---
title: "Best AI Tools to Query Live Databases Using Plain English"
type: "Ranking"
url: "https://aidemos.com/best/ai-database-query-tools"
description: "If you need to ask a live database questions in plain English, the best tools are the ones that can turn a conversational prompt into a correct query, a readable answer, a chart, and a follow-up-safe thread. We tested 11 database-AI tools on the same live PostgreSQL ecommerce data with three benchmark chains: customer acquisition, best customers with unpaid-order and payment-method follow-ups, and order-pipeline health with pending-paid edge cases and month-over-month comparisons."
readTime: "14 min read"
tested: "Anomaly AI vs BlazeSQL vs AskYourDatabase vs Querio vs AI for Database vs Dot vs Definite vs camelAI vs Draxlr vs FutureSmart NL2SQL Agent vs Basedash"
testedDate: "June 2026"
category: "developer-tools"
published: "2026-07-11T15:53:29.168006+00:00"
updated: "2026-08-19T07:34:23.651047+00:00"
evidenceCount: 192
verifiedCount: 140
coverage: "dense"
---

# Best AI Tools to Query Live Databases Using Plain English

`11 tools tested` · `Live PostgreSQL` · `3 benchmark inputs` · `SQL visible` · `Charts & dashboards` · `Follow-up chains`

**Tested:** Anomaly AI vs BlazeSQL vs AskYourDatabase vs Querio vs AI for Database vs Dot vs Definite vs camelAI vs Draxlr vs FutureSmart NL2SQL Agent vs Basedash · June 2026

> If you need to ask a live database questions in plain English, the best tools are the ones that can turn a conversational prompt into a correct query, a readable answer, a chart, and a follow-up-safe thread. We tested 11 database-AI tools on the same live PostgreSQL ecommerce data with three benchmark chains: customer acquisition, best customers with unpaid-order and payment-method follow-ups, and order-pipeline health with pending-paid edge cases and month-over-month comparisons.

## Our Verdict

**#1 pick: Anomaly AI** (Best) — Excellent at visible SQL, meanings, and auto-insights, but follow-up context can shift between turns.

- #2 BlazeSQL — Self-correcting analyst with unusually strong trust-on-bad-data behavior
- #3 AskYourDatabase — Strong conversational SQL with excellent follow-up reasoning, but charts need a second ask.
- #4 Querio — Very strong at conversational SQL analytics, especially transparent query generation, charts, and follow-up handling, with a small weakness in deeper context binding and human-friendly naming.
- #5 AI for Database — Strong SQL transparency and operational traceability, but weaker narrative accuracy and chart clarity
- #6 Dot — Strong on transparent SQL answers and clarifying ambiguous questions, but weaker on proactive insight and data-recency trust.
- #7 Definite — Strong at turning plain-English business questions into readable answers and reusable dashboards, but it misses ambiguous phrasing like “best customers” and keeps charts out of the main chat flow.
- #8 camelAI — Trustworthy coding-agent style analytics, but SQL and charts are request-driven
- #9 Draxlr — Strong on SQL correctness and follow-up chaining, but weaker on readable, insight-rich presentation.
- #10 FutureSmart NL2SQL Agent — Strong on observability and well-formed database answers, but weak on relative-time comparisons and ambiguous follow-throughs.
- #11 Basedash — Strong on clean, conversational business answers; weaker when a follow-up is ambiguous and when users need to inspect SQL.

## How We Tested

We tested 11 live-database AI tools against the same PostgreSQL ecommerce schema (customers, orders, order_items, products, payments, and order_status_history). Each tool was given the same three benchmark input sets: a simple customer-acquisition comparison, a medium best-customers chain with two follow-ups, and a complex order-pipeline chain with edge cases and a month-over-month comparison. We judged the tools on plain-English query handling, SQL generation and visibility, result readability, follow-up context, business insight, automatic charting, export/reuse, dashboard workflow, ambiguity handling, and how useful each tool is as a reference for FS NL2SQL Agent.

**What we evaluated:**

| Criterion | Description |
| --- | --- |
| Plain English Query Handling | Can the tool understand business questions without SQL? |
| SQL Generation | Does it generate database-backed SQL correctly? |
| SQL Visibility | Can users inspect or copy the generated SQL? |
| Result Readability | Is the answer easy for a non-technical user to understand? |
| Follow-Up Context | Does the tool remember previous answers correctly? |
| Business Insight | Does it explain what the result means? |
| Chart / Visualization Support | Does it generate charts automatically or allow useful visual views? |
| Export / Reuse | Can users export, save, share, or reuse the result? |
| Dashboard Workflow | Can the answer become a dashboard or reusable view? |
| Ambiguity Handling | Does it clarify unclear business terms instead of guessing silently? |
| FS Learning Value | Does this tool reveal a useful improvement direction for FS NL2SQL Agent? |

## The Ranking

11 tools tested head-to-head on the same input.

### 1. Anomaly AI — Best

*Best at traceable, self-verifying business analysis.*

Excellent at visible SQL, meanings, and auto-insights, but follow-up context can shift between turns.

### 2. BlazeSQL — Usable

*Self-correcting analyst with unusually strong trust-on-bad-data behavior*

A strong direct NL2SQL competitor that self-corrects well, but automatic charting is not as smooth as the leaders.

### 3. AskYourDatabase — Usable

*Strong conversational SQL with excellent follow-up reasoning, but charts need a second ask.*

Best practical direct NL2SQL tool for non-technical users; readable answers, visible SQL, and strong follow-up continuity.

### 4. Querio — Usable

*Very strong at conversational SQL analytics, especially transparent query generation, charts, and follow-up handling, with a small weakness in deeper context binding and human-friendly naming.*

Strong analyst workspace with multiple outputs per question, but some follow-ups get technical or drift in context.

### 5. AI for Database — Usable

*Strong SQL transparency and operational traceability, but weaker narrative accuracy and chart clarity*

Very transparent and cost-aware, but a few query and comparison gaps keep it out of the top tier.

### 6. Dot — Usable

*Strong on transparent SQL answers and clarifying ambiguous questions, but weaker on proactive insight and data-recency trust.*

Helpful charts and good clarification behavior, but the SQL surface and business insight are lighter than the leaders.

### 7. Definite — Usable

*Strong at turning plain-English business questions into readable answers and reusable dashboards, but it misses ambiguous phrasing like “best customers” and keeps charts out of the main chat flow.*

Strong for turning answers into reusable dashboard views, but heavier than the top chat-first tools.

### 8. camelAI — Usable

*Trustworthy coding-agent style analytics, but SQL and charts are request-driven*

Powerful agentic behavior, but it is too code-centric, slow, and brittle for a simple non-technical NL2SQL workflow.

### 9. Draxlr — Usable

*Strong on SQL correctness and follow-up chaining, but weaker on readable, insight-rich presentation.*

Powerful SQL-first exploration with exports and chart switching, but less friendly for fully non-technical users.

### 10. FutureSmart NL2SQL Agent — Usable

*Strong on observability and well-formed database answers, but weak on relative-time comparisons and ambiguous follow-throughs.*

Useful as a reference, but comparison handling and ambiguity resolution were weaker than the top tools.

### 11. Basedash — Usable

*Strong on clean, conversational business answers; weaker when a follow-up is ambiguous and when users need to inspect SQL.*

Best UX reference; the interface is simple, readable, and recovers well when SQL breaks.

## Full Breakdown

### Anomaly AI

Insight-led reporting copilot with a strong traceability surface and persistent saved insights.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- The tool is excellent at visible SQL, plain-language meaning, and saved insight cards. It also adds a strong verification pass before publishing results, which increases trust.

**Where it struggled:**
- Follow-up context can shift between turns, so the selected customer set is not always stable across a conversation.

