# AI Activity

> See every prompt, model request and tool call your AI agents make, what each one sent, and what Guard stopped, all stored on your Mac with secrets masked.

Source: https://docs.subcloak.com/cloak-watch/ai-activity/

AI Activity shows what your AI tools and agents do: the prompts you send, the model requests they make, and the tool calls they run (shell commands, file reads and writes, MCP calls, web fetches), with what each one sent. [Guard](https://docs.subcloak.com/cloak-watch/ai-activity/guard/) can stop secrets and risky tool calls before they happen. Everything is recorded on your Mac; nothing goes to Subcloak.

AI Activity is optional. It starts empty: [connect a tool](https://docs.subcloak.com/cloak-watch/ai-activity/connections/) to fill it.

## The four tabs

| Tab | What it's for |
|---|---|
| **Activity** | Sessions and their events, newest first, with the content of each event and what Guard did. This page. |
| **Guard** | Rules that redact secrets and block, ask or warn on tool calls. See [Guard rules](https://docs.subcloak.com/cloak-watch/ai-activity/guard/). |
| **Usage** | Tokens and estimated cost per day, project, session, model or agent. See [Usage](https://docs.subcloak.com/cloak-watch/ai-activity/usage/). |
| **Connections** | Each AI tool, how Watch sees it, and setup and undo. See [Connect your AI tools](https://docs.subcloak.com/cloak-watch/ai-activity/connections/). |

The status bar at the bottom shows each way Watch can see your tools, **Hooks**, **Gateway**, **Telemetry** and **Network**, with a dot and which tools it's on for. Click one to open Connections. At the right, the lock shows how long content is kept, for example **Content kept 7 days on this Mac**; click it for the [content settings](#what-watch-keeps).

## How Watch sees your tools

| Way | What it gives | Can it stop things? |
|---|---|---|
| **Hooks** | Prompts and every tool call with its input and output, as the agent runs them | Yes: block or ask before a tool call, block a prompt |
| **Gateway** | Every model request and response, and exact token usage | Yes: redact or block secrets in requests |
| **Telemetry** | Usage and tool metrics the agent reports | No |
| **Network** | Which app talks to which AI provider, how much and when, never the content | No |

Hooks, the gateway and telemetry are set up per tool on the Connections tab. The network extension covers every app at once. See [Network extension](https://docs.subcloak.com/cloak-watch/ai-activity/network-extension/).

## Read the Activity tab

*[Screenshot: The Activity tab: sessions for ShopApp and shop-api on the left; the ShopApp session's events on the right, including a blocked prompt, a model request with 2 secrets redacted, an rm -rf command that was asked about, and a blocked read of ~/.ssh/id_ed25519 selected, with its detail showing Blocked before it ran, the rule Block reading ~/.ssh, and Allow Once and Always Allow buttons]*

- **Sessions** are grouped under **Today**, **Yesterday**, the weekday or the date. Each shows the agent, the project or first prompt, and **Now** while it's active.
- The session header shows its time, model, new tokens and estimated cost.
- **Events** are listed in order, with **Time**, **Event** (Prompt, Model request, Bash, Read, Write, MCP call, WebFetch and so on), **Command, path or prompt**, **Tokens · time**, and a **Guard** label: **Blocked**, **Redacted N**, **Asked**, **Warned**, or **Allowed** after you allowed it.
- Filter with **All agents**, **All projects**, **Blocked or redacted**, and **Search prompts, commands, files**, which searches the stored content.

