Update docs: Invent proactively offers alarm auto-diagnosis

build/agents/build-your-agent/evals.mdx

@@ -1,14 +1,14 @@
 ---
 title: 'Evals'
 sidebarTitle: 'Evals'
 description: 'Test and evaluate your AI Agents with scenario-based evaluations and reusable Checks'
 ---
 
 <Info>
 **Rollout Status**: Evals is rolling out progressively, starting with Enterprise customers. If you don't see this feature in your account yet, reach out to your account manager to discuss access.
 </Info>
 
 The Evals section is your command center for testing and evaluating AI Agent performance. Located in the **Evaluate** tab (next to the Build and Use tabs) in the Agent builder, Evals lets you create test sets, define reusable Checks, run automated evaluations, and monitor live Agent quality — all without manual testing. Evals apply to both individual Agents and Workforces, including the sub-agents and tools inside a Workforce.
 
 <div
   className="video-embed"
@@ -64,7 +64,7 @@
 
 The Evals area has five sections, shown in the left sidebar of the Evaluate tab:
 
 - **Test** — Create and manage test sets. Each test set holds scenarios that simulate users; running a scenario produces a conversation with your Agent that gets scored by attached Checks.
 - **Runs** — Past evaluation run results. Browse average scores, tasks evaluated, progress status, cost (Credits and Actions), and creation date for every run.
 - **Checks** — The reusable set of evaluation criteria. Create a Check once, then attach it to scenarios, to Monitor dashboards, or to one-off evaluations of completed tasks.
 - **Publish** — Choose which test sets must pass before your Agent can be published. Set a minimum pass rate and optionally block publishing on failure.
@@ -322,7 +322,7 @@
 
 You also get:
 
 - **Overall score timeseries** to spot regressions or improvements over time.
 - **Per-Check charts** so you can see which criteria are slipping.
 - **Version markers** that line up score changes with Agent publishes.
 - **A list of evaluation runs** with score, name, and a drill-in to the full conversation.
@@ -331,6 +331,10 @@
 To adjust dashboard settings after initial setup, click the **Settings** button in the top right corner of the dashboard.
 </Tip>
 
+<Note>
+  From any Monitor dashboard you can configure alarms that fire when a score crosses a threshold. Enable **Auto-diagnosis by Invent** on an alarm to have Invent investigate the first breach automatically and deliver findings to your configured alert channel. See [Configure an alarm](/build/invent/invent#turn-on-auto-diagnosis) in the Invent documentation for details.
+</Note>
+
 ---
 
 ## Publish
@@ -350,7 +354,7 @@
 | Setting | Description |
 |---------|-------------|
 | **Minimum pass rate (%)** | The minimum score percentage required for the evaluation to pass (e.g., 100%) |
 | **Allow publishing even if eval fails** | When unchecked (the default), the Agent will only be published if the evaluation score meets or exceeds the minimum pass rate. When checked, the Agent publishes regardless of whether the evaluation passes. |
 
 Once configured, click **Save**. When you next publish your Agent, the selected test sets will run automatically and the results will be checked against your minimum pass rate.
 
@@ -441,6 +445,6 @@
   </Accordion>
 
   <Accordion title="I don't see the Evals section. How do I get access?">
     Evals is rolling out progressively, starting with Enterprise customers. If you don't see the Evaluate tab in the Agent builder, reach out to your account manager to discuss access.
   </Accordion>
 </AccordionGroup>

build/invent/invent.mdx

@@ -27,7 +27,7 @@
     Invent defines the checks each Agent must pass before launch and samples live runs after deployment. When quality drops, it diagnoses the problem and proposes changes to prompts, Tools, examples, models, or orchestration. It can test those changes against the same requirements before you approve them.
   </Card>
   <Card title="Review performance and find opportunities" icon="chart-line">
     Invent reviews Agent activity, errors, Evals, and performance dashboards to diagnose problems and recommend improvements. Describe a recurring process, and it can help identify where Agents, Tools, or Workforces could automate it.
   </Card>
 </CardGroup>
 
@@ -89,7 +89,7 @@
 
 <AccordionGroup>
   <Accordion title="Project isolation">
     Invent's access to Relevance AI is scoped to the active project at the API-key and fine-grained authorization layers, not only in the interface. Each internal platform request uses the active project ID and the caller's API key, then passes through the standard authorization checks. Enabling Invent in a sandbox project does not grant it access to assets in a production project.
   </Accordion>
 
   <Accordion title="Integration reach">
@@ -206,7 +206,7 @@
   <Accordion title="Alerts" icon="envelope">
     <img src="/images/invent-alerts.png" alt="The email and Slack alert settings in Invent" />
 
-    Add at least one email address or Slack channel so Invent can notify you when a scheduled check-in finds something.
+    Add at least one email address or Slack channel so Invent can notify you when a scheduled check-in finds something or when an alarm fires with [Auto-diagnosis by Invent](/build/invent/invent#turn-on-auto-diagnosis) enabled.
 
     <Steps>
       <Step title="Open Invent settings">
@@ -289,15 +289,17 @@
   <Tab title="Configure an alarm">
     <img src="/images/invent-alarms.png" alt="The alarm configuration in Invent" />
 
-    #### Turn on auto-diagnosis
-
-    Turn on **Auto-diagnosis by Invent** to investigate the first breach and send a diagnosis and proposed fix to the alarm creator's [Invent alert channels](/build/invent/invent#alerts). Invent still shares its findings if the cause is unclear and never applies changes without your approval.
+    Alarms evaluate the scores collected by a Performance dashboard and notify you when an overall score or individual Check crosses the condition you set.
 
     <Note>
       Alarms are configured in an Agent or Workforce's **Evaluate → Monitor** area, not in Invent settings.
     </Note>
 
-    Alarms evaluate the scores collected by a Performance dashboard and notify you when an overall score or individual Check crosses the condition you set.
+    #### Turn on auto-diagnosis
+
+    When you configure an alarm, Invent proactively offers **Auto-diagnosis by Invent** and explains what it does. Turn it on to have Invent investigate the first breach and deliver a diagnosis and proposed fix to the alarm creator's configured [Invent alert channel](/build/invent/invent#alerts) (email or Slack).
+
+    If no alert channel is configured yet, Invent shows a **SETUP REQUIRED** warning and guides you to set one up before enabling auto-diagnosis — this prevents silently enabling a feature that can't deliver its findings. Invent still shares its findings if the cause is unclear and never applies changes without your approval.
   </Tab>
 </Tabs>