PromptQL Specification
PromptQL is a novel approach to connect LLMs to data & systems. PromptQL outperforms search-based RAG, tool calling and multi-agent approaches that rely on in-context orchestration, by using a on-the-fly programmatic approach to compose computational and cognitive tasks.
PromptQL's mission is to ensure that AI connected to business data and systems can realistically be introduced into business operations & workflows.
PromptQL programs can read/write data, or search through data by invoking Python functions. These tools are implemented outside of PromptQL, and should simply be provided as dependencies to the PromptQL program. Here are some typical examples of tools:
PromptQL primitives are AI functions that are available as python functions in the PromptQL program to perform common AI tasks on data. These primitives can create structured information from unstructurd and structured data and allow the composition of "congitive" tasks with "computational" tasks.
For example, a simple search based RAG system can be represented as a PromptQL program with a retrieval function followed by a PromptQL primitive that then generates the result.
