Dust

Dust is a prompt engineering tool built for chaining prompts together. They provide a web interface for writing prompts and chaining them together.

At the moment, it has a steep learning curve compared to other prompt engineering IDEs.

Features

Dust provides robust tooling in the form of a number of composable "blocks", for functions like LLM querying, code snippets, and internet searches. Dust also supports the use of datasets and automatically testing prompts against datasets.

Current Dust functionality focuses on chaining prompts rather than iterating on a single prompt.

Dust supports multiple model providers: (OpenAI, Cohere), and has planned support for HuggingFace and Replicate. API keys are required for all providers.

You can deploy LLM apps built in Dust.

Notes

Dust has recently reached 1,000 active users.

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.