**What came out:**

![Anomaly AI output showing Acquisition result](https://cdn.futuresmart.ai/public/aidemos/569a297a429a4b7e9908efab99bb1fb1.png?v=1)
*Output — The acquisition answer is verified before it is published and clearly states the 0-vs-13 result.*

![Anomaly AI output showing Auto dashboard](https://cdn.futuresmart.ai/public/aidemos/24c8bbce0d1f49c2b27d4d93f31c41c9.png?v=1)
*Output — The result is saved as an insight card with an auto-generated dashboard chart and an empty current-period table.*

![Anomaly AI output showing Meaning and code view](https://cdn.futuresmart.ai/public/aidemos/aa67bad840744df79ccb8b847e6dc067.png?v=1)
*Output — The meaning tab shows the formula in plain mathematical form, while the code tab shows the exact SQL.*

![Anomaly AI output showing Customer ranking result](https://cdn.futuresmart.ai/public/aidemos/acc8fc289cba49ff9c0ab7460cb73c9c.png?v=1)
*Output — The ranking table shows both order frequency and spend ranks for the best customers and exposes the trade-off clearly.*

![Anomaly AI output showing Scatter plot](https://cdn.futuresmart.ai/public/aidemos/1268fe48e0514a64a34ab2f7db6273dd.png?v=1)
*Output — The scatter plot shows the relationship between order frequency and total spend rather than forcing a single flat leaderboard.*

![Anomaly AI output showing Unpaid-orders follow-up](https://cdn.futuresmart.ai/public/aidemos/0e39de6a176c4723a429c3c095dba783.png?v=1)
*Output — The top-3 unpaid-order check is summarized cleanly with counts and unpaid amount totals.*

![Anomaly AI output showing Payment-method follow-up](https://cdn.futuresmart.ai/public/aidemos/6e00e2c7e65849f1a091591bf982be6d.png?v=1)
*Output — The payment-method follow-up is rendered as a chart-plus-table insight.*

![Anomaly AI output showing Order-stage breakdown](https://cdn.futuresmart.ai/public/aidemos/6781e658e6d4439baf837f3092a1d234.png?v=1)
*Output — The order-stage analysis becomes a saved insight with a bar chart and plain-language summary.*

![Anomaly AI output showing Delivered-vs-cancelled result](https://cdn.futuresmart.ai/public/aidemos/9bc5de6c404f483cb1e3f9ceed786fa6.png?v=1)
*Output — The delivered-versus-cancelled follow-up is visualized as a donut chart with both all-orders and resolved-orders context.*

![Anomaly AI output showing Pending-paid result](https://cdn.futuresmart.ai/public/aidemos/3e9c3e4a984e458eb864fc66c4528f8e.png?v=1)
*Output — The pending-but-paid exceptions are listed with dates and delivery information.*

![Anomaly AI output showing Month-over-month comparison](https://cdn.futuresmart.ai/public/aidemos/200cc1b11fed4a6393a67e6f5dc11cac.png?v=1)
*Output — The April-versus-May comparison shows the pending backlog and the unchanged paid share.*

### BlazeSQL

Direct NL2SQL chatbot with strong self-diagnosis and technical-mode SQL visibility.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- It self-corrects well, explains its reasoning, and handles the core benchmark chains with useful summaries. The order-pipeline flow is especially strong because it can diagnose date-range issues and recover.

**Where it struggled:**
- Charts are not automatic enough, and the product can be a bit more technical than a first-time non-technical business user expects.

**What came out:**

![BlazeSQL output showing Acquisition result](https://cdn.futuresmart.ai/public/aidemos/dda575c2845c4eb1ae8e6a8f29aca98d.png?v=1)
*Output — BlazeSQL answers the acquisition question, then notices the 90-day boundary issue and diagnoses the data gap itself.*

![BlazeSQL output showing Acquisition comparison](https://cdn.futuresmart.ai/public/aidemos/1e9c281762114ab9a6360294d848a662.png?v=1)
*Output — The comparison table shows last-90-days versus previous-90-days counts before the self-diagnostic monthly breakdown.*

![BlazeSQL output showing Best-customers result](https://cdn.futuresmart.ai/public/aidemos/7791279564064634abc382f59a91c44a.png?v=1)
*Output — The first best-customers pass is corrected to use paid, valid orders only, which is a useful self-healing behavior.*

![BlazeSQL output showing Unpaid-orders follow-up](https://cdn.futuresmart.ai/public/aidemos/f4b7984668514155babf5b6dae522c22.png?v=1)
*Output — The follow-up identifies Rahul Sharma's unpaid order and leaves the other selected customers clear.*

![BlazeSQL output showing Payment-method follow-up](https://cdn.futuresmart.ai/public/aidemos/386f892ad1d64704a0f981ec9cdcc9de.png?v=1)
*Output — The payment-method breakdown keeps the top-customer context and shows the dominant methods cleanly.*

![BlazeSQL output showing Order-stage breakdown](https://cdn.futuresmart.ai/public/aidemos/ba29300bdf0848ad97a2e264ddbec6a3.png?v=1)
*Output — The status breakdown is correct and easy to inspect, with all current order stages listed.*

![BlazeSQL output showing Delivered-vs-cancelled result](https://cdn.futuresmart.ai/public/aidemos/28078619d7b3497c8e93ecc937cf0bcb.png?v=1)
*Output — The resolved-orders percentage split is shown as a clean comparison and later gets recounted to include COMPLETED orders.*

![BlazeSQL output showing Pending-paid result](https://cdn.futuresmart.ai/public/aidemos/4bd3e3ecb0c64243929ccb67d032d785.png?v=1)
*Output — The tool correctly surfaces the two pending-but-paid exceptions as operational issues.*

![BlazeSQL output showing Date-range diagnostic](https://cdn.futuresmart.ai/public/aidemos/02dfc4b9a7e4478ebb980117efaeae7b.png?v=1)
*Output — When the month comparison initially misses, BlazeSQL checks the actual date range and pivots to the right months.*

![BlazeSQL output showing Month comparison](https://cdn.futuresmart.ai/public/aidemos/9292f67dbace49f0be3293bfe66607ea.png?v=1)
*Output — The April-versus-May comparison closes the loop with a clearer month-over-month operational read.*

### AskYourDatabase

Direct NL2SQL chatbot with visible SQL, readable summaries, and strong conversational follow-up handling.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Answered all three benchmark chains with readable business summaries, visible SQL, and strong follow-up continuity. It also kept the customer and order-pipeline context anchored correctly across turns.

**Where it struggled:**
- Automatic charting is not fully hands-off; in at least one flow the user had to ask again for visualization.

**What came out:**

![AskYourDatabase output showing Acquisition result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-customer-acquisition-sql-7656b9448475.png)
*Output — Last 90 days: 12 customers versus 23 in the previous 90 days; acquisition is down about 48%, and the recent-customer list is readable without UUIDs.*

![AskYourDatabase output showing Customer ranking result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-best-customers-sql-visib-629187e7b9a4.png)
*Output — The best-customers query shows visible SQL and a clean ranking that uses paid, non-cancelled orders.*

![AskYourDatabase output showing Unpaid-orders follow-up](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-top-customers-unpaid-ord-a699f4cf81c6.png)
*Output — Rahul Sharma is the only top customer with an unpaid order; Deepak Kulkarni and Karan Joshi are fully paid.*

![AskYourDatabase output showing Payment-method follow-up](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-top-customers-payment-me-de7564c3dcd5.png)
*Output — Deepak uses EMI, Rahul mostly uses UPI with one Credit Card order, and Karan uses Net Banking.*

![AskYourDatabase output showing Order-stage breakdown](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-order-stages-breakdown-c3c13c6ce301.png)
*Output — The tool breaks down 93 orders across seven statuses and surfaces a clear operational snapshot.*

![AskYourDatabase output showing Pending-but-paid result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-pending-paid-orders-curr-323073d549c7.png)
*Output — Two orders are pending but already paid, both from late 2025, and the report flags them as operational exceptions.*

![AskYourDatabase output showing Month-over-month comparison](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-pending-paid-last-month--a7e8d24a0e46.png)
*Output — The pending-paid comparison stays on the right context and shows the backlog is unchanged rather than silently resetting.*

![AskYourDatabase output showing Chart prompt required](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-askyourdatabase-chart-requires-extra-pro-93b61e509943.png)
*Output — A chart appears only after a separate visualization prompt, so charting is not fully automatic.*

### Querio

Analyst workspace that can turn one question into multiple SQL-backed outputs, charts, and insight views.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Strong analyst-workspace behavior: one prompt can produce multiple SQL-backed outputs, charts, and written insights. The tool is powerful and highly automated for exploratory analysis.

**Where it struggled:**
- Deeper follow-up context can drift to the wrong previous breakdown, and some outputs become ID-heavy or too technical for non-technical users.

**What came out:**

![Querio output showing Acquisition result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-customer-acquisition-multiple-sql-b3b39d9a5b76.png)
*Output — One prompt yields multiple database-backed outputs, including the customer list and period comparison.*

![Querio output showing Acquisition charts](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-customer-acquisition-auto-charts-e99589cacc1f.png)
*Output — Querio automatically generates chart views for the acquisition question without requiring a second prompt.*

![Querio output showing Key insights](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-key-insights-customer-acquisition-8ef94e2ed8ff.png)
*Output — The tool adds a written insight layer that explains the acquisition drop and the clustering pattern.*

![Querio output showing Customer ranking follow-up](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-best-customers-followup-context-4ed564e92615.png)
*Output — The follow-up keeps the prior customer-ranking context, but the output can become more technical than a non-technical user wants.*

![Querio output showing ID-heavy caution](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-customer-id-heavy-output-caution-707600d69f63.png)
*Output — Some follow-up outputs lean on customer IDs instead of readable names, which hurts business readability.*

![Querio output showing Pending-paid context](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-pending-paid-previous-question-4496089e047e.png)
*Output — The previous question is the pending-paid query that the next turn should have stayed anchored to.*

![Querio output showing Wrong-context comparison](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-querio-same-breakdown-wrong-context-64105c9dec85.png)
*Output — The final comparison uses the wrong previous breakdown instead of staying on the pending-paid context, which is a real follow-up failure.*

### AI for Database

Traceable chat agent with inline SQL, step-by-step execution traces, and cost/latency telemetry.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Inline SQL, step-by-step traces, and cost telemetry make the tool unusually transparent. It also handles the core order-pipeline workflow and the pending-but-paid edge case with useful evidence.

