Querying Application /User Data LLM Challenges of this architecture: Is the data correct? Is the data governed and compliant? Is the data ethical, unbiased, auditable?
Querying Data Application /User LLM Quantitative Engine incl. data masking, permission management, auditability for data • Lewis, Patrick, et al. "Retrieval-augmented generation for knowledge-intensive NLP tasks." Advances in Neural Information Processing Systems, vol. 33, 2020, pp. 9459-9474. RAG* (Retrieval Augmented Generation) Data Governance
Data Review and approval UX End User Rich Chat BI UX Domain and Human Interface LLM Consistency and correction LLM Text-To-SQL LLM Relational interface Virtual SQL Engine (ex. Cdata Virtuality, Connect Cloud) RAG with data governance, row permissions, data masking, metadata queries. Data *Gao, Dawei, et al. "Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation." arXiv preprint arXiv:2308.15363 (2023). Metadata and Semantics Vector interface Application/ User Data Steward
Q4 2025 Roadmap SaaS 3.0 (SSO, Multi instance, Git) AI Features II (AI RAG-based engine, TTYD) Web Data Shop 3.0 (Request data access, show additional attributes) SaaS clustering support Git integration part III (UI, Backend improvement) Schema matching and association discovery Automatic load balancing and scaling (for cluster solutions) Platform foundation upgrade (J ava 17, WildFly 26) MPP component Web UI IDE improvements - General rework and improvements - View editing - J ob dependencies /graphical ETL, ER diagrams, etc. External security vaults (Azure Key Vault) J obs time zone awareness Kintone connector 28
cdataj
ysknsid25
kenjikondobai
oracle4engineer
kazushi_ohata
kniino
kamina_zzz
kaminashi
chou500
stajima
minorun365
danielanewman
bluesmoon
mongodb
csswizardry
jnunemaker
colly
sferik
cassininazir
tammyeverts
pedronauck
zakiyama
quramy
