Evidence · first-party tested/Query Live Databases Using Plain English with AI

Exposes the generated SQL directly in the chat, including the explicit filter for pending-but-paid orders.

✓ Worked🧾 artifact-verifiedinput + output shownTest date not recordedQuerio →

What was measured

SQL Visibility

Can users inspect or copy the generated SQL?

capability

What was given, what came back

Test input: Order pipeline breakdown with paid-pending edge case and last-month comparison · text · group: ecommerce-nl2sql-benchmark

Input — what we sent

The exact prompt

How many orders do we have at each stage right now?

Follow-up 1: What percentage of our orders were successfully delivered vs cancelled?

Follow-up 2: Are there any orders that are pending but already paid?

Follow-up 3: Compare that to last month — same breakdown, I want to see if things have improved or got worse.

A deeper operational analysis of current order stages, delivery-versus-cancellation rates, pending-but-paid edge cases, and a month-over-month comparison of the same breakdown.

Why this input is hard

· Order pipeline analysis
· Percentage calculation
· Edge-case detection
· Payment/order status joins
· Multi-turn context retention
· Month-over-month comparison
· Ambiguity handling for 'same breakdown'

Output — unretouched

Also checked on this input — same tool, 5 other criteria

Business Insight✓ WorkedExplains the comparison rather than just reporting numbers, including that the month-to-date view is an early signal and should not be treated as a stable trend yet.Chart / Visualization Support✓ WorkedAutomatically generates chart views for the order-stage breakdown and the delivered-vs-cancelled comparison, including the month-over-month share chart.Follow-Up Context⚠ StruggledKeeps the conversation going across multiple turns, but on the final comparison it reuses the delivered-versus-cancelled thread instead of the pending-paid edge-case context, so context selection breaks on one follow-up.Plain English Query Handling✓ WorkedAccepts a multi-step operational question in plain English across several follow-ups without requiring SQL from the user.Result Readability✓ WorkedPresents the operational breakdown in compact tables with counts and percentages, making the current-stage and month-over-month results easy to scan.

Provenance

Observation: 552b4ecb-a23d-4a01-812a-7a097d16d278
Evidence run: db2bb5d5-0e0e-4cb3-8d76-3555c45c23cd
Study: Query Live Databases Using Plain English with AI
Research task: 86b9y6c99
Tested at: not recorded
Source: first-party
Evidence state: verified
Proof shown: input + output shown
Cost / latency: not captured
Repeat run: not captured
Tester: not captured

The last three rows are honest blanks, not placeholders — our capture has no field for them yet.

Query this

get_evidence({
  tool: "querio",
  scenario: "ecommerce-nl2sql-benchmark"
})

MCP · mcp.aidemos.com/api/mcp

JSON · ai.aidemos.com/v1/observations/552b4ecb-a23d-4a01-812a-7a097d16d278

Free with attribution.

Same input, same check — 1 other tool

measured on SQL Visibility

AskYourDatabase✓ WorkedShowed the SQL used for each step instead of only presenting the final answer.

This evidence is published in

Query Live Databases Using Plain English with AI →

From the same study (page rebuilt from a later run)

Best AI Tools to Query Live Databases Using Plain English →

Real inputs and real outputs, no retouching · every cell queryable via API & MCP · aidemos.com