Published October 17, 2025
| Version v2
Poster
Open
Effective AI Prompting Strategies from the Humanities
Description
Poster to support successful prompting by teachers and researchers.
Good AI prompts are essential to predictably and consistently getting a desired output.There are no single phrases that work across all situations - AI will simply amplify the user’s capabilities, creativity, judgement and discernment.
These effective prompting strategies will help develop your own skills and strategies with AI prompting.
Text:
- Start with a goal: what is the single thing you are trying to achieve?
- Add context and details: requirements, instructions and parameters. AI needs clear scaffolding so it’s set up for success. Don’t ask it to search for facts - it’s not a search engine.
- State your role, so it knows what register to use. The use of words influences its sample and response. Tell it what you want and who the output will be for.
- Work as thinking partners: Tell the AI to “Ask me one critical question at a time until we achieve our goal”
- Check for clarity: Include a final sentence for the AI to scaffold the task to make sure what you said is what you meant. “To begin, please functionally decompose the task.”
- Use examples. AI is effective at imitation, and if you give it a few examples of what you want, it can copy their form.
- Longer prompts, rather than shorter: Make sure that you provide all the details it needs. Edit your prompts if errors occur, or start over.
- Clear expectations: At the end of each prompt, end with a single, specific task.
- Have a real conversation: Go back and forth a few times before you reach your answer. Asking it to ask you for clarification highlights blank spots in your thinking.
(Also, you can prompt it to help you design prompts...) - Avoid “AI-slop” - Would you be comfortable putting your name to this? Have you interacted using some effort? Make sure you know enough to be able to validate the output.
Files
AI Prompts_V2.pdf
Files
(129.4 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:19ef45450fba03deff6ac802ae6501c0
|
129.4 kB | Preview Download |