Key takeaways
- Put agents on the semantic layer, not raw warehouses.
- Metric catalogs are the source of truth for definitions.
- Verify SQL and tool plans before charts reach decision-makers.
- Explainability is part of the product for finance and operations.
The KPI hallucination problem
Natural language feels productive until two teams get two different revenue numbers from the same question. The model did not invent malice. It invented a join or a filter that looked plausible.
Dashboards already encode hard-won definitions. Generative BI that bypasses those definitions recreates shadow metrics at chat speed.
The job is not "chat with the database." The job is "ask questions that respect the company's metric contracts."
Agents on a governed semantic layer
Expose metrics, dimensions, and entities through a semantic layer the agent must use. Prefer certified metrics over freeform table access.
Encode ownership and freshness. If a metric is deprecated or delayed, the agent should say so instead of improvising a substitute.
Access control travels with the layer. Row-level and column-level rules must apply to agent-generated queries the same way they apply to BI tools.
Loading diagram…
Verification loops before narratives ship
Generate a plan: which metrics, which filters, which time grain. Validate the plan against the catalog before executing SQL.
Show the query or metric path next to the chart. Analysts and finance partners need to audit the path, not only the picture.
Allow draft mode. Agents can propose analyses; humans publish when the stake is high. That is how generative BI earns a place in weekly ops reviews.
What an intelligence layer actually contains
A metric catalog, semantic models, agent planners, verification, and delivery surfaces (chat, briefings, alerts). Without the catalog, you only have a chatbot with a warehouse password.
Observability belongs here too: which questions failed, which metrics were missing, which plans were rejected. That backlog is your next modeling work.
Netrasight-style AI-assisted analytics is an early form of this idea: ask questions of data without standing up an entire parallel BI stack first, while still aiming at governed answers.
A rollout sequence that reduces risk
Start with a narrow domain: one team, one certified metric set, read-only answers. Expand after evals show stable definition adherence.
Measure definition adherence, not only answer satisfaction. A liked wrong number is worse than a refused question.
Keep a human review queue for financial and board-facing narratives until trust is earned with evidence.
FAQ
- What is a generative BI intelligence layer?
- It is the combination of a governed semantic layer, metric catalog, agent planners, verification, and delivery surfaces that lets people ask data questions without inventing KPIs or bypassing access controls.
- How do you stop NL-to-SQL agents from inventing metrics?
- Require agents to select certified metrics from a catalog, validate plans before execution, and show the metric path alongside the answer so humans can audit definitions.
- Is generative BI a replacement for dashboards?
- Not usually. It accelerates routine questions and exploration on top of the same governed definitions dashboards already use. Dashboards remain useful for shared, recurring views.