1
Data Catalog
Select the Data Source

Browse the role-filtered Data Catalog and select the source table. Row counts, descriptions, and sensitivity flags are visible before any query is written.

Actual Data Source Selected
DATAWAREHOUSE.KINETIQ_INSIGHTS.DEVELOPMENT
2
Columns
Choose the Columns in Scope

Select exactly which columns the AI will work with. Only schema metadata is used — no raw data is ever sent to the AI.

Actual Columns Selected
AMOUNT CATEGORY DESIGNATION
3
Use Case
Define the Business Question

Describe what you need in plain English. The AI validates the request for clarity and SQL suitability.

Actual use case entered
"We will use the data for comparision of the category of funding and their amounts in relation to other Universities with 10,000 student body. This comparison data derived from AI Agent research during the preview generation."
4
SQL Generation
AI Generates & Tests the Query

The AI produces a validated SELECT query tailored to the use case. The query is tested against live data before proceeding — only SELECT statements are permitted.

5
Data Quality ✓ Approved
Validate & Approve the Data

Query results are previewed before any visualization is created. A named approver signs off on data quality — this gate is required and tracked.

Actual Approval Recorded
✓ Approved by Ben Marchbanks  ·  2026-04-08
6
Refine & Release
AI Generates the Visualization — Then You Refine It

The AI recommends the best visualization type and generates the raw program code required for an interactive rendering. Each refinement is a natural language instruction — no code editing required. Every iteration is stored and reusable.

Actual Refinements Applied
Layout "Consider this document ultimately will be saved as PDF in 8.5 x 11 page format. Construct the content accordingly to produce content that nicely transitions from page to page."
Layout "Create a Letterhead with the following Title:Villiers University of Higher Learning, next line as a subtitle format : North Circular Road, Limerick V94 F983 Ireland"
▶ Data Dictionary
Column Definition Domain Examples Synonyms
AVG_AMOUNT The average monetary value per individual gift or contribution within a specific category or designation. This is calculated by dividing the total amount by the gift count to show typical giving levels. Finance 5000.00, 15000.00, 2500.00, 75000.00, 12000.00 Average Gift Size, Mean Contribution, Typical Donation, Average Giving Level, Per-Gift Average
CATEGORY The broad classification or type of funding received by the university. This groups donations, grants, and other financial contributions into major categories to help analyze funding patterns and compare with peer institutions. Finance Academic Programs, Student Services, Research Initiatives, Campus Infrastructure, Athletics Funding Type, Contribution Category, Gift Classification, Revenue Stream, Donation Category
DESIGNATION The specific purpose, fund name, or detailed description of how the funding is intended to be used within the university. This provides more granular detail than the broader category classification. Finance Engineering Scholarship Fund, Library Renovation Project, Graduate Research Fellowship, Student Emergency Aid, Alumni Center Construction Fund Purpose, Allocation Description, Specific Use, Fund Designation, Purpose Code
GIFT_COUNT The total number of individual donations, grants, or contributions received for a specific category or designation. This metric helps understand donor engagement and frequency of giving patterns. Finance 5, 23, 157, 8, 42 Number of Donations, Contribution Count, Gift Frequency, Donor Transactions, Funding Instances
TOTAL_AMOUNT The combined monetary value of all gifts and contributions received for a specific category or designation. This represents the aggregate financial impact and total funding secured. Finance 25000, 150000, 750000, 45000, 320000 Total Funding, Aggregate Amount, Sum of Gifts, Combined Value, Total Contributions