Skip to main content
Wisdom is DataGenie’s agentic analytics assistant — you ask complex, multi-stage questions in plain English; Wisdom plans, executes, and explains. A master coordinator agent understands your question, selects and sequences deterministic analytical services, and delivers the answer as charts, tables, or natural-language summaries.
Every number Wisdom produces comes from a deterministic service — not from a language model. Your raw data never reaches an LLM. See Responsible AI.

How to use Wisdom

1

Select your dataset

From the DataGenie home screen, click on the dataset you want to analyze. Wisdom’s answers are grounded in that dataset’s KPIs, dimensions, and domain knowledge — selecting the right one ensures your questions are answered within the correct business context.
Selecting a dataset from the DataGenie home screen to start a Wisdom session
2

Enter your business question

Click into the natural language input field and type your question in plain English — for example, “Show me sales by region for the last quarter” or “What caused the drop in Revenue yesterday?” Press Enter to submit. You don’t need to know SQL or exact column names; Wisdom interprets conversational phrasing.
Typing a business question into Wisdom's natural language input field and submitting it
3

Watch Wisdom process your query

Wisdom’s master coordinator agent breaks down your question, identifies the relevant KPIs and dimensions, and sequences the appropriate analytical services. The processing view shows exactly which measures and columns are being used — giving you full transparency into how the answer is being built before it appears.
Wisdom's processing view showing the coordinator agent mapping measures and columns to the query
4

Review the business summary

Wisdom returns a plain-English summary alongside charts and tables, using your organization’s terminology. The summary interprets the data in context — not just raw numbers — so you immediately understand what changed, by how much, and in which segment.
Wisdom displaying a contextual business summary with charts and natural-language explanation
5

Ask follow-up or multi-part questions

Type a follow-up question in the same session — Wisdom retains context from earlier in the conversation and builds on previous answers. For compound questions (e.g., “Show revenue trend and compare to last year”), Wisdom runs multiple analytical services in sequence and combines them into a single unified report.
Wisdom synthesizing a multi-part query into a unified analytical report
6

View drivers and explanations

Wisdom surfaces the drivers behind the pattern — which dimensions contributed most, how trends evolved, and what the data suggests. Every explanation comes from a deterministic service; no LLM-generated speculation, and your raw data never leaves your environment.
Wisdom surfacing drivers, trend explanations, and data-backed recommendations
7

Drill into underlying data and visuals

Click into any chart or table in the response to explore the underlying data. You can break down results by dimension, compare periods side-by-side, and trace exactly which rows and aggregations produced the number you’re reviewing.
Drilling into a Wisdom chart to access the underlying data table and visual breakdown
8

Scroll to review the full report

Scroll through the workspace to see all charts, tables, and narrative sections Wisdom generated. The workspace preserves your entire session — each question and its answer appear in sequence, so you can follow the full thread of your analysis and share it with your team.
Scrolling through the full Wisdom workspace showing all questions, charts, and summaries in sequence
The more specific your question, the sharper the answer. “What caused the drop in Conversion Rate on Mobile in the US last week?” gives Wisdom a clear scope to work with — vague questions produce broader, less actionable results.

Multi-stage queries

Wisdom handles compound prompts that span multiple analytical tasks in a single question. The master coordinator’s execution plan branches dynamically — the result of one service call determines the next service to invoke.
When you ask the same multi-stage question repeatedly, package it as a Wisdom Skill — invocable with arguments, deterministic output every time.

How Wisdom stays accurate

Three configuration surfaces per dataset act as guardrails. Together they make Wisdom respond within your business rules instead of inventing them.

Domain Knowledge

Natural-language business rules — definitions, exclusions, aliases. Wisdom answers within these rules.

Wisdom Skills

Packaged, reusable analytical pipelines. Each Skill runs as a deterministic pipeline with arguments.

Business Events

Documented timeline of real-world context (promotions, outages, seasonality) that Wisdom uses to explain patterns.

Example questions to try

Trend analysis

“Show me the trend of Revenue over the last 3 months.”

Dimensional breakdown

“Break down Conversion Rate by marketing channel.”

Period comparison

“Compare Revenue this period vs last period.”

Explain a story

“What caused the drop in Conversion Rate yesterday?”

Forecast

“Forecast Revenue for the next 4 weeks.”

Scenario

“If Conversion Rate rises 10%, what happens to Revenue next month?”

What’s next

Conversational Dashboards

Pin any Wisdom answer as a dashboard chart.

Domain Knowledge

Teach Wisdom your business rules.

Wisdom Skills

Package reusable analytical patterns.

Business Events

Document real-world context for causal explanations.

Responsible AI

How Wisdom stays deterministic and safe.

Hyper Connected

Multi-source insights with no ETL.