---
title: "The money logic review that happened in the wrong place"
canonical: https://dxdev.com/everyday-ai/the-tool-nobody-was-using/
datePublished: 2026-06-26
---
Twelve questions were still open on a plan, and we had built a tool so the person reviewing it wouldn't have to answer them in a ticket comment. They answered most of the important ones in a ticket comment anyway.

## A review that had to happen

We were heading into a major overhaul with real money logic riding on it. The plan had four tiers of decisions, and the riskiest tier stayed frozen until a reviewer signed off, on purpose. A wrong call there would do more than make something look different. It would change what customers were charged.

To make the review easy, we built a tool that laid the plan out by tier and walked a reviewer through the open questions in order. We also pointed straight at it in a ticket comment. The idea was simple: read it, answer the grouped questions, unlock the next tier.

## The answers turned up somewhere else

The colleague reviewing the plan answered the highest-stakes questions correctly. That included a real contradiction buried in the brief that could have gone either way. They just did it inline in the ticket, not inside the tool.

Nothing about the tool had stopped anyone. There was no error, no missing button, no confusing layout. The review was happening. It was happening in the ticket instead of in the place we had built for it.

## Two ways to be wrong about it

We could have kept pointing back at the tool. That would have kept our record tidy, but it would have made progress depend on someone changing a habit that was already working for them.

We could have rebuilt the tool until it felt easier than replying to a comment. That was tempting precisely because we had built the first version. It also would have solved a problem that wasn't there. The interface was not the obstacle. The reviewer had picked the channel with less friction, and a better interface doesn't fix a channel that was never broken.

So we copied the remaining open questions, including the named contradiction, into a fresh comment and asked for answers there. The four tiers and the gate stayed. The requirement to use our tool didn't.

## What the tool was still good for

The tool wasn't wasted effort. Forcing the plan into four tiers with an explicit gate is what let us see, quickly, that the real decisions were already being made somewhere else. Without that structure, the review would have been a looser conversation with no clear sense of what was still open.

## Where AI helped, and where it stopped

An AI agent can reliably flag the mismatch: here is where the process says the decision should happen, here is where it is actually happening, and here is what would be lost if you only looked in one place. It can also carry the unresolved structure, the tiers and the named contradiction, into whichever channel is actually in use.

Deciding to drop a mandatory gate on money-sensitive work is not a call to hand to a tool. That decision stayed with a person, and so did confirming that the contradiction was resolved correctly rather than just answered somewhere.

## What we kept

When someone works around a tool you built for them, they have told you something about the tool. Keep whatever it was protecting, the decision list, the gate, the named risk, and drop the requirement to use a specific interface if that's the only part nobody needed.