BlazeSQL in AI Database Agents

BlazeSQL did not report analytics that matched what happened. Its query review page listed only one of five questions and left out both deliberately unanswerable ones, with no answered-versus-unanswered breakdown.

BlazeSQL failed to surface unanswered questions as failures. In the recording, Query review showed one ordinary row marked 'Not verified' and no failures or unanswered view appeared anywhere in the sections shown. The social-media complaints question appeared in Chat with a normal answer, and the other unanswerable question is not shown in the admin view.

BlazeSQL answered the plain fact in prose, so the evidence does not show the result being confined to a chart or a one-cell table. In the captured run, the reply said there were 100 orders ever, and the same frame also showed a one-row result table and no chart.

BlazeSQL failed to give the overall figure together with the breakdown. It first asked which dimension to use, then showed category-level query, results, highlights, and CSV export, but none stated the month total.

BlazeSQL passed this scenario: it showed the same revenue answer in a different form. In the recorded conversation, the first result appeared as a table with seven categories, then the follow-up request switched that same result to a bar chart. The bar lengths matched the table values within the chart's scale.

BlazeSQL replaced the earlier July answer with the corrected June answer. In the visible exchange, the first turn returned 21 orders for July 2026, and the follow-up turn rebuilt the query for June 2026 and returned 20 orders, matching the corrected period only.

BlazeSQL offered what to ask next after answering the revenue question. It ended the August 2026 revenue reply with “Would you like a breakdown by category, or any other analysis?”, so the capture shows one specific follow-up rather than only a generic closing.

BlazeSQL asked which comparison the customer meant instead of silently choosing one. Turn 1 showed two distinct candidate sets, and turn 2 returned only a clarification question with no table, chart, or figures. It also produced a merged comparison view in turn 1.

BlazeSQL failed to shift from the first-turn Texas filter to the broader all-states answer. In the second turn it dropped the filter but returned a state-by-state breakdown instead of the overall 12% rate; the export totals 100 orders and 12 cancellations, so the missing figure was available.

BlazeSQL preserved the earlier 90-day window when the user narrowed the request to Texas. The follow-up query kept the original date filter and added only the Texas filter, and the Texas export matched the Texas subset of the first export.

BlazeSQL fails when the needed table is excluded. It never said it could not answer; instead it returned 4 from support tickets and then widened the search to pending confirmations, action log, and orders, while still never querying the excluded table.

BlazeSQL kept the two scopes apart. The full-access account returned plus for the membership question, while the restricted account refused to look the customer up and showed no SQL or result table.

BlazeSQL said it could not answer from the available data when asked how many 5-star reviews were received this month. It listed ten available tables, gave no number, and pointed to adding review data or using a related source instead. The key finding is that it declined rather than inventing a count.

BlazeSQL did not answer revenue as a bare number; it stated the definition it applied and showed the breakdown it used. In the captured Sep 2, 2026 run, it reported order revenue, subscription revenue, refunds, and an adjusted net revenue total, with the order line explicitly marked as excluding cancelled orders.

BlazeSQL kept the saved report current after new rows were added. The fixed-date save rose from 52 to 55, and the relative 30-day save rose from 162 to 164.

BlazeSQL passed this one-report task. The combined table kept the earlier revenue, category, and cancellation answers intact, with the same values and bases, and brought all five metrics into one report.

BlazeSQL saves an answer and its query, then reopens the saved item with the same three rows under the saved name. The saved item appears in a separate Saved area, and the reopened table matches the earlier chat answer.

BlazeSQL used the user’s documentation to answer from the cryptic table and column. It reported 6 returns currently awaiting manual fraud review, split across 5 approved and 1 received. The stored note was applied to returns.flg_x2, and the follow-up answer came from that documented column.

BlazeSQL kept the standing rule across future questions. After the rule was set once, the later revenue answer returned 51,848.02 and the later order-count answer returned 32, and both generated queries still filtered out cancelled orders.

BlazeSQL generalized the supplied question-query pair in this case. It first asked what counted as successful, then after the example query was added it returned 42 for both the repeated question and a reworded one; the same-session reference value was 42.