What problem does it solve? Feeding large sets of source documents (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 YAML frontmatter. - Semantic Splitting: Automatically splits large distillates into self-contained section files with an index when content exceeds token thresholds or a user-specified token budget. - Round-Trip Validation: Optionally reconstructs original documents from the distillate alone and produces a validation report 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 a downstream planning agent consumes as sole context without information loss. ## Quick Start Distill the documents product-brief.md and discovery-notes.md into a distillate for PRD creation, then run it with the --validate flag to confirm nothing was lost.
