# Choosing an HTTP Status for AI Agent Authorization Through Transparent Proxies

DevFeed: [Choosing an HTTP Status for AI Agent Authorization Through Transparent Proxies](<https://devfeed.tech/articles/how-to-tell-an-ai-agent-that-its-user-needs-to-authorize-15978.md>)

Original publisher: [Read original article](<https://workos.com/blog/402-not-401-ai-agents>)

Author: WorkOS

Published: 2026-08-11T00:00:00Z

Content type: tutorial

Language: en

Sources: [WorkOS Blog](<https://devfeed.tech/sources/workos-blog.md>)

Topics: [API](<https://devfeed.tech/topics/api.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [HTTP](<https://devfeed.tech/topics/http.md>), [Authentication](<https://devfeed.tech/topics/authentication.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [api](<https://devfeed.tech/tags/api.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [http](<https://devfeed.tech/tags/http.md>), [rest](<https://devfeed.tech/tags/rest.md>)

## AI overview

This article explains how a transparent proxy for AI agents should respond when a user has not connected a third-party API. It examines why 401 and 403 conflict with existing authentication and provider-response meanings, and discusses the proposed response shape and the x402 standard.

## Source excerpt

Your agent calls a third-party API for a user who never connected it. What to send back, why 401 and 403 are both already taken, and what the x402 standard means for the answer.