New KNOWIDEA research, co-authored with Georgia Tech and developed with researchers at one of the world’s largest asset managers, makes AI-written financial calculations checkable before any action.

NEW YORK, Oct. 13, 2026 /PRNewswire/ — Two AI-written queries ask the same database the same question and return the same answer. One is incorrect, and nobody can tell. Then a single missing value appears in the data, and the query with incorrect logic quietly drops accounts from a report, with no error message and no warning.

That is the failure KNOWIDEA, the decision intelligence company, prevents. Today it published “VeriPIE: Checkable Query Plans and Evidence-Guided Selection for Text-to-SQL,” co-authored with Georgia Tech and developed with one of the world’s largest asset managers. The paper shows how to make AI-generated database queries more accurate and every answer comes with evidence a risk team can validate before it informs a decision. The paper is available at https://www.knowidea.dev/papers/veripie-text2sql.pdf.

The wrong number that looks right

Banks, asset managers and corporate finance teams are adopting AI tools that turn plain-English questions into database queries, a task known as text-to-SQL. The danger is not the query that fails. It is the query that runs, returns a reasonable number and is wrong. The paper’s example: two common ways to write “no matching payment” return identical results. Add one payment record with a missing account ID, and one version silently excludes every unmatched account while the other still returns them. The report looks complete. It isn’t.

That kind of error does not stay in a spreadsheet. A wrong query, the paper notes, “can silently omit exposures, double-count transactions, or miscalculate financial aggregates while returning plausible results.”

• In risk, an omitted exposure understates a portfolio’s risk.
• In reporting, double-counted transactions misstate a regulatory filing.
• In operations, a reconciliation that drops unmatched accounts hides the breaks it was built to find.

Most AI systems settle on the answer most of their candidate queries agree on. The paper shows why that is inadequate: queries can agree on today’s data and disagree tomorrow.

About KNOWIDEA
KNOWIDEA is a decision intelligence company. To see VeriPIE on your data, bring one decision to a 30-minute session at knowidea.dev.

Media contact
Yatharth Sejpal, info@knowidea.dev

View original content:https://www.prnewswire.com/news-releases/no-idea-if-your-ai-is-right-knowidea-lets-finance-check-every-answer-302906297.html

SOURCE KNOWIDEA