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

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

@@ -12,7 +12,7 @@ sidebarTitle: "Tasks View"
 
 ### View Title
 
-Enter a clear, descriptive name for your custom task view. This title will appear in the task view selector, making it easy to find and switch between your different task dashboards.
+Enter a clear, descriptive name for your custom Task View. This title will appear in the Task View selector, making it easy to find and switch between your different task dashboards.
 
 **Examples:**
 
@@ -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:
 

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

@@ -72,13 +72,13 @@
 
 All the technical information and metadata about each task:
 
 - **Created:** When the task started and who/what triggered it
 - **Status:** Whether it's active, paused, or complete
 - **Credits Used:** How many Relevance AI credits this task consumed
 - **Metadata:** Any custom tags you've added
 - **Schedule:** Timing details for recurring tasks
 - **Linked Tools:** What Tools your Agent accessed/uses
 - **Linked Agents:** Any other Agents (subagents) that helped with this task
 
 <Tip> Quick Tip: This section is your audit trail - helpful for troubleshooting or understanding exactly how a task was processed.</Tip>
 
@@ -92,3 +92,30 @@
 4. Check the **right sidebar** for technical details and resource usage
 
 This integrated view ensures you always know what your Agent is doing, why it made certain decisions, and how you can work together to get better results.
+
+## Filtering tasks
+
+The task filter builder in the Task List lets you narrow the list to exactly the tasks you need. Filters work directly from the run tab — you don't need to create a custom Task View to use them.
+
+### Available filters
+
+- **Status** — filter by task state (Running, Completed, Paused, Timed out, Unrecoverable error, Pending approval, and others)
+- **Agent** — filter to tasks from a specific Agent
+- **Tool usage** — filter by which tools the task used
+- **Errors** — filter by failure type, including **Has active tool failures** and **Agent has errored**
+- **Metadata (Memory)** — filter on custom metadata fields attached to tasks
+- **Date created / Last updated** — filter by time range
+- **Email tracking** — filter by email open events
+- **Created by** — filter by who or what triggered the task
+- **Advanced filters** — combine custom conditions for more specific queries
+
+### Filtering for failures
+
+The **Errors** filter has two options that surface different kinds of failure:
+
+- **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
+
+**Why both matter:** 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. The **Has active tool failures** filter surfaces those tasks so you can review them, even when overall task status appears normal.
+
+Combine both filters to see tasks with any kind of failure — both agent-level errors and tool-level failures.

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 [Filtering for failures](/build/agents/give-your-agent-tasks/task-overview#filtering-for-failures) 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