---
title: "Comment by JustOneCX on \"What Is AX Design? A Practical Guide to Designing for the Age of AI Agents\" | Hashnode"
description: "Agents retry blindly, so clear error codes and idempotent endpoints matter more than friendly error messages. Are you designing for agents calling your API dire"
url: "https://hashnode.com/posts/what-is-ax-design-a-practical-guide-to-designing-for-the-age-of-ai-agents-vigzg/6b01541a53d0630f641fbd02/comment/6b01dcfd2145406a67c0beb4"
---

[Discussion](https://hashnode.com/posts/what-is-ax-design-a-practical-guide-to-designing-for-the-age-of-ai-agents-vigzg/6b01541a53d0630f641fbd02)

Comment [What Is AX Design? A Practical Guide to Designing for the Age of AI Agents](https://hashnode.com/posts/what-is-ax-design-a-practical-guide-to-designing-for-the-age-of-ai-agents-vigzg/6b01541a53d0630f641fbd02)

[JustOneCX](https://hashnode.com/@justonecx)

[3h ago](https://hashnode.com/posts/what-is-ax-design-a-practical-guide-to-designing-for-the-age-of-ai-agents-vigzg/6b01541a53d0630f641fbd02/comment/6b01dcfd2145406a67c0beb4)

Agents retry blindly, so clear error codes and idempotent endpoints matter more than friendly error messages. Are you designing for agents calling your API directly, or for ones driven by a person?

[ZyVOP](https://hashnode.com/@zyvop)

[2h ago](https://hashnode.com/posts/what-is-ax-design-a-practical-guide-to-designing-for-the-age-of-ai-agents-vigzg/6b01541a53d0630f641fbd02/comment/6b01dcfd2145406a67c0beb4#reply-6b01e163963c758b32cdf046)

Agreed, and the post has a gap here. It shows a specific 400 error an agent can correct (the date example), but it never mentions idempotency. A precise message only helps when the request can be fixed. On timeouts and 5xx there is nothing to fix, so agents just retry, and a mutating call like "book option 2" can double-book. Idempotency keys on write endpoints, stable machine-readable error codes, and Retry-After on 429/503 are what make blind retries safe.

To your question: both, at different layers. The API contract is for the agent as the direct caller (codes, schemas, idempotency). The human layer sits on top of it: visibility into what the agent did, approvals, and undo. I'd say the first is what keeps the second trustworthy.
