Gravicus, turning data into signal.
I designed the SAR relationship maps and investigator workflow that made Osprey's ML output usable for bank compliance analysts.
Role
Senior Product Designer
When
2018 - 2019
Team
2 PMs, data science, 6 engineers
Product
Osprey · SAR, DPIA, Privacy, BackOffice
Background
Gravicus built Osprey, an ML and NLP product that finds privacy breaches, conflicts of interest and sanction risk in huge document stores. The data science was strong and the interface buried it.
UX Design
Connecting data sets
Setup for SharePoint, drives and mail that shows the corpus is indexed.
Collections
Live working sets that begin analysing the moment you set parameters.
Data alerts & NLP
Alerts like an anti virus scanner, specific enough that nobody triages 500.
SAR workflow
Subject Access Requests walked from a name through search, redact, package and send.
SAR · entity graph and relationship map
Collections & alerts · the analyst's daily surface
UI Design
Visualisation library
Chose React Vis over D3 for easier maintenance and better animation defaults.
Entity graph
The relationship map anchors every investigation and hides most detail by default.
Risk scoring surface
Confidence and risk shown separately, so a confidently wrong model gets caught.
Across five surfaces
SAR, DPIA, Privacy, BackOffice and Dashboard share one set of primitives.
Outcome
Enterprise customers ran their compliance and privacy operations on Osprey before Smartbox acquired Gravicus.