**Where it struggled:**
- A few comparison and follow-up turns have real query gaps or explanation issues, so the tool is transparent but not always flawless.

**What came out:**

![AI for Database output showing Acquisition result](https://cdn.futuresmart.ai/public/aidemos/b615bfb324b347c0a75c7c7473ebeef8.png?v=1)
*Output — The customer-acquisition answer is correct on the 0-customer window and includes a diagnostic chain before the final response.*

![AI for Database output showing SQL trace](https://cdn.futuresmart.ai/public/aidemos/aebd04e533234824b3298e437c4bc415.png?v=1)
*Output — The generated SQL and step-by-step trace are visible inline, which is unusually transparent.*

![AI for Database output showing Best customers result](https://cdn.futuresmart.ai/public/aidemos/f29baaad55a14da0b6fa33a1f77e2691.png?v=1)
*Output — The main ranking table shows customer order count, total spend, average order value, and rank positions.*

![AI for Database output showing Unpaid-orders follow-up](https://cdn.futuresmart.ai/public/aidemos/fb834fa5d82d43899161dd0811d157e5.png?v=1)
*Output — The top-3 unpaid-order follow-up shows Rahul Sharma as the only customer with an unpaid order.*

![AI for Database output showing Payment-method follow-up](https://cdn.futuresmart.ai/public/aidemos/438900f012b24c8396a6e31ee01fd795.png?v=1)
*Output — The payment-method drilldown presents a chart plus table for the top three customers.*

![AI for Database output showing Order-stage breakdown](https://cdn.futuresmart.ai/public/aidemos/c25bc35d7ab64671a43827b93ecef7a9.png?v=1)
*Output — The order-stage view combines a table and pie chart for all current statuses.*

![AI for Database output showing Delivered-vs-cancelled result](https://cdn.futuresmart.ai/public/aidemos/4dbc1a2e4b8f4f4682b89f519f2ab135.png?v=1)
*Output — The delivered-versus-cancelled result is charted and presented with all-orders and resolved-orders percentages.*

![AI for Database output showing Pending-paid result](https://cdn.futuresmart.ai/public/aidemos/c4950b61851144c0b42b735b7bc27aee.png?v=1)
*Output — The pending-but-paid exceptions are listed with delivery dates and a short explanation.*

![AI for Database output showing Month-over-month comparison](https://cdn.futuresmart.ai/public/aidemos/dfe16a774c4941daad843dfca63b3665.png?v=1)
*Output — The April-versus-May comparison shows the pending backlog increasing, with the paid share staying at zero.*

![AI for Database output showing Disambiguated pending-paid comparison](https://cdn.futuresmart.ai/public/aidemos/e2c4735710b14b168497b0befb78a231.png?v=1)
*Output — After disambiguation, the tool correctly compares the pending-paid subset and keeps the right context separate from the broader pipeline view.*

### Dot

Agentic database assistant with strong traceability, charts, and a clear clarification habit.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Dot is strong at traceability, charting, and one-step clarification when the follow-up is ambiguous. It also keeps the database answers readable for a business user.

**Where it struggled:**
- The SQL and logic are not as inline as the best tools, the insight layer is thinner, and some charts or labels are less polished than ideal.

**What came out:**

![Dot output showing Acquisition result](https://cdn.futuresmart.ai/public/aidemos/798e448c38dd4a589cf0b9da8d79403e.png?v=1)
*Output — The acquisition answer is paired with a correct comparison chart and a customer table.*

![Dot output showing SQL view](https://cdn.futuresmart.ai/public/aidemos/e299b3ec876c4979b528c3a969661634.png?v=1)
*Output — The query tab shows the SQL that powers the acquisition result.*

![Dot output showing Customer list](https://cdn.futuresmart.ai/public/aidemos/6cb80bb5e95e4875b825d5450fcf1bc9.png?v=1)
*Output — The data tab exposes the returned customer list and the period comparison side by side.*

![Dot output showing Customer ranking result](https://cdn.futuresmart.ai/public/aidemos/41e35a81a1774e13937d5225cc8e2ce3.png?v=1)
*Output — The best-customers result shows a combined rank table rather than collapsing the problem to one metric.*

![Dot output showing Unpaid-orders follow-up](https://cdn.futuresmart.ai/public/aidemos/51bcb23c33fd48c795f2e37c8db6b549.png?v=1)
*Output — The unpaid-order follow-up is scoped to the selected top customers and returns a clear answer.*

![Dot output showing Payment-method follow-up](https://cdn.futuresmart.ai/public/aidemos/0b8dfce8b21b4b1f885f2a232b343e35.png?v=1)
*Output — The payment-method drilldown is readable and shows the dominant methods for the top customers.*

![Dot output showing Order-stage breakdown](https://cdn.futuresmart.ai/public/aidemos/65909299d3444d85bcce47234b495d3c.png?v=1)
*Output — The order-stage breakdown is charted clearly with a 93-order total.*

![Dot output showing Delivered-vs-cancelled result](https://cdn.futuresmart.ai/public/aidemos/91a2ff66470b449e9bce53dc859226cb.png?v=1)
*Output — The delivered-versus-cancelled split is calculated cleanly and shown in a chart.*

![Dot output showing Pending-paid result](https://cdn.futuresmart.ai/public/aidemos/f2359777161144e599281d5571dec700.png?v=1)
*Output — The two pending-but-paid orders are identified as exceptions needing follow-up.*

![Dot output showing Clarification question](https://cdn.futuresmart.ai/public/aidemos/ecbe287345374721983bde51e292ae6c.png?v=1)
*Output — Before guessing, the tool asks the user to clarify which comparison they mean.*

![Dot output showing Comparison result](https://cdn.futuresmart.ai/public/aidemos/08bf07e8db964667abdcf7b864c6b5f9.png?v=1)
*Output — The comparison result keeps the pending-paid context and shows the same count on both dates.*

### Definite

Dashboard-first database assistant that turns chat answers into reusable dashboard views.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Strong at turning chat answers into reusable dashboards and at adding business-friendly commentary around status and payment questions. It also handles the order-pipeline workflow well once the analysis is underway.

**Where it struggled:**
- The chat experience is heavier than the top tools, and multi-metric questions can be narrowed too aggressively before the user has a chance to clarify intent.

**What came out:**

![Definite output showing Acquisition result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-customer-acquisition-result-4a7f632c85be.png)
*Output — The acquisition comparison is correct and readable, with a clear period-over-period drop.*

![Definite output showing Acquisition dashboard](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-customer-acquisition-dashboard-afae23741b1b.png)
*Output — The result can be turned into a reusable dashboard-style view, which is the product's strongest pattern.*

![Definite output showing Best-customers caution](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-best-customers-spend-focused-ca-79c30f12d21d.png)
*Output — The best-customers question is narrowed mainly toward spend, so the order-frequency part is underweighted.*

![Definite output showing Unpaid-order commentary](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-unpaid-order-business-commentar-4370c40e9f48.png)
*Output — The unpaid-order follow-up adds business commentary instead of only returning rows.*

![Definite output showing Order-stage breakdown](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-order-stages-breakdown-48578db5c51c.png)
*Output — The order-stage analysis is clean and works well as a dashboard input.*

![Definite output showing Assumption handling](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-delivered-cancelled-assumption--546dc20b16dc.png)
*Output — The tool explicitly explains how it is interpreting delivered versus cancelled outcomes.*

![Definite output showing Dashboard view](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-definite-order-pipeline-dashboard-d6d77b97ab00.png)
*Output — The order-pipeline result becomes a reusable dashboard with KPI cards and charts.*

### camelAI

A general coding agent that can query a database through code and self-correction, rather than a purpose-built NL2SQL chatbot.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- The agent can query a live database, inspect schema, self-correct, and eventually produce correct results. It also proves that a coding-agent architecture can still answer the benchmark questions.

**Where it struggled:**
- The experience is too code-centric and too slow for a typical non-technical business user, and SQL transparency is buried inside the agent workflow instead of being front and center.

