Data manager
In product · unified at GAData-quality remediation
Data-quality errors investigated in the context of the feeds, rules and configuration involved — so remediation becomes review-and-apply.
Data-quality remediation assistance runs inside DataHub today as product-embedded AI (MCP servers + system prompts); it is unified on the NeoXam Agents platform at GA (Q3 2026).
In DataHub
The daily reality
The work this replaces
Data-quality alerts queue up daily, and each one demands the same archaeology: which feed, which rule, which mapping, what changed. The fix is often minutes; finding it is the expensive part.
How it works
What the agent actually does
datahub — embedded AI (pre-platform)
An error is flagged
A data-quality control fails in DataHub — a suspect value, a broken mapping, a rule breach.
AI investigates in context
Embedded AI assistance investigates the error against the configuration and business rules involved, instead of leaving the data manager to reconstruct that context by hand.
The data manager stays in command
Remediation is proposed for review; DataHub remains the system of record, and nothing is applied without its owner.
Unified at GA
On the unified platform, remediation steps become declared, traced task agents returning structured verdicts — the same governed pattern as the shipped BR agent family.
The outcome
Outcome
Remediation shifts from manual archaeology to review-and-apply, inside the screens data managers already use.
Governed by design
Platform unification at GA brings each remediation step under the catalog, eval gates and the append-only audit trail; today's assistance lives inside DataHub itself.
FAQ
Questions teams ask about this
Is this available today?
AI-assisted data-quality remediation runs inside DataHub today as a product-embedded capability. The unified NeoXam Agents platform industrializes it at GA (Q3 2026) — same use case, platform-grade governance.
Does the AI change my data?
No. It investigates and proposes; corrections are reviewed and applied through DataHub's own controls. Deterministic systems keep the golden copy.
How does this relate to the BR agents?
Closely. Many data-quality issues resolve to a rule that needs creating or fixing — the shipped BR generation and validation agents cover that part on the platform today.
Go further
Related use cases and concepts
Business rule validation & testing
Shipped (V0)On every rule save, DataHub chains governed agents: validate syntax and best practice, evaluate against business assertions, build and run tests.
Business rule generation from plain language
Shipped (V0)Write 'flag NAV deviations above 2%' — the generator returns a syntactically valid business rule as a typed object DataHub consumes directly.
Data onboarding & configuration Q&A
Beta (V1)'How do I configure a Kafka feed?' — answered from documentation and live configuration objects, with deep links to the exact screens.
Join the Early Adopter Program
General availability lands in Q3 2026. The Early Adopter Program is open now — a limited cohort, a one-year platform trial, and three workshop streams: Business ROI, Compliance, and Operational fit.