation. Rather than asking “Write an email,” you might specify “I need to inform our department about a policy change affecting annual leave.”
Role defines who the AI should act as. This might be “Act as an experienced HR communications specialist” or “Respond as a technical documentation writer.”
Action states the specific task to complete. Be explicit: “Draft a 200-word email announcement” rather than “Help me with this.”
Format specifies the structure of the output you need. Do you want bullet points, a formal letter, a table, or JSON data? State this clearly.
Tone sets the voice and style. Should the output be formal, conversational, technical, or empathetic? This prevents mismatches between your needs and the AI’s response.
When you combine these five elements, you create prompts that consistently deliver relevant, appropriately structured results. The framework is flexible—not every prompt requires all five elements, but considering each one significantly improves your outcomes.
Why does good prompting matter?
Good prompting is fundamentally three things: a skill, a multiplier, and an investment.
As a skill, prompting is something anyone can learn. You don’t need technical expertise or programming knowledge. Like any communication skill, it improves with practice and awareness of effective techniques.
As a multiplier, better prompts generate exponentially better outputs. A vague prompt might save you 10 minutes, whilst a well-crafted prompt using the CRAFT framework might save you hours and deliver precisely what you need on the first attempt. The difference between adequate and excellent prompting can determine whether AI becomes a minor convenience or a transformative tool in your workflow.
As an investment, the time you spend developing effective prompts pays dividends. Once you’ve created a strong prompt template for a recurring task—whether that’s summarising meeting notes, drafting reports, or analysing data—you can reuse and refine it indefinitely. This transforms prompt engineering from a task into an asset.
What’s the biggest mistake people make?
Three common mistakes prevent people from getting good results, but they’re all easily corrected once you’re aware of them.
Ambiguous language is perhaps the most frequent issue. Phrases like “Make it better” or “Write something professional” mean different things to different people. AI cannot read your mind, so vague instructions produce vague results. Specificity is your friend.
Assuming prior knowledge creates problems when you reference information the AI doesn’t have access to. Unless you’ve provided context within the conversation, the AI cannot know about your organisation’s internal processes, your team’s current projects, or your personal preferences.
Chaining too many tasks overwhelms even sophisticated AI models. Asking the AI to “Research this topic, write a report, create a presentation, and suggest three follow-up projects” in a single prompt typically produces mediocre results across all tasks. Break complex workflows into sequential, focused prompts instead.
This post is part of the Cambridge AI Lunch & Learn series, a 24-week upskilling programme designed to transform participants from AI curious to AI confident. Through bite-sized
30-minute weekly sessions, we’re building practical AI literacy across Cambridge University Press & Assessment, equipping our team with the skills to work effectively and ethically with artificial intelligence.
Each session follows a proven learn-by-doing approach: 10 minutes of instruction, 10 minutes of demonstration, and 10 minutes of hands-on practice. This isn’t about becoming AI experts but rather it’s about understanding how to augment our work, make better decisions, and navigate the evolving landscape of AI tools with confidence and responsibility.