{"observation":{"id":"820cfe6d-d216-49fe-bb1f-78694880d4d4","tool":"askyourdatabase","tool_name":"AskYourDatabase","criterion":"business-insight","criterion_name":"Business Insight","criterion_definition":"Does it explain what the result means?","criterion_evidence_type":"transformation","criterion_rank_role":null,"criterion_rank_role_reason":null,"scenario":"best-customers-with-unpaid-order-and-payment-method-follow-ups","scenario_name":"Best customers with unpaid-order and payment-method follow-ups","group_tag":"ecommerce-nl2sql-benchmark","scenario_description":"A conversational multi-table customer analysis that identifies best customers by both order volume and spend, then drills into unpaid orders and payment methods for the top 3.","modality":"text","input_text":"Who are my best customers — the ones who order the most and spend the most?\n\nFollow-up 1: For the top 3 from that list — do any of them have unpaid orders?\n\nFollow-up 2: What payment methods do these top 3 usually use?","input_artifact_refs":["AskYourDatabase_Best_Customers_SQL_Visible-2.png","AskYourDatabase_Top_Customers_Unpaid_Orders-2.png","Draxlr_Top_Customers_Payment_Methods.png"],"stresses":["Ambiguous business-term interpretation","Multi-table joins across customers orders and payments","Aggregation and ranking","Follow-up context retention","Scoped drill-down to the top 3 customers","Readable customer-level output"],"verdict":"worked","score":null,"score_total":null,"note":"The follow-up reasoning went beyond listing payments by flagging Mohan Vishe's unpaid shipped orders as a process risk and noting that Rahul Sharma's pattern was largely UPI-driven.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://d3epheqghktydj.cloudfront.net/askyourdatabase-image-6-902f430c00fe.png","role":null,"alt":null},{"url":"https://d3epheqghktydj.cloudfront.net/askyourdatabase-image-7-01ffaabd5a8e.png","role":null,"alt":null}],"run_id":"db2bb5d5-0e0e-4cb3-8d76-3555c45c23cd","study_title":"Query Live Databases Using Plain English with AI","study_kind":"generation","research_task":"86b9y6c99","tested_at":null,"completeness":"input-and-output","input":{"state":"text","text":"Who are my best customers — the ones who order the most and spend the most?\n\nFollow-up 1: For the top 3 from that list — do any of them have unpaid orders?\n\nFollow-up 2: What payment methods do these top 3 usually use?","files":[],"modality":"text","stresses":["Ambiguous business-term interpretation","Multi-table joins across customers orders and payments","Aggregation and ranking","Follow-up context retention","Scoped drill-down to the top 3 customers","Readable customer-level output"]},"tool_page_slug":"askyourdatabase","tool_url":"https://aidemos.com/tools/askyourdatabase","permalink":"https://aidemos.com/evidence/820cfe6d-d216-49fe-bb1f-78694880d4d4","api_url":"https://ai.aidemos.com/v1/observations/820cfe6d-d216-49fe-bb1f-78694880d4d4"},"peers":[{"id":"38afc684-08a2-4518-b556-20b07d9912be","tool":"basedash","tool_name":"Basedash","verdict":"worked","score":null,"score_total":null,"note":"It turns the ranking tables into a plain-English business takeaway by naming Rahul Sharma as the best overall customer, Mohan Vishe as the most frequent buyer, and Deepak Kulkarni as the biggest spender.","artifact_count":1,"thumbnail":"https://d3epheqghktydj.cloudfront.net/basedash-image-2-288c8204c355.png","evidence_url":"https://aidemos.com/evidence/38afc684-08a2-4518-b556-20b07d9912be"},{"id":"6161c827-6469-4922-ac82-0511d300dc87","tool":"definite","tool_name":"Definite","verdict":"worked","score":null,"score_total":null,"note":"It added useful follow-up commentary by flagging Rahul Sharma's unpaid $2,199 order as worth chasing because he was #2 by spend, and by linking that unpaid order to his payment behavior as likely an oversight rather than a pattern.","artifact_count":2,"thumbnail":"https://d3epheqghktydj.cloudfront.net/definite-image-4-aa6da855028f.png","evidence_url":"https://aidemos.com/evidence/6161c827-6469-4922-ac82-0511d300dc87"}],"other_criteria":[{"id":"87bac5d0-cd93-46de-a5fa-5daec5d3d86d","criterion":"ambiguity-handling","criterion_name":"Ambiguity Handling","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"Handled the ambiguous phrase by not collapsing it into one ranking; it produced separate order-count and total-spend rankings instead of guessing silently.