Prompting is a free, experimental tool for browsing and building prompts for scientific work. By checking the box and clicking Agree, you accept these terms.
The prompts here, and anything an AI produces from them — including the meta-prompt generator's output — may be inaccurate, incomplete, or misleading. Verify anything important. Nothing here is professional, scientific, medical, or legal advice.
The library and the deterministic builder run entirely in your browser; nothing you type into them is sent anywhere. Only the meta-prompt generator sends the text you enter to third-party AI providers (via the Vercel AI Gateway). Do not enter confidential, personal, proprietary, or unpublished information into it.
This site counts page views and a few actions (that a prompt was copied, or that the generator ran and whether it succeeded) with Vercel Web Analytics. It sets no cookies; visitors are counted with an anonymous hash that is discarded after 24 hours. Nothing you type is included.
The app is provided “as is,” without warranties of any kind. It may be slow, rate-limited, unavailable, or discontinued at any time. To the maximum extent permitted by law, James M. Dewar is not liable for any damages arising from your use of it.
The prompt texts in this library are drawn from the author's CC BY-NC 4.0 work and may be adapted for non-commercial academic use with attribution. The app itself — its design, interface, and code — is owned by James M. Dewar; you may not copy, reverse-engineer, redistribute, or create a derivative of the app. This does not restrict separately-licensed open-source components, which remain under their own licenses.
These terms may be updated; significant changes will ask for your agreement again.
Fill in the blanks, reword the prompt, copy, and share. Switch prompts from the list.
When to use: When a conversation has grown long and the model is getting less reliable.
Click in the prompt to reword it, then copy.
Run at the end of a long thread, then paste the output into a brand-new chat. (Conversations help humans but accumulate context that degrades models.)