Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.datagenie.ai/llms.txt

Use this file to discover all available pages before exploring further.

What Wisdom is

Wisdom is DataGenie’s agentic analytics assistant — you ask complex, multi-stage questions in plain English; Wisdom plans, executes, and explains. It is not text-to-SQL. 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.

When to use Wisdom

  • You want an ad-hoc answer without building a dashboard or writing SQL
  • You have a multi-stage question (“Show revenue trend for the last 30 days and forecast the next 14”)
  • You want forecasts or what-if scenarios on any KPI + dimension combination
  • You want to explain or validate a Top Story in plain English
  • You want a repeatable analytical pattern packaged as a Wisdom Skill

What you get

Wisdom orchestrates five deterministic services dynamically. Each service is invoked by the coordinator based on your question.

Metric Service

Time series for any KPI × dimension × period combination — with anomaly flags and deviation data.

Insights Service

Pulls the relevant Top Stories for the KPIs, dimensions, and period in scope.

Contribution Analysis

Identifies which sub-dimensions disproportionately contributed to a detected change.

Forecasting

Future-period forecasts for any metric combination, aligned to your dataset granularity.

Scenario Planning

What-if simulations — change one or more drivers and see downstream KPI impact.

Natural-language output

Every result is consolidated into plain-English narrative alongside the charts.

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 keep asking the same multi-stage question, package it as a Wisdom Skill — invocable with arguments, deterministic output every time.

How Wisdom stays accurate

Three configuration surfaces per dataset act as safety gates. 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.

HyperConnected

Multi-source insights with no ETL.