**What came out:**

![camelAI output showing Acquisition result](https://cdn.futuresmart.ai/public/aidemos/6eef6a25fb534385a21235974a0f9212.png?v=1)
*Output — The tool correctly reports the 0-vs-13 acquisition result, but the explanation is buried inside a coding-agent workflow.*

![camelAI output showing Visualization](https://cdn.futuresmart.ai/public/aidemos/15baec07ad744621a5adebe8843552ff.png?v=1)
*Output — A chart is available only after a separate visualization action, not automatically on the initial answer.*

![camelAI output showing SQL trace](https://cdn.futuresmart.ai/public/aidemos/7d717bb14dda43329cfe9a79ab9c8170.png?v=1)
*Output — The schema inspection and SQL logic are visible inside a show-work panel rather than a dedicated NL2SQL surface.*

![camelAI output showing Best customers result](https://cdn.futuresmart.ai/public/aidemos/c77c77c6d0a24441b9db11454ea5d124.png?v=1)
*Output — The customer ranking result is correct, but the product behaves like a coding agent building tables rather than a natural-language analyst.*

![camelAI output showing Unpaid-orders follow-up](https://cdn.futuresmart.ai/public/aidemos/2594179746114db4a70cccebd5435bce.png?v=1)
*Output — The unpaid-order follow-up correctly identifies Rahul Sharma's unpaid order.*

![camelAI output showing Payment-method follow-up](https://cdn.futuresmart.ai/public/aidemos/fd8e803e3c1d4f39bc9608260a57a7e9.png?v=1)
*Output — The payment-method follow-up returns the observed methods for the selected customers.*

![camelAI output showing Order-stage breakdown](https://cdn.futuresmart.ai/public/aidemos/1cbaff3fd30e482f8b143b699c0801cb.png?v=1)
*Output — The stage breakdown is correct, but the experience still feels code-first and heavy.*

![camelAI output showing Delivered-vs-cancelled result](https://cdn.futuresmart.ai/public/aidemos/3800bb178c2841cfb0fc3d77c695e1db.png?v=1)
*Output — The delivered-versus-cancelled result is a polished business insight.*

![camelAI output showing Pending-paid result](https://cdn.futuresmart.ai/public/aidemos/78a48591f4674bff8c66a90dda506953.png?v=1)
*Output — The pending-but-paid result is accurate, but it still lives inside a code-oriented workflow.*

![camelAI output showing Month-over-month comparison](https://cdn.futuresmart.ai/public/aidemos/b75ca1deb78d40c4add5c184b427783b.png?v=1)
*Output — The tool explains the comparison caveat, but the overall experience remains much slower and more code-centric than the leaders.*

### Draxlr

SQL-first exploration tool with visible SQL, chart switching, exports, and dashboard-style actions.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Strong SQL visibility, good follow-up continuity, multiple chart options, and practical export/dashboard actions make it powerful for analysts. It also handles the customer-ranking chain and order-pipeline chain without manual SQL editing.

**Where it struggled:**
- It is less friendly for non-technical users, and some chart defaults or predictive assumptions are not ideal for simple business questions.

**What came out:**

![Draxlr output showing Acquisition result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-customer-acquisition-sql-output-356e55258138.png)
*Output — The customer-acquisition result is SQL-backed and technically solid, but the interface feels more like a data explorer than a guided business analyst.*

![Draxlr output showing Customer ranking result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-best-customers-sql-visible-e37e37d6f858.png)
*Output — The best-customers query exposes SQL clearly and handles the ranking logic directly.*

![Draxlr output showing Unpaid-orders follow-up](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-top-customers-unpaid-orders-99867fde6665.png)
*Output — The top-customer unpaid-order follow-up is correctly scoped to the selected customer set.*

![Draxlr output showing Payment-method follow-up](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-top-customers-payment-methods-e87aef38ae28.png)
*Output — The payment-method drilldown stays connected to the same top-customer context.*

![Draxlr output showing Order-stage breakdown](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-order-pipeline-sql-summary-6282a13f1e9c.png)
*Output — The order-pipeline query returns SQL-backed status analysis with an AI summary.*

![Draxlr output showing Chart switching](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-chart-switching-options-dca2f8d87ab9.png)
*Output — The same result can be switched among multiple chart types, which is useful for analysts.*

![Draxlr output showing CSV export](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-csv-export-action-c191a12dac77.png)
*Output — CSV export is available, so the workflow supports reuse outside the chat view.*

![Draxlr output showing Churn caution](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-draxlr-churn-assumption-sql-caution-68ce122c8fc3.png)
*Output — Predictive-style output can lean on assumptions, so churn-like questions need caution.*

### FutureSmart NL2SQL Agent

FutureSmart's own NL2SQL benchmark product, tested here as an internal reference against the same live PostgreSQL database.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- It can answer some benchmark questions, show SQL, and produce readable tables and charts, which makes it a useful internal reference. The dashboard and reporting vocabulary are aligned with the use case.

**Where it struggled:**
- The acquisition flow fails to return the prior-period comparison cleanly, the best-customers flow collapses to spend-heavy behavior, and the last comparison does not resolve the ambiguity gracefully.

**What came out:**

![FutureSmart NL2SQL Agent output showing Acquisition result](https://cdn.futuresmart.ai/public/aidemos/8046c3e804cb4e36937389df4b4f901e.png?v=1)
*Output — The tool correctly sees the empty current window, but fails to surface the previous-period comparison as a complete result.*

![FutureSmart NL2SQL Agent output showing Best customers result](https://cdn.futuresmart.ai/public/aidemos/46cc03910c4744fb80108da04813a7da.png?v=1)
*Output — The best-customers result is readable, but it effectively reduces the question to a spend-led ranking.*

![FutureSmart NL2SQL Agent output showing Customer ranking chart](https://cdn.futuresmart.ai/public/aidemos/86a7282ac8aa4f55a70287421124a2a8.png?v=1)
*Output — A bar chart is produced for the spend ranking, but the customer-frequency dimension is not treated equally.*

![FutureSmart NL2SQL Agent output showing Unpaid-orders follow-up](https://cdn.futuresmart.ai/public/aidemos/960a297b2a224573acba4f60ad943f6d.png?v=1)
*Output — The unpaid-order follow-up is answered, but the result surface is less polished than the top tools.*

![FutureSmart NL2SQL Agent output showing Payment-method follow-up](https://cdn.futuresmart.ai/public/aidemos/4b34826c18f14809beee611be3fce360.png?v=1)
*Output — The payment-method drilldown is shown with SQL, but the output remains more technical than business-friendly.*

![FutureSmart NL2SQL Agent output showing Order-stage breakdown](https://cdn.futuresmart.ai/public/aidemos/23652ff2b5d349d596e618b7f9d5bff8.png?v=1)
*Output — The current-status breakdown is usable, but not differentiated enough from the stronger products.*

![FutureSmart NL2SQL Agent output showing Delivered-vs-cancelled result](https://cdn.futuresmart.ai/public/aidemos/83e943b58f5640f8b9306e6de56c4403.png?v=1)
*Output — The delivered-versus-cancelled calculation is present, but the comparison handling is weaker than the leaders.*

![FutureSmart NL2SQL Agent output showing Pending-paid result](https://cdn.futuresmart.ai/public/aidemos/30ec0d411cf740f8a848912f95ce5e9d.png?v=1)
*Output — The pending-but-paid check is visible, but the result is more procedural than insightful.*

![FutureSmart NL2SQL Agent output showing Comparison refusal](https://cdn.futuresmart.ai/public/aidemos/ca4b1a9f06a4494e9b573abc41673044.png?v=1)
*Output — The final comparison can give up on the requested time window instead of cleanly resolving the user intent.*

![FutureSmart NL2SQL Agent output showing Disambiguated reask](https://cdn.futuresmart.ai/public/aidemos/0517a6d8954b47519e3df81663264c5b.png?v=1)
*Output — Even after rephrasing, the comparison still does not resolve cleanly, which keeps the tool below the leaders.*

### Basedash

Clean agentic BI/chat UX that shows visible steps, produces readable tables and charts, and can self-heal SQL.

> **Screenshot** — Input 1 benchmark — Shared benchmark input 1 for customer acquisition.

> **Screenshot** — Input 2 benchmark — Shared benchmark input 2 for best customers and follow-ups.

> **Screenshot** — Input 3 benchmark — Shared benchmark input 3 for order pipeline and follow-ups.

**What worked:**
- Delivered the cleanest UX of the tested tools, with simple readability, visible steps, and self-healing SQL behavior. It also generated a useful chart for the acquisition question without requiring SQL knowledge.

**Where it struggled:**
- Ambiguous follow-up scope can narrow silently instead of asking a clarification question first.

