diff --git a/src/_data/catalog/destination_categories.yml b/src/_data/catalog/destination_categories.yml index c24d435e31..29314632ea 100644 --- a/src/_data/catalog/destination_categories.yml +++ b/src/_data/catalog/destination_categories.yml @@ -1,5 +1,5 @@ # AUTOGENERATED FROM PUBLIC API. DO NOT EDIT -# destination categories last updated 2024-11-21 +# destination categories last updated 2024-11-26 items: - display_name: A/B Testing slug: a-b-testing diff --git a/src/_data/catalog/destinations.yml b/src/_data/catalog/destinations.yml index d88850e1f6..82eeaa97e7 100644 --- a/src/_data/catalog/destinations.yml +++ b/src/_data/catalog/destinations.yml @@ -1,5 +1,5 @@ # AUTOGENERATED FROM PUBLIC API. DO NOT EDIT -# destination data last updated 2024-11-21 +# destination data last updated 2024-11-26 items: - id: 637e8d185e2dec264895ea89 display_name: 1Flow diff --git a/src/_data/catalog/destinations_private.yml b/src/_data/catalog/destinations_private.yml index 10009b010d..3aea21e3c8 100644 --- a/src/_data/catalog/destinations_private.yml +++ b/src/_data/catalog/destinations_private.yml @@ -1,5 +1,5 @@ # AUTOGENERATED FROM PUBLIC API. DO NOT EDIT -# destination data last updated 2024-11-21 +# destination data last updated 2024-11-26 items: - id: 54521fd925e721e32a72eee1 display_name: Pardot diff --git a/src/_data/catalog/source_categories.yml b/src/_data/catalog/source_categories.yml index 871db37254..4bd3e0e92a 100644 --- a/src/_data/catalog/source_categories.yml +++ b/src/_data/catalog/source_categories.yml @@ -1,5 +1,5 @@ # AUTOGENERATED FROM PUBLIC API. DO NOT EDIT -# source categories last updated 2024-11-21 +# source categories last updated 2024-11-26 items: - display_name: A/B Testing slug: a-b-testing diff --git a/src/_data/catalog/sources.yml b/src/_data/catalog/sources.yml index 1420c089c2..0c171fa22f 100644 --- a/src/_data/catalog/sources.yml +++ b/src/_data/catalog/sources.yml @@ -1,5 +1,5 @@ # AUTOGENERATED FROM PUBLIC API. DO NOT EDIT -# sources last updated 2024-11-21 +# sources last updated 2024-11-26 items: - id: 8HWbgPTt3k display_name: .NET diff --git a/src/connections/destinations/catalog/actions-klaviyo/index.md b/src/connections/destinations/catalog/actions-klaviyo/index.md index 26ee601a08..e848f5b49a 100644 --- a/src/connections/destinations/catalog/actions-klaviyo/index.md +++ b/src/connections/destinations/catalog/actions-klaviyo/index.md @@ -108,4 +108,10 @@ No. Engage audiences are designed to initiate the creation of new lists in Klavi When adding a user to a list, our action make use of the [Bulk Profile Import](https://developers.klaviyo.com/en/reference/spawn_bulk_profile_import_job){:target="_blank”} endpoint (when batching is enabled), and the [Add Profile To List](https://developers.klaviyo.com/en/reference/create_list_relationships){:target="_blank”} endpoint for non-batched requests. Both of which will not update a users suppression status if they were previously suppressed. -To ensure a suppressed profile gets unsuppressed, you can use the "Subscribe Profile" action. When a profile is subscribed in Klaviyo, it automatically unsuppresses any previously suppressed user. You can combine this action with other actions to achieve your goal. If this solution does not fully address your use case, please contact us at friends@segment.com so we can consider your specific requirements. +To unsuppress a previously suppressed profile in Klaviyo, use the **Subscribe Profile** action. This action automatically removes the suppression status for the user when they are subscribed. You can also pair this action with other mappings to suit your workflow. + +If this approach doesn't address your use case, [reach out to Segment](mailto:friends@segment.com) to discuss your specific requirements. + +### Can batching be enabled for the entire Klaviyo (Actions) destination? + +Batching is only available for events sent through the Upsert Profile action mapping. Other actions in the Klaviyo (Actions) destination don't support batching. \ No newline at end of file diff --git a/src/connections/destinations/catalog/hubspot/index.md b/src/connections/destinations/catalog/hubspot/index.md index 58d4a9f434..69d8579b80 100644 --- a/src/connections/destinations/catalog/hubspot/index.md +++ b/src/connections/destinations/catalog/hubspot/index.md @@ -196,6 +196,14 @@ HubSpot Plan: API Add-On (Any Tier) * Maximum Number of API Calls per 10 Seconds, per Key or Token: **120** * Maximum Number of API Calls per Day, per Key or Token: **1,000,000** +### Maximum data size returned from HubSpot + +When Segment pulls contact or company fields from HubSpot, there is a 1MB limit on the size of the data Segment allows to return from HubSpot’s platform. If this limit is exceeded, the request and response process stops, and the event you tried to send to HubSpot won't be delivered. + +To avoid this issue: +- **Maintain clean and concise datasets**: Regularly review and remove unused or redundant fields. +- **Minimize returned