The invoice said £244.80. Why did the AI tool show £0?
Who chose zero? I did. Four rules for a failed AI request, replayed on 81 tasks: what each one lets through, and what it costs.
Topic
Agents and workflows that admit what they didn’t check
Pipelines, defaults, fallbacks and tracing: keeping the model as one step, and showing what was and wasn’t checked.
Version 1 let an AI agent decide. Version 2 lets written rules decide.
A better model removes the model's excuses. What's left is the design: if a check has no way to say it didn't run, it will be reported as clean.
Before you quote a UK company, know what wasn’t checked
An underwriter needs a route and its reasons before quoting a company, plus an honest list of what wasn’t checked. A tool that hides its gaps is worse than none.
Try the UK Company Pre-Screen yourself
Two saved cases teach the difference between a check that couldn’t run and a finding on the record. Then screen your own company, or make it fail on purpose.
My AI agent called a fined bank “medium risk”. No model made that call.
A schema checks the shape of an answer, not whether it is true. How a default value hid two failures in my agent, and the rules I follow now.
Nothing found isn't the same as nothing checked
A check that never ran reported every director as clean. The fix wasn't a better model; it was making "couldn't check" an answer of its own.