Prompt Stretching: Applying Linear Transformations and Recursive Decomposition to Prompts

Explore a Python library that transforms prompts using linear algebra and recursive decomposition, enabling LLMs to generate other LLMs and build deep research agents.

Overview

I’ll walk through an open source Python library I’m working on where LLMs generate other LLMs as reusable JSON configs. The core demo is “prompt stretching” — a pipeline that takes a single user prompt and fans it out through a family tree of transformations (inverse, abstract up/down, reflection, rotation, shear, scaling, recursion, dimension shift). Then I’ll also demo subprompting — recursively decomposing a prompt into a tree of subprompts at configurable depth and branching factor (e.g. n=[4,3,2]), with concurrent execution, so anyone can build their own deep research agent. Finally, all the transformed/decomposed prompt variants and their responses can be pairwise evaluated.

Tech stack