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/87bac5d0-cd93-46de-a5fa-5daec5d3d86d"},{"id":"88894e72-df01-4f3d-bf3f-a8bcefcc91b1","criterion":"chart-visualization-support","criterion_name":"Chart / Visualization Support","rank_role":null,"verdict":"failed","score":null,"score_total":null,"note":"Visualization did not auto-generate on this customer analysis flow; the report says it required an additional prompt every time.","artifact_count":0,"evidence_url":"https://aidemos.com/evidence/88894e72-df01-4f3d-bf3f-a8bcefcc91b1"},{"id":"0f379e1b-c980-49c7-9d60-df438430e631","criterion":"follow-up-context","criterion_name":"Follow-Up Context","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"Kept the top-3 customer context across the follow-up chain by hardcoding the same three customer IDs into the unpaid-order check.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/0f379e1b-c980-49c7-9d60-df438430e631"},{"id":"4a24d35a-e481-4ca2-bbed-3a5c9c86e0ea","criterion":"follow-up-context","criterion_name":"Follow-Up Context","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"The tool preserved conversational context across turns by reusing the previously identified top three customers in the unpaid-order follow-up.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/4a24d35a-e481-4ca2-bbed-3a5c9c86e0ea"},{"id":"472450fa-faa4-4aef-bb6b-72c321381ccf","criterion":"plain-english-query-handling","criterion_name":"Plain English Query Handling","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"The tool understood follow-up phrasing naturally, including 'For the top 3 from that list' and 'What payment methods do these top 3 usually use?'.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/472450fa-faa4-4aef-bb6b-72c321381ccf"},{"id":"a76bbf6a-d3bf-4614-88df-e466d93830b7","criterion":"plain-english-query-handling","criterion_name":"Plain English Query Handling","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"Accepted an informal customer-analytics question and split it into two dimensions without requiring SQL: who orders most and who spends most.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/a76bbf6a-d3bf-4614-88df-e466d93830b7"},{"id":"e62d9777-e371-46ea-939d-39f2db2b1909","criterion":"result-readability","criterion_name":"Result Readability","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"Presented the follow-up results as clearly labeled customer status blocks such as 'All Clear', '1 Unpaid', and 'All 4 Unpaid!', which makes the risk scan easy.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/e62d9777-e371-46ea-939d-39f2db2b1909"},{"id":"05dbced4-de87-4e7a-a1bf-84da4f7a6be8","criterion":"result-readability","criterion_name":"Result Readability","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"The customer ranking output was easy to scan because it separated frequent shoppers from highest spenders into clearly named tables with totals and ranks.","artifact_count":1,"evidence_url":"https://aidemos.com/evidence/05dbced4-de87-4e7a-a1bf-84da4f7a6be8"},{"id":"d379e546-f71f-42c9-9b76-510e9a9b61bc","criterion":"sql-generation","criterion_name":"SQL Generation","rank_role":null,"verdict":"worked","score":null,"score_total":null,"note":"Ran 2 SQL queries simultaneously for the main request, and then generated a filtered follow-up query for the exact top 3 customers.","artifact_count":2,"evidence_url":"https://aidemos.com/evidence/d379e546-f71f-42c9-9b76-510e9a9b61bc"}],"appears_in":[{"page_type":"use-case","slug":"query-live-databases","title":"Query Live Databases Using Plain English with AI","url":"https://aidemos.com/use-cases/query-live-databases","binding":"run"},{"page_type":"ranking","slug":"text-to-sql-tools","title":"Best AI Tools to Query Live Databases Using Plain English","url":"https://aidemos.com/best/text-to-sql-tools","binding":"study"}],"same_scenario":[{"id":"38afc684-08a2-4518-b556-20b07d9912be","tool":"basedash","tool_name":"Basedash","verdict":"worked","score":null,"score_total":null,"note":"It turns the ranking tables into a plain-English business takeaway by naming Rahul Sharma as the best overall customer, Mohan Vishe as the most frequent buyer, and Deepak Kulkarni as the biggest spender."},{"id":"6161c827-6469-4922-ac82-0511d300dc87","tool":"definite","tool_name":"Definite","verdict":"worked","score":null,"score_total":null,"note":"It added useful follow-up commentary by flagging Rahul Sharma's unpaid $2,199 order as worth chasing because he was #2 by spend, and by linking that unpaid order to his payment behavior as likely an oversight rather than a pattern."}]}