Observed arrival · 2026-09-23
Velo puts a local scrubber between patient records and cloud AI
Velo is presented as an on-premise tool for detecting and transforming personal information in clinical notes, PDFs, images, and audio before data reaches a cloud LLM.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Healthcare teams handling clinical records and LLMs
- Worth noticing
- Its examples include identifiers generic models may miss, such as MRNs, NPIs, member IDs, authorization numbers, and dates.
Field notes
The sample discharge summary is explicitly labeled fictional and contains names, contact details, record numbers, insurer information, and clinical text. The page says its detection combines clinical-note-trained NER models with rules for identifiers such as SSNs, MRNs, NPIs, and member IDs, and says each detection is logged with its type, position, and confidence.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue