Claude✓ ReviewedAnnounced 5 August 2026Reviewed 10 October 2026Claude Enterprise can now ask your security team before it answers.
Reviewed editorial Update
Claude Enterprise can now ask your security team before it answers.
Inference hooks route every Claude Enterprise prompt, context and tool response through a customer security server for an allow-or-deny verdict before the model sees it, one policy across chat, Claude Code and Cowork.
What changed
Anthropic launched inference hooks in beta for Claude Enterprise. Requests travel over a signed WebSocket to a data-loss-prevention server the customer controls, which returns allow or deny before inference begins. It covers chat, Claude Code, Cowork and tool calls through MCP connectors, skills and plugins, integrates with Netskope, Palo Alto Networks, Proofpoint and Zscaler or a custom server, and supports shadow mode, role exclusions and percentage rollouts.
Why it matters
Until now, stopping sensitive data reaching an AI model relied on training and hope. A checkpoint before inference turns policy into enforcement, but it also means somebody has to write the policy, and a badly tuned one silently blocks legitimate work or waves through what it should not.
Bit’s takeaway
The human take
A person writes the policy, owns the false positives and decides what the checkpoint should catch. The hook only enforces that judgement.
Turn this into a workflow
Bring your task to Bit.
Bit reevaluates the recorded facts when you ask. Historical recommendations do not approve a current action.
Ask Bit about my taskSource-backed facts
- Anthropic launched inference hooks in beta for Claude Enterprise, routing prompts, context and tool responses through a customer-controlled security server for an allow-or-deny verdict before inference, across chat, Claude Code and Cowork.Reviewed
Technical record
[claude-inference-hooks-fact; official_fact; product_fact; reviewed 2026-10-10; sources: Anthropic blog — Claude Enterprise inference hooks (https://claude.com/blog/claude-enterprise-inference-hooks)] Anthropic launched inference hooks in beta for Claude Enterprise, routing prompts, context and tool responses through a customer-controlled security server for an allow-or-deny verdict before inference, across chat, Claude Code and Cowork.
Sources and method