An agent can suggest a lesson. Should it become a rule?

Description and use

<p>If you are running an agentic workflow for coding, I am pretty sure you already know that - sometimes an AI coding agent can get stuck for a stupid, boring reason.</p> <p>For example, in a recent run of my own workflow, an agent failed because it was missing Jam credentials. I use Jam to report bugs and provide a link and the MCP to the triage agent to help it understand the bug, but this run failed even though there was no Jam link to investigate. If anyone with a common sense would have worked on this issue (i.e. a human) they wouldn't worry about it, but the agent does unless you tell it

Problem

<p>If you are running an agentic workflow for coding, I am pretty sure you already know that - sometimes an AI coding agent can get stuck for a stupid, boring reason.</p> <p>For example, in a recent run of my own workflow, an agent failed because it was missing Jam credentials. I use Jam to report bugs and provide a link and the MCP to the triage agent to help it understand the bug, but this run failed even though there was no Jam link to investigate. If anyone with a common sense would have worked on this issue (i.e. a human) they wouldn't worry about it, but the agent does unless you tell it

Outcome

<p>If you are running an agentic workflow for coding, I am pretty sure you already know that - sometimes an AI coding agent can get stuck for a stupid, boring reason.</p> <p>For example, in a recent run of my own workflow, an agent failed because it was missing Jam credentials. I use Jam to report bugs and provide a link and the MCP to the triage agent to help it understand the bug, but this run failed even though there was no Jam link to investigate. If anyone with a common sense would have worked on this issue (i.e. a human) they wouldn't worry about it, but the agent does unless you tell it

Evidence

An agent can suggest a lesson. Should it become a rule?

Source