Foundations
Foundations
Revenue Is Number 28, and Someone Has to Tell the SQL Agent
Ask an AI agent a question about your company's data, and it writes a database query, runs it, and returns a number. New research tested how often that number is right. Running was rarely the problem: every system tested wrote queries that ran at least 99% of the time. Yet apart from the researchers' own system, none answered even half the questions correctly. The wrong answers look as exact as the right ones, and nothing warns you which is which. This close read asks what a query that runs actually tells you.
Revenue Is Number 28, and Someone Has to Tell the SQL Agent
Ask an AI agent a question about your company's data, and it writes a database query, runs it, and returns a number. New research tested how often that number is right. Running was rarely the problem: every system tested wrote queries that ran at least 99% of the time. Yet apart from the researchers' own system, none answered even half the questions correctly. The wrong answers look as exact as the right ones, and nothing warns you which is which. This close read asks what a query that runs actually tells you.
Test a Page's Agent Tools the Way You Test Its Buttons
Web pages are starting to hand AI agents tools instead of buttons. Rather than clicking, the agent calls a tool, sends it some inputs, and gets something back. That raises a question clicking never did: who checks what goes in and what comes out?
This hands-on walkthrough works through it with Playwright, testing a demo tool, add_numbers. First it's called with { a: 3, b: 7 }. Then it's sent { a: "3", b: 7 } instead, where the 3 is text rather than a number, and the walkthrough watches what happens.
Test a Page's Agent Tools the Way You Test Its Buttons
Web pages are starting to hand AI agents tools instead of buttons. Rather than clicking, the agent calls a tool, sends it some inputs, and gets something back. That raises a question clicking never did: who checks what goes in and what comes out?
This hands-on walkthrough works through it with Playwright, testing a demo tool, add_numbers. First it's called with { a: 3, b: 7 }. Then it's sent { a: "3", b: 7 } instead, where the 3 is text rather than a number, and the walkthrough watches what happens.
Documented Cases
