Local document intake
PDF, DOCX, MD, TXT, JSON, CSV, code, and image metadata stay in browser memory until you choose a model endpoint.
A single-file HTML5 workbench that ingests documents locally, applies the Apex Lotus lenses, builds a grounded prompt pack, and exports a clean Markdown report.
PDF, DOCX, MD, TXT, JSON, CSV, code, and image metadata stay in browser memory until you choose a model endpoint.
Learning Architect, JurisLogic, Forensic Linguist, and QA / Secure Code outputs use fixed structures.
Triage, lens selection, parsing, audit, and synthesis are shown as a traceable pipeline.
Skip link, keyboard controls, large touch targets, reduced-motion support, and pure black/white contrast mode.
Ingest → Ground → Analyze → Export
PDF and DOCX parsing runs client-side. Text and code load through FileReader. Images are listed as evidence objects.
Loaded into this single HTML file
Load context, choose a lens, then run the offline pass.
Embedded source docs + selected lens + payload