**What came out:**

![Basedash output showing Acquisition result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-customer-acquisition-table-char-c88e12ecfc3a.png)
*Output — Basedash shows the acquisition comparison as a simple table plus chart, with a clear drop from the previous 90 days to the last 90 days.*

![Basedash output showing Agentic steps](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-agentic-steps-customer-acquisit-9b1f2e1b6c36.png)
*Output — The product surfaces visible agent steps before the final answer, which improves trust without adding clutter.*

![Basedash output showing Customer ranking result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-best-customers-multi-metric-out-852984c11f6d.png)
*Output — The best-customers result handles order count and spend together and keeps the output readable for business users.*

![Basedash output showing Follow-up scope caution](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-top3-followup-scope-caution-82ae85688e91.png)
*Output — The follow-up continues with one interpretation of the top 3, but it does not ask the user to clarify which ranking they meant.*

![Basedash output showing Payment-method follow-up](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-payment-method-followup-e82ca447c86f.png)
*Output — The payment-method follow-up stays on the selected customer set and remains easy to read.*

![Basedash output showing SQL self-healing retry](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-sql-self-healing-retry-ae0f662eaf8b.png)
*Output — When SQL errors occur, Basedash retries and recovers instead of stopping at the failure.*

![Basedash output showing Delivered-vs-cancelled result](https://d3epheqghktydj.cloudfront.net/query-live-databases-using-plain-english-basedash-delivered-cancelled-percentage-f2cf62a1af3b.png)
*Output — The delivered-versus-cancelled output is clean and business-friendly, with the percentage split shown clearly.*

## Evidence (first-party, tested)

*192 tested cells · 140/192 artifact-verified. Cite a cell by its Evidence ID, e.g. `ev:ai-for-database·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling`.*

