Agent 38 · Data Automation
DataGovern Agent
Catalogues data and finds PII in the wrong places.
ServiceInsightLangGraph
Found2
Fixed + verified2
Held for approval0
Recalln/a
One offline run on demo data with planted problems (recorded platform test, November 2026).
How DataGovern heals data, step by step
INData inAll lake tables.
01Detect2 problems found
02Diagnose1 problem type named
03Plan2 safe to fix · 0 need a person
04Fix + verify2 fixed and re-checked
05ReportPlain-English report and Control Tower record
- Client problem
- Nobody knows where personal data sits.
- What it does
- Builds a data catalogue and scans for PII.
- How it heals
- Masks PII in free text and records lineage.
- Human gate
- Deletion requests need approval.
- Typical buyer
- Regulated firms (DPO, data lead)
- Built with
- LangGraph self-healing loop
- Demo data
- All lake tables.
- Tables
- Landing batches and lakehouse tables built by other agents
- Target outcome
- Target: 100% of tables catalogued.
- Path to production
- Service.
Issues detected on the demo data
| Issue | Risk | Proposed fix | Count |
|---|---|---|---|
| pii_in_free_text 37 rows of 'text' contain phone/email/ID numbers | low | Mask identifiers in free text | 2 |
How we demo it
- Run DataGovern.
- Show the catalogue and masked fields.
Built on AWS
Runs in the platform container on EC2 Graviton (or on demand in Lambda), writes healed tables to the S3 lakehouse, uses Amazon Bedrock only to write explanations, and reports six metrics to CloudWatch.
Step into DigiQuench.
Agents that heal your data.
Watch an agent find planted problems, fix the safe ones and wait for your approval on the rest. Thirty minutes, live.