Enterprise Data Management
Shipped — task modeAgents in NeoXam DataHub
Business rules drafted, validated, evaluated and tested by agents that know your syntax dictionary, your rule corpus and your engine.
The enterprise data management platform — a single source of truth for market, reference and master data across the investment lifecycle.
Embedded agents
What each agent does in DataHub
Statuses are exact and published for every capability — shipped means running today, Beta and GA wave are always future tense.
BR Generator
Shipped — task modedh-br-generatortask mode
Generates a Business Rule expression from a plain-language specification, grounded in the DataHub syntax dictionary and an examples corpus — returned as a typed object the product consumes directly.
BR Validator
Shipped — task modedh-br-validatortask mode
Validates a Business Rule on syntax and best-practice compliance and returns a prioritized improvement plan as a structured verdict.
BR Evaluator
Shipped — task modedh-br-evaluatortask mode
Evaluates a Business Rule against business assertions on the DataHub engine: pass or fail per assertion, a coverage score and diagnostics.
BR Tester
Shipped — task modedh-br-testertask mode
Builds and runs a BRTU test suite: generates test cases, schedules execution and reports results.
BR Assistant
Betadh-br-assistantconversational mode
An interactive Business Rule expert inside the authoring screen: draft, explain, validate, test and improve rules through conversation. Actions touching the live engine will require explicit user confirmation.
DataHub Assistant
Betadatahub-assistantconversational mode
A product assistant grounded in documentation and live configuration — ask "How do I configure a Kafka feed?" and get an answer with deep links to the exact screens. The Beta milestone pilot.
Status note The four Business Rule task agents run against contract-tested fixture tools today; the live DataHub engine connection is a Beta milestone. Data-quality remediation, configuration assistance and lineage exploration run inside DataHub today, pre-platform, and unify on the governed platform at GA.
On the platform
Governed like every NeoXam agent
DataHub invokes its agents on NeoXam Agents — one catalog, one runtime, one compliance posture across the suite.
Declared in the Catalog
Every agent is a versioned descriptor in the Git-governed Catalog, reviewed through pull requests. Nothing undeclared can run — the catalog-first integrity contract.
One Runner API
Product screens invoke agents through the same stable Runner API — auth, tenancy, rate limiting, schema validation and run lifecycle included.
Traced, with cost
Every model and tool call emits an OpenTelemetry span, with token usage and cost per run, per agent and per tenant.
Eval-gated
Each agent ships a versioned eval dataset and a baseline score that can only go up; CI re-runs evals on every change.
Use cases
DataHub workflows, agent-assisted
Business Rule generation from plain language
ShippedWrite "flag NAV deviations above 2%" and receive a syntactically valid rule drafted from the syntax dictionary and example corpus.
Automated BR quality pipeline
ShippedOn every save, the DataHub workflow chains governed agents — generate, validate, evaluate, test — each returning a structured verdict. The app orchestrates; agents execute bounded steps.
Configuration Q&A and data onboarding
BetaProduct questions will be answered from documentation and live configuration objects, with deep links to the exact screens — compressing the onboarding of new data flows.
Solutions
Built for these teams
Data Manager · DataHub Developer
Data Management
Draft, validate, evaluate and test business rules in minutes — grounded in your real syntax dictionary and rule corpus, returned as typed verdicts.
COO · Head of Operations · Fund Administrator
Operations
Absorb the investigation toil on breaks and exceptions. Analysts review structured findings — root cause, evidence, recommended action — instead of digging.
FAQ
Questions about agents in DataHub
What does "Shipped — task mode" mean exactly?
The four Business Rule task agents — generator, validator, evaluator, tester — are implemented and verified in the platform catalog today, invoked by workflows with typed inputs and schema-validated outputs. They run against contract-tested fixture tools; the live DataHub engine connection arrives in Beta.
When can our data managers chat with DataHub?
Conversational agents — the BR Assistant in the authoring screen and the DataHub product assistant — ship with the Beta, which also brings sessions, platform-managed memory and human-in-the-loop confirmations.
Do the agents modify our rules on their own?
No. They draft and assess; your workflow and your people decide. Outputs are typed verdicts the product consumes, and any live-engine action will require explicit confirmation.
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.