Follow Discord
Sweep 06 Nov 2026 · 01:32Z Build v2.1.319 537 read Stable v2.1.311 Latest v2.1.319 Next v2.1.319 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 11 Sep 2026
One change · api

inference-hooks changedmanage-claude/inference-hooks

Nearest release: v2.1.269, published 3 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+2added
Lines−2removed
From line 23 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits24to this page, all time

The whole hunk

from line 23, old and new numbered
/
lines
from line 23
23233. Your AI security server evaluates the content and responds with a verdict within the verdict timeout your organization configures (5 seconds by default).
24244. On `allow`, inference proceeds normally. On `deny`, the request is rejected and the user sees a blocked-by-policy message assembled from two parts: the per-request reason your AI security server supplied in the verdict's `deny_reason` field, followed by a standing message your administrators configure (for example, who to contact or where to request an exception). If your administrators haven't configured one, a built-in default directs the user to contact them. Each denial is also recorded in your organization's [Activity Feed](https://platform.claude.com/docs/en/manage-claude/compliance-activity-feed).
2525 
26The following diagram traces one example (a Cowork request where Claude also calls an O365 tool) to illustrate which parts of the flow are hooked. The hooked points are the diagram's steps 1 and 5, where the prompt arrives and the tool result returns; each results in the validation exchange with your AI security server shown in steps 2 and 6.
26The following diagram traces one example (a Cowork request where Claude also calls an O365 tool) to illustrate which parts of the flow are hooked. The hooked points are the diagram's steps 1 and 6, where the prompt arrives and the tool result returns; each results in the validation exchange with your AI security server shown in steps 2–3 and 7–8.
2727 
28![Flow diagram: the AI security server validates both the prompt and the tool result before inference proceeds](https://platform.claude.com/docs/images/inference-hooks-flow.svg)
28![Flow diagram: the AI security server validates both the prompt and the tool result before inference proceeds](https://platform.claude.com/docs/images/inference-hooks-flow.png)
2929 
3030A verdict is a small JSON object: `{"action": "allow"}` lets the request proceed, and a deny carries the user-facing reason. For the full verdict schema, see [Return a verdict](https://platform.claude.com/docs/en/manage-claude/inference-hooks-endpoint#return-a-verdict).
3131 
Feedback