Short Version Meta-Prompt: Create a Prompt from a Planning Template
Use Case
Instructors use a completed planning template as the basis for generating an instructional chatbot prompt. The chatbot helps systematically translate instructional goals, the division of responsibilities, the conversation flow, subject-matter foundations, and technical constraints into clear instructions for a chatbot. To do this, it first checks the worksheet for significant gaps or inconsistencies, asks follow-up questions as needed, and then produces a prompt adapted to the target model and language. The output consists of the finished prompt, along with assumptions and testing checkpoints. The short version is particularly suitable for simple, manageable use cases or less capable models and is part of a set of resources for prompt development.
Example Prompt
Turn my completed planning template into a ready-to-use instructional chatbot prompt for higher education or teaching.
The planning template contains questions, explanations, and entries labeled “Response:”. Treat only the information following “Response:” as decisions I have made; the remaining text is for guidance only.
Follow the information especially closely regarding the objective and target audience, the work users are expected to do themselves, the type and limits of chatbot support, the subject-matter basis, the information needed and when it should be requested, the conversation flow and desired outcome, and—if completed—the information in Block B.
If essential information is missing or entries are inconsistent, ask no more than three brief follow-up questions, one at a time. If a remaining gap is not critical, make a minimal assumption and later include it as a testing checkpoint.
Adapt the prompt to the target models specified under “Technical Constraints.” If multiple target models are listed, write a version that is as concise and robust as possible and can also work with the more limited model. Do not invent instructional or subject-matter requirements that do not follow from my responses.
Also make sure the generated prompt instructs the chatbot to gather necessary context at the appropriate time, follow the planned conversation flow, preserve the intended work users are expected to do themselves, ask follow-up questions when responses are unclear, avoid inventing uncertain facts, and conclude the conversation as specified.
At the end, output exactly:
(a) the finished prompt in a code block;
(b) a brief list of assumptions and points that should receive particular attention during testing.
Here is my completed planning template:
[Paste the planning template here]