> For the complete documentation index, see [llms.txt](https://help.nightfall.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.nightfall.ai/nightfall-for-anthropic-claude/frequently-asked-questions-faqs.md).

# Frequently Asked Questions (FAQs)

**How fast does Nightfall see a new Claude message?**

Conversations and files are polled every 60 seconds; the activity feed is polled every 30 seconds.

**What happens if a user deletes content in Claude?**

When a conversation or file is deleted in Claude Enterprise, Nightfall reflects that state on subsequent sync cycles according to your retention configuration.

**Can I keep finding metadata but drop the raw Claude conversation text?**

Yes. Enable redaction-at-ingest mode on the integration. Findings, detector hits, and byte offsets are preserved; the raw content is not stored.

**Where can I see Claude admin activity?**

The **Claude Activity** view in Nightfall. Events also forward to your SIEM destination if you have one configured.

**Can I block a prompt before it reaches Claude?**

Not via the Compliance API. Use [Claude Inference Hooks](https://help.nightfall.ai/data-exfiltration-prevention/ai-agent-security/ai-governance/auditability-and-control/claude-inference-hooks) for agentless prompt blocking across Claude Enterprise (claude.ai, Cowork, Claude Desktop, mobile, Slack, and Claude Code), [AI Agent Security device hooks](https://help.nightfall.ai/data-exfiltration-prevention/ai-agent-security/ai-governance/auditability-and-control) to block prompts, tool calls, shell commands, and tool responses in Claude Code, or the [Nightfall endpoint agent](https://help.nightfall.ai/data-exfiltration-prevention/exfiltration_endpoint) for file upload and clipboard blocking on Claude Desktop and the browser tab.

**Will this cover Claude on Bedrock or Vertex AI?**

No. Those surfaces are not exposed by the Compliance API. Use the [Nightfall endpoint agent](https://help.nightfall.ai/data-exfiltration-prevention/exfiltration_endpoint) on the developer's machine, or the [AI Agent Security](https://help.nightfall.ai/data-exfiltration-prevention/ai-agent-security/ai-governance/auditability-and-control) integration if the work is happening inside Claude Code.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.nightfall.ai/nightfall-for-anthropic-claude/frequently-asked-questions-faqs.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.