| Tool | Criterion | Scenario | Verdict | Proof | Evidence ID |
| --- | --- | --- | --- | --- | --- |
| AI for Database | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/9e7ad27c49f04104a3656a73cef8902b.png?v=1) | `ev:ai-for-database·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| AI for Database | Ambiguity Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/27cee542eeb24661b605482c5dae20a2.png?v=1) | `ev:ai-for-database·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·ambiguity-handling` |
| AI for Database | Ambiguity Handling | cross-scenario | ◐ mixed | 👁 observed | `ev:ai-for-database·cross·ambiguity-handling` |
| AI for Database | Business Insight | Order pipeline breakdown with paid-pending edge case and last-month comparison | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2ae319db105341fea5c073c13cf7d4ee.png?v=1) | `ev:ai-for-database·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·business-insight` |
| AI for Database | Business Insight | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/73ae37735073485283aafc12d5ae183b.png?v=1) | `ev:ai-for-database·cross·business-insight` |
| AI for Database | Chart / Visualization Support | cross-scenario | ◐ mixed | 👁 observed | `ev:ai-for-database·cross·chart-visualization-support` |
| AI for Database | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/73ae37735073485283aafc12d5ae183b.png?v=1) | `ev:ai-for-database·cross·dashboard-workflow` |
| AI for Database | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/73ae37735073485283aafc12d5ae183b.png?v=1) | `ev:ai-for-database·cross·export-reuse` |
| AI for Database | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/27cee542eeb24661b605482c5dae20a2.png?v=1) | `ev:ai-for-database·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| AI for Database | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✗ failed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/beb3be5f949c403083b813a7d7d8ed80.png?v=1) | `ev:ai-for-database·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| AI for Database | Follow-Up Context | cross-scenario | ◐ mixed | 👁 observed | `ev:ai-for-database·cross·follow-up-context` |
| AI for Database | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d93976964b0a432db4a366bbc95bd76c.png?v=1) | `ev:ai-for-database·cross·fs-learning-value` |
| AI for Database | Plain English Query Handling | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/3735db40c721439f908bc3375d7e325c.mp4?v=1) | `ev:ai-for-database·cross·plain-english-query-handling` |
| AI for Database | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/73ae37735073485283aafc12d5ae183b.png?v=1) | `ev:ai-for-database·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| AI for Database | SQL Generation | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/5756a229ea64445ca09e7056c1788ae1.png?v=1) | `ev:ai-for-database·cross·sql-generation` |
| AI for Database | SQL Visibility | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/5756a229ea64445ca09e7056c1788ae1.png?v=1) | `ev:ai-for-database·cross·sql-visibility` |
| Anomaly AI | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/dd400dc0a3b5474299b4e9edac56b2b5.png?v=1) | `ev:anomaly-ai·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| Anomaly AI | Business Insight | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/bf427aa7e9184aeab1e88ac115f6e825.png?v=1) | `ev:anomaly-ai·cross·business-insight` |
| Anomaly AI | Chart / Visualization Support | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/a421adfe46724ce8b18e68873244f3c4.png?v=1) | `ev:anomaly-ai·cross·chart-visualization-support` |
| Anomaly AI | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/a421adfe46724ce8b18e68873244f3c4.png?v=1) | `ev:anomaly-ai·cross·dashboard-workflow` |
| Anomaly AI | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/a421adfe46724ce8b18e68873244f3c4.png?v=1) | `ev:anomaly-ai·cross·export-reuse` |
| Anomaly AI | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✗ failed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/37e5963be794432da14f9cdcf638885f.png?v=1) | `ev:anomaly-ai·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| Anomaly AI | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/1111f7bb130c479f82fdaa7d41c53dc9.png?v=1) | `ev:anomaly-ai·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| Anomaly AI | Follow-Up Context | cross-scenario | ◐ mixed | 👁 observed | `ev:anomaly-ai·cross·follow-up-context` |
| Anomaly AI | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/37e5963be794432da14f9cdcf638885f.png?v=1) | `ev:anomaly-ai·cross·fs-learning-value` |
| Anomaly AI | Plain English Query Handling | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/12999d5fbf424e23bf60ddb510c98929.png?v=1) | `ev:anomaly-ai·cross·plain-english-query-handling` |
| Anomaly AI | Result Readability | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/bf427aa7e9184aeab1e88ac115f6e825.png?v=1) | `ev:anomaly-ai·cross·result-readability` |
| Anomaly AI | SQL Generation | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/3cebabc822874cdeb31be2d566a6ceb7.png?v=1) | `ev:anomaly-ai·cross·sql-generation` |
| Anomaly AI | SQL Visibility | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/96a7c0ab5a4241598712c95f7930eb2c.png?v=1) | `ev:anomaly-ai·cross·sql-visibility` |
| AskYourDatabase | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ec0ed41fe3dd45b5b13b082d174be6b7.png?v=1) | `ev:askyourdatabase·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| AskYourDatabase | Ambiguity Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b08d5704766c40d3b4f7c08c570e25c3.png?v=1) | `ev:askyourdatabase·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·ambiguity-handling` |
| AskYourDatabase | Ambiguity Handling | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/4913a8ac12eb420a80619dec22708d2b.png?v=1) | `ev:askyourdatabase·cross·ambiguity-handling` |
| AskYourDatabase | Business Insight | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/96d7b37f20554dadb69d8d8a65af2b72.png?v=1) | `ev:askyourdatabase·cross·business-insight` |
| AskYourDatabase | Business Insight | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f036ab58243a44ecbcc49fd0fbaae644.png?v=1) | `ev:askyourdatabase·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·business-insight` |
| AskYourDatabase | Business Insight | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/a86f17ae7bfc4061b79dd78e334e7f02.png?v=1) | `ev:askyourdatabase·customer-acquisition-in-the-last-90-days-vs-previous-90-days·business-insight` |
| AskYourDatabase | Business Insight | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ec0ed41fe3dd45b5b13b082d174be6b7.png?v=1) | `ev:askyourdatabase·best-customers-with-unpaid-order-and-payment-method-follow-ups·business-insight` |
| AskYourDatabase | Chart / Visualization Support | cross-scenario | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2eb60a8ad02f4591a45fef9c9c783dc6.png?v=1) | `ev:askyourdatabase·cross·chart-visualization-support` |
| AskYourDatabase | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f36d988ed7254ec282517e3213df964d.png?v=1) | `ev:askyourdatabase·cross·dashboard-workflow` |
| AskYourDatabase | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f36d988ed7254ec282517e3213df964d.png?v=1) | `ev:askyourdatabase·cross·export-reuse` |
| AskYourDatabase | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b08d5704766c40d3b4f7c08c570e25c3.png?v=1) | `ev:askyourdatabase·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| AskYourDatabase | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b566115874cd4ee687494cc959e0239c.png?v=1) | `ev:askyourdatabase·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| AskYourDatabase | Follow-Up Context | cross-scenario | ◐ mixed | 👁 observed | `ev:askyourdatabase·cross·follow-up-context` |
| AskYourDatabase | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2eb60a8ad02f4591a45fef9c9c783dc6.png?v=1) | `ev:askyourdatabase·cross·fs-learning-value` |
| AskYourDatabase | Plain English Query Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f53605d222624c199b365f4beaf646f5.png?v=1) | `ev:askyourdatabase·best-customers-with-unpaid-order-and-payment-method-follow-ups·plain-english-query-handling` |
| AskYourDatabase | Plain English Query Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b333e9493695402998ebb026ab42195c.png?v=1) | `ev:askyourdatabase·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·plain-english-query-handling` |
| AskYourDatabase | Plain English Query Handling | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/08d7785e86b14d96bfeeced0d7a87ddd.png?v=1) | `ev:askyourdatabase·cross·plain-english-query-handling` |
| AskYourDatabase | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/9540b89e4d4240989d9e26e931b21cb8.png?v=1) | `ev:askyourdatabase·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| AskYourDatabase | Result Readability | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/96d7b37f20554dadb69d8d8a65af2b72.png?v=1) | `ev:askyourdatabase·cross·result-readability` |
| AskYourDatabase | Result Readability | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b333e9493695402998ebb026ab42195c.png?v=1) | `ev:askyourdatabase·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·result-readability` |
| AskYourDatabase | Result Readability | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ec0ed41fe3dd45b5b13b082d174be6b7.png?v=1) | `ev:askyourdatabase·best-customers-with-unpaid-order-and-payment-method-follow-ups·result-readability` |
| AskYourDatabase | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/a86f17ae7bfc4061b79dd78e334e7f02.png?v=1) | `ev:askyourdatabase·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| AskYourDatabase | SQL Generation | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b08d5704766c40d3b4f7c08c570e25c3.png?v=1) | `ev:askyourdatabase·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·sql-generation` |
| AskYourDatabase | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/9540b89e4d4240989d9e26e931b21cb8.png?v=1) | `ev:askyourdatabase·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| AskYourDatabase | SQL Generation | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b566115874cd4ee687494cc959e0239c.png?v=1) | `ev:askyourdatabase·best-customers-with-unpaid-order-and-payment-method-follow-ups·sql-generation` |
| AskYourDatabase | SQL Generation | cross-scenario | ✓ worked | 👁 observed | `ev:askyourdatabase·cross·sql-generation` |
| AskYourDatabase | SQL Visibility | cross-scenario | ✓ worked | 👁 observed | `ev:askyourdatabase·cross·sql-visibility` |
| Basedash | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ⚠ struggled | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/1d5ee66912954067955529095f49f9ef.png?v=1) | `ev:basedash·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| Basedash | Ambiguity Handling | cross-scenario | ⚠ struggled | 👁 observed | `ev:basedash·cross·ambiguity-handling` |
| Basedash | Business Insight | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b32adc19ccfc434bb534d9c3684fee55.png?v=1) | `ev:basedash·best-customers-with-unpaid-order-and-payment-method-follow-ups·business-insight` |
| Basedash | Business Insight | cross-scenario | ◐ mixed | 👁 observed | `ev:basedash·cross·business-insight` |
| Basedash | Business Insight | Customer acquisition in the last 90 days vs previous 90 days | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/6e48cc55f9e34b8289eb052c44b186bb.png?v=1) | `ev:basedash·customer-acquisition-in-the-last-90-days-vs-previous-90-days·business-insight` |
| Basedash | Chart / Visualization Support | cross-scenario | ◐ mixed | 👁 observed | `ev:basedash·cross·chart-visualization-support` |
| Basedash | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/6e48cc55f9e34b8289eb052c44b186bb.png?v=1) | `ev:basedash·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| Basedash | Plain English Query Handling | cross-scenario | ✓ worked | 👁 observed | `ev:basedash·cross·plain-english-query-handling` |
| Basedash | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/6e48cc55f9e34b8289eb052c44b186bb.png?v=1) | `ev:basedash·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| Basedash | Result Readability | cross-scenario | ✓ worked | 👁 observed | `ev:basedash·cross·result-readability` |
| Basedash | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/6e48cc55f9e34b8289eb052c44b186bb.png?v=1) | `ev:basedash·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| Basedash | SQL Generation | cross-scenario | ◐ mixed | 👁 observed | `ev:basedash·cross·sql-generation` |
| BlazeSQL | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/060201dc6b174181bc474b4e5563f5d7.png?v=1) | `ev:blazesql·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| BlazeSQL | Ambiguity Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/874996691797438e932bceab62ab151a.png?v=1) | `ev:blazesql·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·ambiguity-handling` |
| BlazeSQL | Ambiguity Handling | cross-scenario | ✓ worked | 👁 observed | `ev:blazesql·cross·ambiguity-handling` |
| BlazeSQL | Business Insight | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/0528899ca2d74bccac992f1fe88a411b.png?v=1) | `ev:blazesql·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·business-insight` |
| BlazeSQL | Business Insight | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d46e741481484410a17a5845e5c0fc4b.png?v=1) | `ev:blazesql·customer-acquisition-in-the-last-90-days-vs-previous-90-days·business-insight` |
| BlazeSQL | Business Insight | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8659db3b02aa49d68b26dd7e6267c998.png?v=1) | `ev:blazesql·best-customers-with-unpaid-order-and-payment-method-follow-ups·business-insight` |
| BlazeSQL | Business Insight | cross-scenario | ✓ worked | 👁 observed | `ev:blazesql·cross·business-insight` |
| BlazeSQL | Chart / Visualization Support | cross-scenario | ✓ worked | 👁 observed | `ev:blazesql·cross·chart-visualization-support` |
| BlazeSQL | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/772a970e09504e26bb3b65c7d84c2ac0.mp4?v=1) | `ev:blazesql·cross·dashboard-workflow` |
| BlazeSQL | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/772a970e09504e26bb3b65c7d84c2ac0.mp4?v=1) | `ev:blazesql·cross·export-reuse` |
| BlazeSQL | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8659db3b02aa49d68b26dd7e6267c998.png?v=1) | `ev:blazesql·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| BlazeSQL | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d46e741481484410a17a5845e5c0fc4b.png?v=1) | `ev:blazesql·cross·fs-learning-value` |
| BlazeSQL | Plain English Query Handling | cross-scenario | ✓ worked | 👁 observed | `ev:blazesql·cross·plain-english-query-handling` |
| BlazeSQL | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d46e741481484410a17a5845e5c0fc4b.png?v=1) | `ev:blazesql·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| BlazeSQL | Plain English Query Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d87335383e9a48ffab52b7db6e507b69.png?v=1) | `ev:blazesql·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·plain-english-query-handling` |
| BlazeSQL | Result Readability | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8659db3b02aa49d68b26dd7e6267c998.png?v=1) | `ev:blazesql·cross·result-readability` |
| BlazeSQL | SQL Generation | cross-scenario | ✓ worked | 👁 observed | `ev:blazesql·cross·sql-generation` |
| BlazeSQL | SQL Generation | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d87335383e9a48ffab52b7db6e507b69.png?v=1) | `ev:blazesql·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·sql-generation` |
| BlazeSQL | SQL Generation | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/7b4a67af644f4cf4b3cb9c3ab3e11265.png?v=1) | `ev:blazesql·best-customers-with-unpaid-order-and-payment-method-follow-ups·sql-generation` |
| BlazeSQL | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/75576e4a581c4c71bfbfff01d5d3c44f.png?v=1) | `ev:blazesql·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| BlazeSQL | SQL Visibility | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/75576e4a581c4c71bfbfff01d5d3c44f.png?v=1) | `ev:blazesql·cross·sql-visibility` |
| camelAI | Ambiguity Handling | cross-scenario | ✓ worked | 👁 observed | `ev:camelai·cross·ambiguity-handling` |
| camelAI | Ambiguity Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/71017f6dd1314fc0ba794be697bc8f3c.png?v=1) | `ev:camelai·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·ambiguity-handling` |
| camelAI | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/1c1df761c0854b5da1ff79f846fd34b9.png?v=1) | `ev:camelai·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| camelAI | Business Insight | cross-scenario | ⚠ struggled | 👁 observed | `ev:camelai·cross·business-insight` |
| camelAI | Business Insight | Best customers with unpaid-order and payment-method follow-ups | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/1c1df761c0854b5da1ff79f846fd34b9.png?v=1) | `ev:camelai·best-customers-with-unpaid-order-and-payment-method-follow-ups·business-insight` |
| camelAI | Business Insight | Customer acquisition in the last 90 days vs previous 90 days | ✗ failed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2c2f039a66f34e54bac38fd77e08da14.png?v=1) | `ev:camelai·customer-acquisition-in-the-last-90-days-vs-previous-90-days·business-insight` |
