What problem does it solve? Feeding large sets of source documents (product briefs, discovery notes, research reports) into downstream LLM workflows wastes tokens on prose, transitions, and repetition, while naive summarization loses critical facts, decisions, and constraints. ## Core Features & Use Cases - Lossless Compression: Extracts every fact, decision, constraint, and relationship from source documents into dense, thematically-grouped bullet distillates with no information loss. - Semantic Splitting: Automatically splits large distillates into self-contained section files with an index when content exceeds token budgets. - Round-Trip Validation: Optionally reconstructs original documents from the distillate alone and diffs them to prove completeness, flagging gaps and hallucinations. - Use Case: Before writing a PRD, distill a product brief plus its discovery notes into a single ~1,500-token distillate that the PRD workflow consumes as sole context input. ## Quick Start Distill the documents in my planning folder into a single context file for PRD creation and run the validation check.
