> For the complete documentation index, see [llms.txt](https://help.solink.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.solink.com/docs/understand-your-business/ai-features/agents/agents-performance-insights-and-settings-agent-dashboard.md). # Agents: Performance Insights and Settings (Agent Dashboard) You can track Solink agent performance, get a detailed view of its history, and adjust its configuration. From the main **Agents** page in the Solink platform, select one of your agents near the bottom of the page or the "My Agents" page to see: * How the agent is performing ([Performance](#performance-tab) tab) * Individual agent run logs ([Logs](#logs-tab) tab) * Confirm the agent configuration is set up correctly ([Settings](#settings-tab) tab) This article explains each tab available when you open an agent's detail view. *** ## Performance Tab The Performance tab provides a high-level view of how your agent is performing over time. Use it to understand detection trends, identify which locations generate the most activity, and drill into specific findings. ### Summary Cards At the top of the page, four summary cards show key metrics for the selected date range: * **Locations Active**: The number of locations actively monitored by the agent. * **Cameras Active**: The number of cameras actively monitored by the agent. * **Total Detections**: The total number of detections flagged by the agent. * **Avg Detections / Day**: The average number of detections per day over the selected period. **Note**: The labels and metrics shown may vary depending on the type of agent. For example, a Loss Prevention agent shows transaction-focused metrics, and an Overnight Guard agent shows incident-focused metrics. ### Performance Charts Below the summary cards, two charts visualize detection data: * **Total Detections Over Time**: An area chart showing detection volume across the selected date range. Use this to spot trends or spikes in activity. * **Events Flagged by Location**: A horizontal bar chart showing which locations generated the most detections. Use this to identify sites that may need attention. ### Filtering Results Use the filter bar to narrow data to a specific time period or subset of your locations: * **Date range**: Select the date picker to choose a preset period, such as Today, Yesterday, Past week, Month to date, Past 4 weeks, or enter a custom date range. * **Add filter**: Select Add filter to filter by Location, Skill, or Outcome. Applied filters appear as chips in the filter bar. * To remove a filter, select X on the chip. To clear all filters, select **Clear**. ### Viewing Individual Findings Select any bar or data point within a chart on the **Performance** tab to open a **Findings** panel on the right side of the screen. This panel lists individual detections associated with that chart segment and includes: * Filters for Location, Severity, Confidence, Human review, and Skill * A toggle between Table and Card view * A column picker, in Table view, to show or hide fields such as Time started, Camera, Agent reasoning, and more * An **Export CSV** button to download the filtered findings Select a finding to open the associated video clip alongside the detection details: *** ## Logs Tab The Logs tab shows a record of every time the agent ran, including what it analyzed, how long it took, what it detected, and what action it took, if any. **Note**: Agent run logs are retained for 14 days. ### Log Table Each row in the log table represents one agent run and includes the following columns: * **Location**: The site where the agent ran. * **Time Started**: The date and time the run began, displayed in the site's local time zone. * **Duration**: How long the run took. * **Camera**: The camera or cameras analyzed during the run. * **Status**: The outcome of the run: * **Queued**: Agent is ready to run when scheduled. * **Running**: Agent is currently running. * **Detected**: Agent detected activity. * **Not Detected**: Agent did not detect activity. * **Success:** Agent ran succesfully. * **Failed**: Agent did not run successfully due to an issue with the footage. * **Suspended**: Agent was delayed and will attempt to run successfully again. * **Actions Taken**: The action or actions triggered during the run, such as Email, SMS, or Event. Displays No Action if nothing was triggered. ### Showing All Logs By default, the Logs tab shows only runs where the agent triggered an action. Toggle **Show all logs** to display every run, including those where the agent ran but did not detect anything. ### Toolbar Actions * **Refresh**: Select the refresh icon (2 arrows) to reload the log list and see the latest runs. * Trigger Now * **View all Events**: Opens the Events page to show all events generated by this agent. *** ## Settings Tab The Settings tab displays a read-only summary of how the agent is configured. Use it to confirm the agent's scope, schedule, monitored areas, and actions without entering edit mode. The following sections may appear depending on the agent type: * **Agent name / Description**: The agent's name, description, and scope, such as Cloud or Reseller. * **Skills / Prompt**: The types of activity the agent is configured to detect and any associated conditions or prompts. * **Analysis**: How the agent captures footage, such as a video clip or image. * **Schedule**: When and how often the agent runs, such as Every day or On event. * **Monitored Areas**: The locations and cameras included in the agent's scope. * **Confidence Threshold**: The detection sensitivity level selected for this agent. * **Event Structure**: The conditions under which the agent creates a new event and the output fields included. * **Actions**: The actions configured to run when the agent detects activity, such as sending an email or SMS. ### Editing an Agent To make changes to an agent's configuration, select the **Edit** pencil icon at the top of the **Settings** tab. This opens the agent editor. **Note**: The **Edit** option is only available if you have permission to manage agents. Contact your Solink Customer Success representative if the Edit option is not visible. --- # 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.solink.com/docs/understand-your-business/ai-features/agents/agents-performance-insights-and-settings-agent-dashboard.md?ask=&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.