Lab admin demo: the pipeline behind the answers
Before a researcher gets a cited answer, a lab admin turns raw files into a governed, citeable knowledge base. These walkthroughs show that pipeline on the real product UI — from upload and security scanning through ingestion, embedding, and structured sources.
The data pipeline
The data pipelineAdmin walkthrough
- Upload research files — PDFs, Office docs, notes, code and simulation decks.
- Each file is malware-scanned before anything else touches it.
- Ingestion extracts text; embedding makes it searchable — each stage shows its status.
Every upload clears security scanning, then ingestion, then embedding — visible per file.
Data structuring
Data structuringAdmin walkthrough
- A document carries its type, source, and confidentiality — captured, never invented.
- Its page and section structure is what later answers cite back to.
- Nothing is summarized or altered; the original passages remain the source of truth.
A raw file becomes a structured, citeable document with type, source, and page/section context.
Governance and provider choice
Governance and provider choiceAdmin walkthrough
- Every workspace shows its own AI usage — the basis for hard spend caps.
- The AI provider is the admin's call: platform-managed, your own API key, or on-prem/local.
- Where the research data and the model run stays a governance decision, not a default.
Per-workspace AI usage plus the provider setup — managed, your own key, or fully local.
Governance the whole time
- Per-tenant isolation: each lab's corpus stays separate by organization and workspace.
- Your choice of where the AI runs — managed, your own key, or fully local/on-prem.
- Hard AI spend caps per workspace, so ingestion and questions never run away on cost.