Replayable AI Tool Calls Need Run Receipts

Description and use

<h2> The missing artifact after a tool call </h2> <p>An AI workflow can say that it called a tool successfully, while leaving you with almost nothing useful when the next step breaks. A green log line is not the same thing as evidence. When a scheduled job runs at 3 AM, I want to know what the model asked for, which tool version answered, and what the workflow actually used.</p> <p>My practical fix is a small <strong>run receipt</strong>: one structured record written after every tool call. It makes automation less mysterious and gives the next person a short path from failure to replay. This

Problem

<h2> The missing artifact after a tool call </h2> <p>An AI workflow can say that it called a tool successfully, while leaving you with almost nothing useful when the next step breaks. A green log line is not the same thing as evidence. When a scheduled job runs at 3 AM, I want to know what the model asked for, which tool version answered, and what the workflow actually used.</p> <p>My practical fix is a small <strong>run receipt</strong>: one structured record written after every tool call. It makes automation less mysterious and gives the next person a short path from failure to replay. This

Outcome

<h2> The missing artifact after a tool call </h2> <p>An AI workflow can say that it called a tool successfully, while leaving you with almost nothing useful when the next step breaks. A green log line is not the same thing as evidence. When a scheduled job runs at 3 AM, I want to know what the model asked for, which tool version answered, and what the workflow actually used.</p> <p>My practical fix is a small <strong>run receipt</strong>: one structured record written after every tool call. It makes automation less mysterious and gives the next person a short path from failure to replay. This

Evidence

Replayable AI Tool Calls Need Run Receipts

Source