Product
17-agent orchestration, 40+ API endpoints, multi-tenant architecture.
What is DQ-Agent?
DQ-Agent is an on-premise data quality platform for banks, insurers and other regulated financial institutions. Seventeen autonomous agents, powered by a local LLM that runs on the customer's own server, profile SQL Server databases, detect anomalies and produce BDDK, KVKK, BCBS 239, IFRS 9, SOX and AML compliance reports, without any customer data leaving the premises.
- Deployment
- On-premise only; there is no cloud-hosted mode
- LLM
- Local Ollama models; no calls to external LLM providers
- Databases
- SQL Server 2014+ (PostgreSQL and MySQL experimental)
- Pipeline
- 14 phases orchestrated across 17 agents
- Audit trail
- 7-year encrypted audit log
- License
- Annual and hardware-bound; the vendor has no remote access to customer data
A 14-phase autonomous pipeline
Each phase produces a snapshot; the next phase reads it. A single phase failure never stops the pipeline.
Phase 1
Schema Discovery
SchemaDiscoveryAgent
Catalogs all tables, FKs and finance-table patterns from INFORMATION_SCHEMA + sys.foreign_keys.
- Typical duration
- ~5s
- Minimum tier
- professional
17 autonomous agents
17-agent orchestration, 40+ API endpoints, multi-tenant architecture.
SchemaDiscoveryAgent
Discovers the schema
→ Tables + FKs + info schema snapshot
ProfilingAgent
Generates 20+ metrics per table
→ Profiles snapshot
AnomalyDetectionAgent
Detects 22 anomaly types
→ Anomalies snapshot
RCAAgent
Four-evidence root cause for critical anomalies
→ RCA hypotheses
CrossTableAgent
MinHash/LSH schema similarity + PII duplicates
→ Cross-table report
ForecastAgent
7-day SLA breach forecast
→ Forecast snapshot
CDCAgent
Tracks change volumes via SQL Server CDC
→ CDC events snapshot
ContractAgent
Data contract drift (8 violation types)
→ Contract violations snapshot
OrchestratorAgent
Manages 14-phase pipeline + approval flow
→ Session JSON + audit log
LineageAgent
FK + procedure dependency graph
→ Lineage snapshot + Mermaid
GovernanceAgent
Ownership, classification, business glossary
→ Governance snapshot
MaskingAgent
DDM scripts + k-anonymity + KVKK retention
→ Masking + retention DDL
SLAManagerAgent
SLA breach tracking + escalation
→ SLA scorecard HTML
ComplianceAgent
BDDK + KVKK + BCBS 239 + IFRS 9 + SOX reports
→ Compliance PDF/HTML
ReconciliationAgent
GL ↔ subledger SUM reconciliation
→ Reconciliation report
ImpactScorerAgent
TRY impact estimation per anomaly
→ Impact scorecard HTML
RemediationAgent
Approval-gated fix scripts + rollback
→ Fix scripts
Dashboard included. Zero build pipeline.
A single HTML file, no Node toolchain. 13 tabs: KPIs, anomalies, lineage, compliance, heatmap, approvals, AI copilot.
- 6 KPI widgets
- 13-tab analytics
- ISO 8000 heatmap
- WebSocket live alerts
- PDF / HTML / Excel export
- Natural-language DQ queries
ISO 8000 Heatmap
Completeness
96%
Accuracy
92%
Validity
89%
Consistency
94%
Timeliness
87%
Uniqueness
98%
Integrations
Native support for your surrounding systems; no extra middleware layer.
SQL Server
Primary target. All 2014+ editions. CDC requires Standard or higher.
PostgreSQL
Experimental. Full profiling + anomaly; CDC limited.
MySQL
Experimental. INFORMATION_SCHEMA-based discovery.
Ollama
Local LLM. qwen2.5:7b chat + qwen2.5-coder:14b SQL + nomic-embed-text.
Slack / Teams
Webhook alerting with 24h deduplication to suppress noise.
SMTP
TLS, multipart HTML report attachments.
30-minute live demo against your own schema
Not a slideshow — a live install. We profile your SQL Server connection in minutes.