Query and forecast against your own tables.
Use dashboards and plain-language queries over governed views. KEZEL Insights Studio adds analytical models, while masks and lineage make the data access reviewable. The examples below use sample data.
Inspect the analytics workbench.
Live views over the system of record
Queries execute on the source engine where supported. Other computation runs in the local agent. Dashboards read the resulting governed views.
→ plan · 3 tables · masked · approved
Plain language to a governed plan
LLMCore plans from schema metadata without raw-row access. The query plan records the tables, masks and policy decision.
Ranked work, explained
Scores with reasons attached, so reviewers see why an item is at the top of the queue.
| reader | card_no | |
|---|---|---|
| analyst | a•••@corp.eu | •••• 4412 |
| fraud-rev | [email protected] | •••• 4412 |
Column rules, applied in the query
Row filters and column masks are part of the plan itself, scoped to the reader's role. Cleartext reads are themselves logged.
Lineage for every figure
Each published figure traces back through its transforms to its sources, as a graph.
| 10:42 | nl-query | masked view | j.rao |
| 10:44 | forecast | aggregate | planning |
| 10:47 | export | denied · policy | svc-crm |
Every read is logged
The ledger records the question, policy decision, reader and timestamp for each read.
Choose a model for the question.
Introduced at Bengaluru Tech Summit 2025. Each question below has its own engine, shown here on demonstration data.
“How much?”
Estimate how spend affects weekly volume
Fit the relationship between campaign spend and volume using your own tables. The fitted line shows an estimate; an analyst still needs to check whether the relationship supports the decision.
regression · fitted relationship on sample data
campaign spend vs. weekly volume · fitted · sample data
VizEngine · dashboards · LLMCore · plain-language plans · time series · Prophet, ARIMA · classification · 8 model candidates, evaluated with and without outlier correction
Third parties work inside your boundary.
Suppliers, partners and service providers read governed views where the data lives. No records pool on a second platform, and every read they make lands on the same ledger yours do.
| reader | scope | outcome |
|---|---|---|
| partner-logistics | fill_rate_weekly · governed view | reads logged |
| auditor | ledger + lineage | read-only |
| svc-crm | export request | denied · policy |
governed views · in-boundary reads through the policy gate · sample data
See KEZEL run a workload like yours.
Tell us which system holds your data and what you need to do with it. We’ll demonstrate on sample data, then scope a pilot with your security team.