Free prompt engineering toolkit

Pick a recurring task, use fictional or anonymised data and fill in the four blocks. Try the prompt, check the answer and note one useful change. Keep the version that works best for that task.

These tags are a practical convention, not a mandatory standard or a defence against instructions contained in documents. Results also depend on the model, inputs and checks. If text includes <, > or &, use &lt;, &gt; and &amp; or a CDATA section in an XML file.

These are original teaching examples with fictional data. The expected outcomes describe how to judge results; they are not measured or recorded model responses.

Free Take Two material: use and adapt the templates for your work and share the toolkit with attribution. Do not resell the toolkit or claim authorship.
https://take-two.net/en/ai-resources/