| camelAI | Chart / Visualization Support | cross-scenario | ◐ mixed | 👁 observed | `ev:camelai·cross·chart-visualization-support` |
| camelAI | Dashboard Workflow | cross-scenario | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8c7d811260924626a5325885bd7cbd29.mp4?v=1) | `ev:camelai·cross·dashboard-workflow` |
| camelAI | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/1f3b3aea3c064f368b1016abed8c926b.png?v=1) | `ev:camelai·cross·export-reuse` |
| camelAI | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ce8a71702b5d416bbf3cce77acb2f7ec.png?v=1) | `ev:camelai·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| camelAI | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b973a325c8164235a884513d207e5b1d.png?v=1) | `ev:camelai·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| camelAI | Follow-Up Context | cross-scenario | ✓ worked | 👁 observed | `ev:camelai·cross·follow-up-context` |
| camelAI | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b5bb1feff33b4d2ba436a7c256d994d9.png?v=1) | `ev:camelai·cross·fs-learning-value` |
| camelAI | Plain English Query Handling | cross-scenario | ✓ worked | 👁 observed | `ev:camelai·cross·plain-english-query-handling` |
| camelAI | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2c2f039a66f34e54bac38fd77e08da14.png?v=1) | `ev:camelai·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| camelAI | Plain English Query Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ee158b4b95f746dbb8e2dea91387d55d.png?v=1) | `ev:camelai·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·plain-english-query-handling` |
| camelAI | Result Readability | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2c2f039a66f34e54bac38fd77e08da14.png?v=1) | `ev:camelai·cross·result-readability` |
| camelAI | SQL Generation | cross-scenario | ✓ worked | 👁 observed | `ev:camelai·cross·sql-generation` |
| camelAI | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/b5bb1feff33b4d2ba436a7c256d994d9.png?v=1) | `ev:camelai·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| camelAI | SQL Generation | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/c7cb9fc561754185bd8eeac207f390d9.png?v=1) | `ev:camelai·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·sql-generation` |
| camelAI | SQL Visibility | cross-scenario | ◐ mixed | 👁 observed | `ev:camelai·cross·sql-visibility` |
| Definite | Business Insight | cross-scenario | ✓ worked | 👁 observed | `ev:definite·cross·business-insight` |
| Definite | Chart / Visualization Support | Order pipeline breakdown with paid-pending edge case and last-month comparison | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/45e506b8357642319672c53420b34872.mp4?v=1) | `ev:definite·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·chart-visualization-support` |
| Definite | Chart / Visualization Support | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/c98110c0dae6439eb3f31e1a3beb663d.mp4?v=1) | `ev:definite·cross·chart-visualization-support` |
| Definite | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/c98110c0dae6439eb3f31e1a3beb663d.mp4?v=1) | `ev:definite·cross·dashboard-workflow` |
| Definite | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/c98110c0dae6439eb3f31e1a3beb663d.mp4?v=1) | `ev:definite·cross·export-reuse` |
| Definite | Follow-Up Context | cross-scenario | ✓ worked | 👁 observed | `ev:definite·cross·follow-up-context` |
| Definite | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ab045ce6245f4fa4b7df9db75d98929b.png?v=1) | `ev:definite·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| Definite | FS Learning Value | cross-scenario | ✓ worked | 👁 observed | `ev:definite·cross·fs-learning-value` |
| Definite | Plain English Query Handling | cross-scenario | ◐ mixed | 👁 observed | `ev:definite·cross·plain-english-query-handling` |
| Definite | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/9e37dd7c62974ba99d64cfedd0ef0813.png?v=1) | `ev:definite·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| Definite | Result Readability | cross-scenario | ✓ worked | 👁 observed | `ev:definite·cross·result-readability` |
| Definite | Result Readability | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d63a94398d514ef98b9ad069bd15feea.png?v=1) | `ev:definite·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·result-readability` |
| Dot | Ambiguity Handling | cross-scenario | ✓ worked | 👁 observed | `ev:dot·cross·ambiguity-handling` |
| Dot | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/c126c58ac82e4d899b11a7006a73d94d.png?v=1) | `ev:dot·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| Dot | Ambiguity Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f4a355dee7cc4264abda5070118c15f6.png?v=1) | `ev:dot·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·ambiguity-handling` |
| Dot | Business Insight | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f66e88efc06343bdb64af3c00e3d1003.png?v=1) | `ev:dot·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·business-insight` |
| Dot | Business Insight | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/c126c58ac82e4d899b11a7006a73d94d.png?v=1) | `ev:dot·best-customers-with-unpaid-order-and-payment-method-follow-ups·business-insight` |
| Dot | Business Insight | Customer acquisition in the last 90 days vs previous 90 days | ⚠ struggled | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8ce008eac9564d3cb0a6a0cf9a6cb5b4.png?v=1) | `ev:dot·customer-acquisition-in-the-last-90-days-vs-previous-90-days·business-insight` |
| Dot | Chart / Visualization Support | cross-scenario | ◐ mixed | 👁 observed | `ev:dot·cross·chart-visualization-support` |
| Dot | Dashboard Workflow | cross-scenario | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/45ef8c30f8f14b8bbb2d43aecc8efa53.mp4?v=1) | `ev:dot·cross·dashboard-workflow` |
| Dot | Export / Reuse | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/45ef8c30f8f14b8bbb2d43aecc8efa53.mp4?v=1) | `ev:dot·cross·export-reuse` |
| Dot | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/e94fab739e414924b69bd67beb632d2f.png?v=1) | `ev:dot·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| Dot | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/83c5f85ec0d44671817d813dda770ef7.png?v=1) | `ev:dot·cross·fs-learning-value` |
| Dot | Plain English Query Handling | cross-scenario | ✓ worked | 👁 observed | `ev:dot·cross·plain-english-query-handling` |
| Dot | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8ce008eac9564d3cb0a6a0cf9a6cb5b4.png?v=1) | `ev:dot·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| Dot | Plain English Query Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ef5af24b11994f87b7003541bb6a49b2.png?v=1) | `ev:dot·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·plain-english-query-handling` |
| Dot | Result Readability | cross-scenario | ◐ mixed | 👁 observed | `ev:dot·cross·result-readability` |
| Dot | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/8ce008eac9564d3cb0a6a0cf9a6cb5b4.png?v=1) | `ev:dot·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| Dot | Result Readability | Best customers with unpaid-order and payment-method follow-ups | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/e94fab739e414924b69bd67beb632d2f.png?v=1) | `ev:dot·best-customers-with-unpaid-order-and-payment-method-follow-ups·result-readability` |
| Dot | SQL Generation | cross-scenario | ✓ worked | 👁 observed | `ev:dot·cross·sql-generation` |
| Dot | SQL Generation | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/de47c420c7294041881ce9083c43523b.png?v=1) | `ev:dot·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·sql-generation` |
| Dot | SQL Generation | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/660535357d404e5ea29b115bbc94f21f.png?v=1) | `ev:dot·best-customers-with-unpaid-order-and-payment-method-follow-ups·sql-generation` |
| Dot | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/2245ba6d917b4b0dba2fd4233ee6ca0a.png?v=1) | `ev:dot·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| Dot | SQL Visibility | cross-scenario | ✓ worked | 👁 observed | `ev:dot·cross·sql-visibility` |
| Draxlr | Ambiguity Handling | cross-scenario | ◐ mixed | 👁 observed | `ev:draxlr·cross·ambiguity-handling` |
| Draxlr | Ambiguity Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/452862f674014056ad7ea901461c5dcd.png?v=1) | `ev:draxlr·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·ambiguity-handling` |
| Draxlr | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ab41b8340d0a45188a25417725b1cede.png?v=1) | `ev:draxlr·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| Draxlr | Business Insight | Customer acquisition in the last 90 days vs previous 90 days | ⚠ struggled | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/91fb51d4c97f47dea6b4379b4c10b82e.png?v=1) | `ev:draxlr·customer-acquisition-in-the-last-90-days-vs-previous-90-days·business-insight` |
| Draxlr | Business Insight | cross-scenario | ⚠ struggled | 👁 observed | `ev:draxlr·cross·business-insight` |
| Draxlr | Business Insight | Order pipeline breakdown with paid-pending edge case and last-month comparison | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/67b55a396aca4f98ab341e075507e22b.png?v=1) | `ev:draxlr·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·business-insight` |
| Draxlr | Business Insight | Best customers with unpaid-order and payment-method follow-ups | ⚠ struggled | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/565a041698d44f05ad75ba27fe1fd48d.png?v=1) | `ev:draxlr·best-customers-with-unpaid-order-and-payment-method-follow-ups·business-insight` |
| Draxlr | Chart / Visualization Support | cross-scenario | ◐ mixed | 👁 observed | `ev:draxlr·cross·chart-visualization-support` |
| Draxlr | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/f70117ef724c4f2483938d9154b9aa35.mp4?v=1) | `ev:draxlr·cross·dashboard-workflow` |
| Draxlr | Export / Reuse | cross-scenario | ✓ worked | 👁 observed | `ev:draxlr·cross·export-reuse` |
| Draxlr | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/46906a3c110d44ff84f116f7abfa3c2d.mp4?v=1) | `ev:draxlr·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| Draxlr | Follow-Up Context | cross-scenario | ✓ worked | 👁 observed | `ev:draxlr·cross·follow-up-context` |
| Draxlr | Follow-Up Context | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/565a041698d44f05ad75ba27fe1fd48d.png?v=1) | `ev:draxlr·best-customers-with-unpaid-order-and-payment-method-follow-ups·follow-up-context` |
| Draxlr | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/91fb51d4c97f47dea6b4379b4c10b82e.png?v=1) | `ev:draxlr·cross·fs-learning-value` |
| Draxlr | Plain English Query Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ab41b8340d0a45188a25417725b1cede.png?v=1) | `ev:draxlr·best-customers-with-unpaid-order-and-payment-method-follow-ups·plain-english-query-handling` |
| Draxlr | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/91fb51d4c97f47dea6b4379b4c10b82e.png?v=1) | `ev:draxlr·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| Draxlr | Plain English Query Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/67b55a396aca4f98ab341e075507e22b.png?v=1) | `ev:draxlr·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·plain-english-query-handling` |
| Draxlr | Plain English Query Handling | cross-scenario | ✓ worked | 👁 observed | `ev:draxlr·cross·plain-english-query-handling` |
| Draxlr | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ⚠ struggled | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/91fb51d4c97f47dea6b4379b4c10b82e.png?v=1) | `ev:draxlr·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| Draxlr | Result Readability | cross-scenario | ⚠ struggled | 👁 observed | `ev:draxlr·cross·result-readability` |
| Draxlr | Result Readability | Best customers with unpaid-order and payment-method follow-ups | ⚠ struggled | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ab41b8340d0a45188a25417725b1cede.png?v=1) | `ev:draxlr·best-customers-with-unpaid-order-and-payment-method-follow-ups·result-readability` |
| Draxlr | SQL Generation | cross-scenario | ✓ worked | 👁 observed | `ev:draxlr·cross·sql-generation` |
| Draxlr | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/91fb51d4c97f47dea6b4379b4c10b82e.png?v=1) | `ev:draxlr·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| Draxlr | SQL Generation | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/eb95ee5e6ace4480948612ae702bfd26.png?v=1) | `ev:draxlr·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·sql-generation` |
| Draxlr | SQL Generation | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/ab41b8340d0a45188a25417725b1cede.png?v=1) | `ev:draxlr·best-customers-with-unpaid-order-and-payment-method-follow-ups·sql-generation` |
| Draxlr | SQL Visibility | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/91fb51d4c97f47dea6b4379b4c10b82e.png?v=1) | `ev:draxlr·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-visibility` |
| Querio | Ambiguity Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/364651fb80d04b7299109e6465d39e8d.png?v=1) | `ev:querio·best-customers-with-unpaid-order-and-payment-method-follow-ups·ambiguity-handling` |
| Querio | Business Insight | cross-scenario | ✓ worked | 👁 observed | `ev:querio·cross·business-insight` |
| Querio | Business Insight | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/aed0f9d2fefa4a96be3e95444911761f.png?v=1) | `ev:querio·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·business-insight` |
| Querio | Chart / Visualization Support | cross-scenario | ✓ worked | 👁 observed | `ev:querio·cross·chart-visualization-support` |
| Querio | Dashboard Workflow | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/e89e34d16b444685828e043904cbb882.mp4?v=1) | `ev:querio·cross·dashboard-workflow` |
| Querio | Export / Reuse | cross-scenario | ✓ worked | 👁 observed | `ev:querio·cross·export-reuse` |
| Querio | Follow-Up Context | cross-scenario | ◐ mixed | 👁 observed | `ev:querio·cross·follow-up-context` |
| Querio | Follow-Up Context | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✗ failed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/aed0f9d2fefa4a96be3e95444911761f.png?v=1) | `ev:querio·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·follow-up-context` |
| Querio | FS Learning Value | cross-scenario | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/aed0f9d2fefa4a96be3e95444911761f.png?v=1) | `ev:querio·cross·fs-learning-value` |
| Querio | Plain English Query Handling | cross-scenario | ✓ worked | 👁 observed | `ev:querio·cross·plain-english-query-handling` |
| Querio | Plain English Query Handling | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d042c97da21a41a495c77b4a493283ee.png?v=1) | `ev:querio·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·plain-english-query-handling` |
| Querio | Plain English Query Handling | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/4342b34dad4044fca7ee7da4545fef6f.png?v=1) | `ev:querio·customer-acquisition-in-the-last-90-days-vs-previous-90-days·plain-english-query-handling` |
| Querio | Plain English Query Handling | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/364651fb80d04b7299109e6465d39e8d.png?v=1) | `ev:querio·best-customers-with-unpaid-order-and-payment-method-follow-ups·plain-english-query-handling` |
| Querio | Result Readability | cross-scenario | ◐ mixed | 👁 observed | `ev:querio·cross·result-readability` |
| Querio | Result Readability | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/4342b34dad4044fca7ee7da4545fef6f.png?v=1) | `ev:querio·customer-acquisition-in-the-last-90-days-vs-previous-90-days·result-readability` |
| Querio | Result Readability | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/d042c97da21a41a495c77b4a493283ee.png?v=1) | `ev:querio·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·result-readability` |
| Querio | Result Readability | Best customers with unpaid-order and payment-method follow-ups | ◐ mixed | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/a2212df102a643b4bd41951fd064776d.png?v=1) | `ev:querio·best-customers-with-unpaid-order-and-payment-method-follow-ups·result-readability` |
| Querio | SQL Generation | cross-scenario | ✓ worked | 👁 observed | `ev:querio·cross·sql-generation` |
| Querio | SQL Generation | Order pipeline breakdown with paid-pending edge case and last-month comparison | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/4322f0ecc4f64bef984ddaa9efb7209a.png?v=1) | `ev:querio·order-pipeline-breakdown-with-paid-pending-edge-case-and-last-month-comparison·sql-generation` |
| Querio | SQL Generation | Customer acquisition in the last 90 days vs previous 90 days | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/4342b34dad4044fca7ee7da4545fef6f.png?v=1) | `ev:querio·customer-acquisition-in-the-last-90-days-vs-previous-90-days·sql-generation` |
| Querio | SQL Generation | Best customers with unpaid-order and payment-method follow-ups | ✓ worked | 🧾 [proof](https://cdn.futuresmart.ai/public/aidemos/364651fb80d04b7299109e6465d39e8d.png?v=1) | `ev:querio·best-customers-with-unpaid-order-and-payment-method-follow-ups·sql-generation` |
| Querio | SQL Visibility | cross-scenario | ✓ worked | 👁 observed | `ev:querio·cross·sql-visibility` |

