What is a prompt?

A prompt is the instruction you provide Clarity or any commercial chatbot to obtain the appropriate response or output you desire. You may want a draft of an email, a summary of a document, or suggestions of study questions to help students prepare for a quiz. The prompt is how you relay your requirements to an agent or chatbot.

You can think of the prompt as a recipe -  the details you provide to the agent are the list of ingredients and cooking instructions.

However, the ingredients alone don’t determine the merit of the meal – the quality of those ingredients, and how they are used, directly impact the excellence of the result. Prompts work the same way – quality prompts produce quality responses. A quality prompt requires clear, specific instructions to get the best results. By following a few core principles, you can significantly improve the quality, relevance, and usefulness of the agent’s responses.

How would you like Clarity to respond?

One way to write an effective prompt is to break the prompt down into the following components:

Goal: What response do you want from the agent? 

Context: Why do you need it  and who is involved? 

Source: Are there sources of information that the agent should include, or an example it should follow?

Expectations: How should the agent respond to best meet your expectations? 

Sample prompt:

Goal: Help drafting an email. 

Context: You had a lot of people apply for your fellowship program and you cannot accept them all. 

Source: If the agent supports file uploads, you might upload a sample email for the agent to follow, or paste those details into your prompt.

Expectation: The email should express gratitude for the applicant’s interest and should have a kind tone.

PROMPT: “Our department recently received an overwhelming number of applications for our upcoming fellowship program. However, we cannot accept everyone. Please help me draft an email to send to those people who were not accepted. The email should express gratitude for their interest and should have a kind tone. Please use the email I have uploaded to this chat as a reference for your response.”

Other things to consider:

State your specific role when that information is relevant to the response you want to receive.

EXAMPLE: “I am a professor at Yale University and am currently brainstorming ideas for a lesson plan on [TOPIC]. Will you please assist me in generating class exercises for first year students?”

Provide specifics about how you would like the response formatted:

  • “Provide 5 bullet points”
  • “Write a 200-word summary”
  • “Create a step-by-step process”

Provide enough context:

  • Explain the background situation
  • Mention your audience or purpose
  • Include any constraints or requirements

Iterate and revise: If the first response from the chatbot isn’t perfect, you can pose follow-up questions or ask for specific changes like “Can you make the tone more formal?” or “That’s a good start, but can you focus more on [Specific Aspect]?” 

Pay attention to the kinds of revisions you routinely ask of the agent, because this will also help you improve the initial prompts you enter.

Best Practice: Start a New Conversation

We recommend starting a new conversation when you shift to a different topic, task, or project. This helps ensure optimal performance and relevant responses from the agent.

Why this matters:

  • Improved accuracy: Starting a new conversation allows the agent to focus on your current topic without being influenced by unrelated previous exchanges.
  • Optimal performance: Shorter, focused conversations help the agent provide more precise and helpful responses. Longer conversations may result in decreased accuracy and unexpected issues.

When to start a new conversation:

  • Changing subjects (e.g., switching from analyzing literature to writing code)
  • Beginning a new assignment or project
  • Addressing a different course or research area
  • When the conversation becomes lengthy or unwieldy
  • If responses seem less relevant or the AI appears to misunderstand your current context

When continuing is fine:

  • You’re building on the same topic or task
  • Following up on previous responses with clarifications or refinements
  • Working through multiple steps of the same project

More prompt examples

You can use these principles to craft prompts for a variety of academic and administrative tasks. (Some of the examples below mention file uploads, which are currently supported in all of Clarity’s featured agents.)

Content Generation & Brainstorming 

  • “I need to reply to an email in a friendly, professional tone reminding the student to check the syllabus and encourages them to attend office hours. Here is the email I am responding to: [PASTE EMAIL CONTENT]”
  • “I am a TA for a history seminar. Help me brainstorm discussion points and group exercises based on the attached reading.” [UPLOAD DOCUMENT].

Summarization & Analysis (with Document Uploads)

  • “Please read the attached syllabus and brainstorm a scavenger hunt activity to engage students with the course policies.” [UPLOAD SYLLABUS]. 
  • “Please summarize the key findings and suggest three methods for statistical analysis for the lab data in the spreadsheet I have uploaded.” [UPLOAD SPREADSHEET].

Transformation & Formatting (with Data or Images)

  • “Transcribe the text from this image of my handwritten notes , organize the content by theme, and summarize the key points in a six-slide presentation.”[UPLOAD IMAGE]
  • “Each row in this spreadsheet represents a conference session. Create a PowerPoint deck with a title slide and one slide for each row, using columns [X, Y, and Z]. Export in .ppt format.” [UPLOAD SPREADSHEET].

Coding Assistance

  • “Act as an expert Python programmer and review the  code I have pasted below. Find and correct any errors and add annotations explaining how each function works. Here is the code: [PASTE CODE].
  • “Write a Python script to perform a regression analysis on the uploaded dataset.” [UPLOAD DATASET].