Prompting Frameworks
- High-quality prompts eliminate ambiguity - Clear context upfront gets better responses
- Use structured frameworks - CLEAR or BASE methods ensure complete prompts
- Never share sensitive data - No personal records, confidential research, or security information
High-quality prompts that eliminate ambiguity are crucial for getting useful responses from Large Language Models. By providing comprehensive context upfront, you’re more likely to receive output that matches your requirements.
Scenario: You have been tasked with running a campaign to increase recruitment of European students for your University’s MSc Engineering programs.
You write the initial prompt:
Write something about recruiting students.
Problems with this prompt:
- No context about the university, program, or target audience
- Vague action (“write something”)
- No specifics about format, length, or communication channel
- No examples of desired output
- Unclear what type of recruitment content is needed
We can use some frameworks to standardize our queries and make sure they are complete and don’t forget any relevant details. There’s no right or wrong approach — different frameworks may work better for different AI tools and yourself, so use the one that works better for you.
The CLEAR Framework
The CLEAR framework offers a systematic approach to prompt construction that ensures comprehensive communication with AI models.
Context - Establish the situation and background
- Explain who you are and what you’re working on
- Provide relevant background information about your project or industry
- Include any important constraints or considerations
Length - Define output requirements
- Specify how much content you want (word count, number of items, etc.)
- Indicate format preferences (paragraphs, bullet points, sections)
- Include any structural requirements
Examples - Illustrate desired outcomes
- Show examples of the style or format you’re looking for
- Provide sample inputs or scenarios when relevant
- Include both positive examples (what you want) and negative examples (what to avoid)
Action - State the specific task
- Clearly articulate what you want the AI to do
- Use specific action verbs (create, analyze, summarize, compare)
- Be direct and avoid ambiguous language
- Focus on one primary task per prompt
Role - Define the AI’s perspective
- Specify what expertise or viewpoint the AI should adopt
- Indicate the audience the AI should write for
- Guide the AI’s approach and decision-making framework
A good prompt example using the CLEAR framework:
Context: I work at a UK university’s admissions office recruiting European students for MSc Engineering programs. Brexit has reduced EU applications by 30%. Our university offers excellent industry links, modern facilities, and 95% graduate employment rates within 6 months.
Length: Create a 250-350 word recruitment email with a compelling subject line and clear call-to-action.
Examples:
- Include brief testimonial format: “Maria from Spain: ‘Best decision for my career’”
- Avoid: overly academic jargon or bureaucratic language
Action: Write a digital marketing email to attract European students to apply for our MSc Engineering programs (Mechanical, Electrical, Civil).
Role: Act as an experienced international student recruitment specialist who understands European students’ concerns about studying in the UK post-Brexit. Emphasize our university’s unique value proposition while addressing practical benefits like industry connections, career prospects, and international community. Focus on inspiring confidence in their investment in UK engineering education.
Independently of the prompting framework that you are using, never share these with AI tools:
🚫 Personal data: Student records, staff information, health data
🚫 Confidential research: Unpublished findings, grant applications under review
🚫 Commercial sensitive: Partnership agreements, financial information
🚫 Legal privileged: Legal advice, disciplinary proceedings
🚫 Security sensitive: Passwords, system configurations, access credentials
The BASE Method
The BASE method provides a four-step structured approach to crafting clear, effective prompts for LLMs.
Background - Provide context and set the scene
- Give the AI relevant background information about your situation, industry, or project
- Explain the broader context that will help inform the response
- Include any constraints or important considerations
- Establish the setting and circumstances for your request
Action - Clearly state what you want the AI to do
- Use specific action verbs (analyze, create, summarize, compare, etc.)
- Avoid ambiguous language that could lead to misinterpretation
- Focus on one clear, primary objective
Specifics - Define the details and parameters
- Specify format requirements (length, structure, tone)
- Include target audience information
- Set clear boundaries and scope for the response
Examples - Provide concrete illustrations
- Show examples of desired output format or style
- Include sample inputs or scenarios when relevant
- Use positive examples (what you want) and negative examples (what to avoid) when helpful
A good prompt example using the BASE method:
Background: I work for the admissions office of a UK university with a strong reputation in Engineering. We’re launching a recruitment campaign targeting European students for our MSc Engineering programs (Mechanical, Electrical, Civil Engineering). Brexit has reduced EU student applications by 30%, so we need to emphasize our value proposition. Our university offers excellent industry connections, state-of-the-art facilities, and strong graduate employment rates (95% employed within 6 months).
Action: Create a digital marketing campaign email that will attract prospective European students to apply for our MSc Engineering programs
Specifics:
- Email should be 250-350 words
- Include an attention-grabbing subject line
- Professional yet inspiring tone
- Include clear call-to-action (visit program webpage)
- Target: European students completing Bachelor’s degrees in Engineering
Examples:
- Include testimonials format: “Maria from Spain says: ‘Best decision for my career’”
- Avoid: overly academic language or lengthy program descriptions
Exercise 3: Building Workplace Prompts
Scenario: You’re organizing a workshop on “Digital Skills for Academics” at the University of Bristol.
Task: Create a prompt to help design the workshop agenda.
Requirements:
- Use the CLEAR framework
- Include appropriate constraints
- Maintain academic integrity
Reflection Questions:
- How do your prompts ensure AI enhances rather than replaces your expertise?
- What verification steps would you take for each output?
- How would you attribute AI assistance appropriately?