> 🧾 = artifact-verified (proof captured) · 👁 = observed (noted, no artifact) · verdicts: worked / mixed / struggled / failed.

## Final Take

Anomaly AI is the page’s overall winner and the safest all-around pick: it is fully measured and scored 5.0/5.0 on every ranking check that decides the result — ambiguity handling, business insight, plain-English queries, result readability, and SQL generation. That makes it the strongest choice when you want a traceable, self-verifying business-analysis flow without obvious gaps.

BlazeSQL is the closest runner-up. It matches Anomaly AI on the five decisive checks, but the scorecard shows more mixed support on the non-ranking dimensions, especially chart support and export/reuse. If you care more about follow-up context and dashboard workflow, BlazeSQL is the strongest alternative. AskYourDatabase is a good fit for conversational SQL with solid follow-up reasoning, but charts need a second ask. Querio is the better fit when transparent SQL generation and charts matter most, though it gives up some business insight and result readability. Basedash works well for clean, conversational business answers, but it is much weaker when questions get ambiguous and it offers very limited SQL visibility. Definite has strong business-answer and dashboard scores, but it is only partly tested on the decisive checks, so it stays below the fully measured tools by policy even though some of its measured scores look strong.

Tested as of June 2026 · re-verified monthly.

## Need a custom AI solution for this use case?

If you are looking to build a custom natural language to SQL, database query assistant, or analytics chatbot for your business or internal workflow, email us at [contact@futuresmart.ai](mailto:contact@futuresmart.ai).

### Found something inaccurate or missing?

We try to keep our AI research accurate and useful. If you found outdated information, an issue, or have a suggestion, email us at [collaborate@aidemos.com](mailto:collaborate@aidemos.com).