### The event detail

Select an event to see what was sent.

| Part | What it shows |
|---|---|
| Header | The event, when, and what saw it (hook, gateway, telemetry or network) |
| Stats | For a model request: **Model** with the kind of login (Subscription login, API key or Gateway token), **New** and output tokens, **Cached**, **Cost** (an estimate; on a subscription, what the tokens would cost at API prices). For a tool call: **Tool**, **Duration**, **Result** (Succeeded, Failed or Not run). For a prompt: its length, **Secrets** found, and **Guard**. |
| Guard banner | What Guard did, for example **2 secrets redacted before sending** or **Blocked before it ran**, the reason, each secret's type, masked value and where it was, what the agent was told, and the rule, with buttons to allow it (see [Guard rules](https://docs.subcloak.com/cloak-watch/ai-activity/guard/#allow-something-guard-stopped)). |
| Findings | Prompt injection in a tool result ([MCP-5](https://docs.subcloak.com/cloak-watch/detections/#mcp-5)) or hidden text in an instructions file ([AGT-6](https://docs.subcloak.com/cloak-watch/detections/#agt-6)). |
| Content | For a model request, **Sent** (only what's new in this request; earlier context folds away) and **Reply**. For a tool call, its input (**Command**, **File**, **URL** or **Input**) and **Output**. Secrets are highlighted and masked. Copy buttons copy the content with secrets still masked; file tools have **Reveal in Finder**. |

*[Screenshot: A model request's detail: 2 secrets redacted before sending, listing an AWS access key and a .env value with their masked forms and where they were, the rule Secrets never leave this Mac, an Allow These Secrets menu, and the tool result with both secrets highlighted. The model received [REDACTED: type] in place of each highlighted secret.]*

When there's no content, the detail says why: content isn't kept, telemetry reports usage but not content, the event was seen on the network only, or the content is older than your retention.

## What Watch keeps

Click the lock at the right of the status bar for the content settings.

*[Screenshot: The content settings popover: Keep what agents send and receive switched on, Keep content for 7 days, a Projects section with a switch per project, and Delete All Activity]*

| Setting | Default | What it does |
|---|---|---|
| **Keep what agents send and receive** | On | Keeps the content hooks and the gateway deliver: prompts, model requests, replies, tool input and output. Nothing is captured until you connect a tool. Turn it off to keep metadata only (tool names, timings and hosts); stored content is deleted at once. |
| **Keep content for N days** | 7 days | 1 to 30 days. Older content is deleted; the timeline keeps the event without it. |
| **Projects** | All on | Turn a project off and its content is never kept (and what's stored is deleted); its events and Guard decisions still are. |
| **Delete All Activity…** | | Deletes every event, all content and usage from this Mac, including older days. Guard rules and exceptions stay. |

- Secrets are masked before anything is stored.
- Every connect sheet says what Watch will keep, with a **Keep prompts and content** switch, so you can choose metadata only before you connect.
- The timeline itself (events, decisions and usage, without content) is kept for 30 days. Change both periods in [Settings › Advanced](https://docs.subcloak.com/cloak-watch/settings/#advanced) (**Keep AI Activity**, **Keep AI content**).
- Everything lives in `~/Library/Application Support/Cloak Watch/AI/activity.sqlite`, readable only by you.

> **Content is sensitive:**
> Stored content includes your prompts, the files agents read and the commands they run. It stays on this Mac, but anyone with access to your user account can read it. Turn off content for projects you don't want recorded, or turn it off altogether.

While content is kept, Claude Code's telemetry connection also asks Claude Code to include prompt text in what it reports to Watch (`OTEL_LOG_USER_PROMPTS=1`), along with tool details (`OTEL_LOG_TOOL_DETAILS=1`). With metadata only, Claude Code isn't asked for prompt text. Those reports go to Watch on `127.0.0.1` only.

## AI today

Home and the [menu bar](https://docs.subcloak.com/cloak-watch/menu-bar/) show a one-line summary of today's AI traffic, for example **Claude Code → Anthropic 4.1 MB, 15 tool calls, 3 MCP servers**. Click it to open AI Activity.

## Related

  - [Connect your AI tools](https://docs.subcloak.com/cloak-watch/ai-activity/connections/): Hooks, the gateway and telemetry for Claude Code, Cursor and Codex.
  - [Guard rules](https://docs.subcloak.com/cloak-watch/ai-activity/guard/): Redact secrets, block risky tool calls.
  - [Network extension](https://docs.subcloak.com/cloak-watch/ai-activity/network-extension/): Which apps talk to AI providers.