> ## Documentation Index > Fetch the complete documentation index at: https://docs.forge.ai/llms.txt > Use this file to discover all available pages before exploring further. # Real-time Monitoring > Review risky AI activity as sessions run and apply configured interventions. Real-time Monitoring evaluates AI activity while a session is running. It combines inline action review with the Watcher agent, which reviews evolving session behavior, maintains a safety state, and can apply configured interventions when risk crosses organization thresholds. ## Inline review and the Watcher agent The two controls operate at different points. | Control | Behavior | | -------------------- | ----------------------------------------------------------------------- | | Inline action review | Evaluates a supported risky action before it continues. | | Watcher agent | Reviews recent activity asynchronously for risk across multiple events. | Inline review is suited to a single action that can be evaluated immediately. The Watcher agent is suited to patterns such as escalating intent, repeated denied activity, suspicious tool sequences, scope changes, or accumulated risk across a session. ## Enable Real-time Monitoring 1. Open **Settings**. 2. Select **Observability**. 3. Find **Real-time monitoring**. 4. Select an **Inline action review** mode. 5. Select a **Session watcher** mode. 6. Choose the appropriate **Failure behavior**. Users with policy-management permission can change these settings. Configuration changes are written to the Audit Log. ## Watcher modes | Mode | Behavior | | --------------- | --------------------------------------------------------------------------------------------------------------------- | | Off | Does not assess new session activity. | | Observe | Records assessments, safety state, evidence, and qualifying risk signals without creating an intervention. | | Suggest context | Includes Observe behavior and can add safer guidance to the active session. | | Enforce | Includes Suggest context behavior and can require approval, recommend stopping, or actively stop a supported session. | Suggest context cannot require approval or stop a session. Those actions require Enforce mode. ## What the Watcher evaluates A Watcher assessment can consider: * Newly accepted session events. * Recent prompts, responses, tool activity, and policy decisions available from the source. * The current session summary and safety state. * Earlier Watcher assessments and event judgments. * Active security signals. * Risk category, severity, confidence, and evidence continuity. The Watcher records the events covered by each assessment so reviewers can trace its conclusion back to the relevant session activity. ## Available interventions | Intervention | Effect | Default eligibility | | --------------------- | ------------------------------------------------------------------- | ---------------------------------------------------------------- | | Add guidance | Adds safer context for the remainder of the supported session. | Watch risk, salience 5 or higher, confidence 0.65 or higher | | Require approval next | Requires approval before the next supported risky action proceeds. | Intervene risk, salience 8 or higher, confidence 0.80 or higher | | Recommend stop | Escalates the session with a recommendation for operator review. | Incident risk, salience 9 or higher, confidence 0.85 or higher | | Actively stop | Prevents the session from continuing at its next enforcement point. | Incident risk, salience 9.5 or higher, confidence 0.90 or higher | Active stopping must also be explicitly enabled and is disabled by default. Organizations can adjust Watcher thresholds through the real-time governance configuration API. Added guidance expires after 30 minutes. Requiring approval for the next risky action expires after 2 hours unless it is resolved earlier. ## What stopping means The Watcher can stop a session only when its activity passes through a supported Forge enforcement point. A stop intervention: * Blocks the governed session at its next supported blocking event. * Applies to the identified session rather than every session belonging to the user. * Prevents future governed activity while the intervention remains active. It does not terminate an arbitrary operating-system process, undo an action that already completed, or stop activity that does not pass through a supported enforcement point. Because the Watcher runs asynchronously, activity may occur before an assessment finishes. Use inline action review when a decision must be made before an individual action proceeds. ## Failure behavior **Fail open** allows a supported inline action to continue when the real-time reviewer cannot return a decision in time. **Fail closed** prevents the action from continuing when the reviewer cannot establish a decision. Watcher assessments are asynchronous. If an assessment fails, Forge does not invent an assessment or create a new intervention. Existing active interventions remain enforceable until they expire or are resolved. ## Review Watcher activity Open a session to review: * Current safety state. * Risk level and confidence. * Watcher rationale. * Covered evidence. * Recommended action. * Active intervention. * Inline review decisions. Qualifying assessments can also create security signals and related findings for investigation. Intervention activation and resolution are recorded as governance and audit evidence. Configuration changes are recorded in the organization Audit Log. ## Related pages Review Watcher assessments and controls for an individual session. Review approvals, stop recommendations, and operator decisions. Define deterministic controls for supported enforcement points. Inspect configuration and intervention history.