⌘K

PII Discovery

Continuous discovery and classification of personal data across the connected estate. 47,824 columns scanned · 14,247 PII columns classified · 247 awaiting human review.

Columns scanned
47,824
98.9% of 48,353 estate columns
PII columns classified
14,247
29.8% of scanned columns
Awaiting review
247
Human-in-the-loop queue
Active classifiers
18
12 regex · 6 ML
Unscanned risks
0
No high-risk schemas left
Avg time to classify
47 min
From appearance to classification

PII coverage by category

Identifier2,847
Contact4,200
Financial3,400
Demographic1,847
Sensitive412
Behavioral1,247
Children294

PII distribution by source system

Finacle Retail Core
4,200
38%
Pinnacle Life PAS
2,847
47%
TCS BaNCS (Apex Capital)
1,847
32%
Salesforce FSC
1,247
44%
Workday HCM
847
52%
FIS CardPro
612
38%
Apex LOS
547
41%
Finacle Corporate
412
18%
Pinnacle Securities
247
24%
Other sources (8)
1,441
21%
Source systems with the highest PII density are tagged high-risk and scanned at higher frequency.
Scan coverage

98.9% of scanned columns have been classified. 1.1% (529 columns) are in deep review or pending classifier updates.

Classifier accuracy

Precision 96.4% · Recall 94.1%. Last review 14 Apr 2026. False positive 2.4% · false negative 5.9% (sampling audit).

Propagation health

Average 14 minutes from source classification to downstream application. 0 propagation backlogs currently.

Recent discoveries

  • Apex Capital loan feed scanned· 47 min ago

    4 new columns. 1 Sensitive PII (digital_kyc_flag). 98.4% confidence. Auto-applied.

    Owner: Faisal Khan
  • Salesforce FSC contact fields· 2 hr ago

    14 new custom fields. 3 PII (phone variants), 11 Internal. All auto-applied.

    Owner: System
  • Pinnacle Securities client_profile· 4 hr ago

    New column pep_status → Sensitive PII (Restricted). 99.7% confidence.

    Owner: System
  • Workday HCM scan completed· 6 hr ago

    47,200 columns scanned in 14 minutes. 4 newly classified PII columns.

    Owner: Meera Pillai
  • Manual override · Salesforce FSC· 8 hr ago

    customer_notes reclassified Internal → Sensitive PII (free-text). Propagation in progress.

    Owner: Meera Pillai
  • Classifier update · PAN v3.4· 12 hr ago

    Improved precision on non-Indian alphanumeric IDs. Recalibration scheduled.

    Owner: System
  • High-risk finding flagged· 1 day ago

    legacy_csv_archive.bulk_kyc_data — unmasked PAN/Aadhaar/DOB. Auto-quarantined pending review.

    Owner: System
  • DPDP PII map regenerated· 1 day ago

    Q2 2026 evidence pack regenerated with latest classifications.

    Owner: System
  • Classifier deployed · GSTIN v2.0· 2 days ago

    Structural validator with 100% precision in calibration.

    Owner: Meera Pillai
  • TCS BaNCS scan completed· 2 days ago

    76 tables, 4,847 columns scanned in 22 minutes. 12 new findings.

    Owner: System
  • Classifier accuracy audit· 3 days ago

    Sampling review of 200 classifications. 96.4% precision confirmed.

    Owner: Meera Pillai
  • SharePoint deep scan· 4 days ago

    14,200 documents scanned. 247 flagged for review.

    Owner: System

Risk and recommendations

  • Schedule overdue scans
    3 source systems have not been scanned in the last 30 days.
  • Deploy free-text ML detector
    Customer free-text fields are the highest source of false negatives.
  • Deep scan Azure Blob archive
    247,000 unscanned documents in legacy archive. Recommend OCR + classifier.
  • Initial scans for new sources
    5 new sources connected in last 30 days have not completed initial scan.