We took all the best practices of prompt design and put them in one collaborative canvas.

During the construction of AI products and workflows, we had repeatedly encountered the same problem. The management of entries as a team and testing different formats was chaotic. Most of the time we juggled Chatgpt/Claude and Google Docs to pursue versions and to be errors. In addition, there is an overwhelming amount of papers, blogs and topics on how we write effective input requests (to which we constantly tried to refer). So we pulled everything into a single canvas to experiment, manage and improve the prompt. I hope this is swinging with some of them ... would like to hear how others manage a growing list of entries. If you want to learn more or try it out ... www.sampler.ai transmitted by /u /ononegaybus