docs(TSP-1233): document Has active tool failures filter

build/agents/build-your-agent/agent-settings/task-view.mdx

@@ -34,7 +34,7 @@ Use this search box to select specific tools or information sources you want to
 
 **Why this matters:** By focusing on specific tools, you can create specialized dashboards that show only the task activity relevant to particular workflows or responsibilities.
 
-### When to Use Custom Task Views
+### When to use custom task views
 
 Task Views are particularly valuable when:
 
@@ -43,4 +43,35 @@ Task Views are particularly valuable when:
 - You want to reduce clutter and focus only on certain types of Agent activity
 - Different team members need to track different aspects of your Agent's work
 
-By creating targeted views, you can efficiently monitor exactly what matters most to you without being overwhelmed by unrelated task activity.
+By creating targeted views, you can efficiently monitor exactly what matters most to you without being overwhelmed by unrelated task activity.
+
+## Filtering tasks by error and status
+
+The task filter builder lets you narrow the task list to exactly the tasks you need. Two filters are especially useful for diagnosing problems:
+
+- **Agent has errored** — shows tasks where the agent itself encountered an error and stopped
+- **Has active tool failures** — shows tasks where one or more tools failed during execution, even if the agent continued running
+
+### How the "Has active tool failures" filter works
+
+1. Open the task filter builder from the task list sidebar
+2. Select **Has active tool failures** from the filter options
+3. The task list updates to show only tasks that have at least one tool failure recorded against them
+
+**Why this matters:** Tool failures don't always cause the agent to stop. An agent may retry, skip a step, or continue with degraded output while a tool failure goes unnoticed. This filter surfaces those tasks so you can review them, even when overall task status appears normal.
+
+### Using both filters together
+
+You can combine **Has active tool failures** and **Agent has errored** in the same filter to see tasks with any kind of failure — both agent-level errors and tool-level failures. This gives you a complete picture of everything that went wrong across your agent's recent runs.
+
+**Common use cases:**
+
+- Debugging: pinpoint which tasks had tool issues after a configuration change
+- Monitoring agent reliability: check periodically for tool failures that didn't surface as errors
+- Identifying problematic tools: if the same tool keeps appearing in filtered results, it likely needs attention
+
+### The Errors tab
+
+The **Errors tab** in the task list is a pre-built view focused entirely on failed and errored tasks. When you open it, the **Has active tool failures** filter is automatically enabled and locked — you'll see explanatory text in the filter bar explaining why. This prevents accidental removal of the filter and ensures the Errors tab always reflects its intended purpose.
+
+Use the Errors tab as your go-to starting point when an agent run produces unexpected results and you need to quickly identify which tasks had tool failures.

build/agents/give-your-agent-tasks/task-queue.mdx

@@ -18,7 +18,7 @@
 4. Click on the **Agent queue** button
 
 <div style={{ width:"100%",position:"relative","padding-top":"56.75%" }}>
 <iframe src="https://app.supademo.com/embed/cmkalnjqr1d1fke4xceyoom3d" frameBorder="0" title="How to access the agent queue" allow="clipboard-write; fullscreen" webkitAllowFullscreen="true" mozAllowFullscreen="true" allowFullscreen style={{ position:"absolute",top:0,left:0,width:"100%",height:"100%",border:"3px solid #5E43CE",borderRadius:"10px" }} />
 </div>
 
 The agent queue button will open a view showing all your task queues organized by their source (triggers and bulk schedules).
@@ -27,7 +27,7 @@
 
 When you open agent queue, you'll see different sections for each operation that creates tasks (per trigger or per bulk schedule). Within each section, tasks are organized by their current status. You can view tasks in the following categories:
 
 - **In Progress**: Tasks that are currently being processed by your agent
 - **Upcoming Queue**: Tasks that are scheduled but haven't started yet
 - **Failed**: Tasks that encountered errors during execution
 - **Processed**: Tasks that have completed successfully
@@ -71,7 +71,16 @@
 
 These insights help you understand your agent's workload and make informed decisions about scaling or adjusting your task schedules.
 
-## Best Practices
+## Filtering tasks by failure type
+
+When reviewing failed tasks, you can use the task filter builder to narrow down exactly which tasks had problems:
+
+- **Has active tool failures** — filters to tasks where one or more tools failed during execution, even if the agent kept running
+- **Agent has errored** — filters to tasks where the agent itself stopped due to an error
+
+These filters help you separate tool-level failures from agent-level failures, which often point to different root causes. For a full explanation of how to configure and combine these filters, see [Task View Settings](/build/agents/build-your-agent/agent-settings/task-view#filtering-tasks-by-error-and-status).
+
+## Best practices
 
 - **Monitor regularly**: Check your task queue regularly to ensure tasks are processing as expected
 - **Review failed tasks**: Pay attention to failed tasks to identify patterns or issues that need addressing

get-started/troubleshooting/troubleshooting-agents-not-working.mdx

@@ -37,6 +37,10 @@
 
 When agents fail, it's often because one of their tools is not working properly. Here's how to troubleshoot tool issues:
 
+<Tip>
+Use the **Has active tool failures** filter in the task list to quickly identify which tasks had tool failures — including cases where the agent continued running despite a tool error. See [Task View Settings](/build/agents/build-your-agent/agent-settings/task-view#filtering-tasks-by-error-and-status) for details.
+</Tip>
+
 #### Step 1: Test the tool independently
 
 1. Go to the [Tools page](https://app.relevanceai.com/tools)
@@ -132,7 +136,7 @@
 
 ### Key prompt engineering principles
 
 - **Be explicit**: Don't assume the agent will understand implicit requirements
 - **Use clear language**: Avoid ambiguous terms and provide specific criteria
 - **Provide context**: Give the agent relevant background information
 - **Set expectations**: Clearly define what success looks like