Learn PromptingConclusion
This page will be updated as I get access to more IDEs.
This chapter has provided an overview of some of the tools which may be of interest to you as a prompt engineer. Below are my recommendations for which to use, and in what capacity. Keep in mind that prompt engineering is a rapidly evolving field, and many of the previously mentioned tools will undergo signifigant changes in the future.
For Single Prompt Iterating
Everyprompt seems to have the best feature set for single prompt iterating (from the IDEs I have been able to try). Regular playground is also good, and a bit simpler.
For Prompt Chaining
Dust is currently the best (less technical) tool for prompt chaining. It provides a very robust feature set.
Embeds
Dyno is the only tool which offers an embed.
For Full Control
LangChainis the way to go! It is a Python library, so it is fully extensible, and already comes with a great feature set.
More
I will be adding more recommendations as I get access to more IDEs. I recommend trying out different ones, as each has a distinct feel and different features.
Sander Schulhoff
Sander Schulhoff is the Founder of Learn Prompting and an ML Researcher at the University of Maryland. He created the first open-source Prompt Engineering guide, reaching 3M+ people and teaching them to use tools like ChatGPT. Sander also led a team behind Prompt Report, the most comprehensive study of prompting ever done, co-authored with researchers from the University of Maryland, OpenAI, Microsoft, Google, Princeton, Stanford, and other leading institutions. This 76-page survey analyzed 1,500+ academic papers and covered 200+ prompting techniques.