traits**: Verify that only the fields essential for to your workflow are included in the data retrieved from HubSpot. +By keeping your datasets streamlined, you improve data hygiene and reduce the risk of exceeding Segment's data size limit for processing. ### Sending Dates as Property Values diff --git a/src/connections/destinations/catalog/impact-partnership-cloud/index.md b/src/connections/destinations/catalog/impact-partnership-cloud/index.md index c1fdfa31a2..71238ebb41 100644 --- a/src/connections/destinations/catalog/impact-partnership-cloud/index.md +++ b/src/connections/destinations/catalog/impact-partnership-cloud/index.md @@ -17,6 +17,9 @@ This destination is maintained by Impact. For any issues with the destination, c 4. Go to the [Impact Partnership Cloud Settings](https://app.impact.com){:target="_blank"}, find and copy the "Account SID", "Auth Token", and "Campaign ID". 5. Back in the Impact Partnership Cloud destination settings in Segment, enter the "Account SID", "Auth Token", and "Campaign ID". +> warning "Workspace owner required for OAuth setup" +> Only a Segment workspace owner can enable OAuth between Impact and Segment. If you run into during setup, check your workspace settings to verify you have the required permissions. + ## Page If you aren't familiar with the Segment Spec, take a look at the [Page method documentation](/docs/connections/spec/page/) to learn about what it does. An example call would look like: diff --git a/src/connections/destinations/catalog/iterable/index.md b/src/connections/destinations/catalog/iterable/index.md index 184370258f..b299e51950 100644 --- a/src/connections/destinations/catalog/iterable/index.md +++ b/src/connections/destinations/catalog/iterable/index.md @@ -128,6 +128,12 @@ Iterable supports sending push notification events to Segment. These events are They support the following events: `Push Delivered`, `Push Bounced`, `Mobile App Uninstalled`, `Push Opened` +## High retry rate + +If you're experiencing a large amount of retries within your destinations that are connected to your HTTP API source, this could be due to Etimedout errors. Etimedout errors are intermittent problems that can come about when HTTP requests are made from server to server. + +The Etimedout error is the result of an HTTP response not being received in a specific timeframe. [Learn more](/docs/connections/destinations/#retries-between-segment-and-destinations) about how Segment retries events to destinations. + ## Using Iterable with Engage diff --git a/src/connections/functions/source-functions.md b/src/connections/functions/source-functions.md index 646db8e948..d9513df49d 100644 --- a/src/connections/functions/source-functions.md +++ b/src/connections/functions/source-functions.md @@ -438,3 +438,9 @@ The test function interface has a 4KB console logging limit. Outputs surpassing #### Can I send a custom response from my Source Function to an external tool? No, Source Functions can't send custom responses to the tool that triggered the Function's webhook. Source Functions can only send a success or failure response, not a custom one. + +#### Why am I seeing the error "Functions are unable to send data or events back to their originating source" when trying to save my Source Function? + +This error occurs because Segment prevents Source Functions from sending data back to their own webhook endpoint (`https://fn.segmentapis.com`). Allowing this could create an infinite loop where the function continuously triggers itself. + +To resolve this error, check your Function code and ensure the URL `https://fn.segmentapis.com` is not included. This URL is used to send data to a Source Function and shouldn't appear in your outgoing requests. Once you remove this URL from your code, you’ll be able to save the Function successfully. diff --git a/src/connections/sources/catalog/libraries/website/javascript/custom-proxy.md b/src/connections/sources/catalog/libraries/website/javascript/custom-proxy.md index fffc618375..7bd144d8a2 100644 --- a/src/connections/sources/catalog/libraries/website/javascript/custom-proxy.md +++ b/src/connections/sources/catalog/libraries/website/javascript/custom-proxy.md @@ -161,13 +161,12 @@ To add a CNAME record for the Segment proxy to your organizations DNS settings: ### Tracking API Proxy -Set up a proxy for the tracking API so that all calls proxy through your domain. To do this, set up a CloudFront distribution that's similar to the one in the previous section, with the exception of the Origin Domain Name: +As events travel through the proxy before reaching the tracking API, set up a proxy for the tracking API so that all calls proxy through your domain. To do this, set up a CloudFront distribution that's similar to the one in the previous section, with the exception of the Origin Domain Name: | Field | Value | Description | | ------------------ | ---------------- | -------------------------------------------- | | Origin Domain Name | `api.segment.io` | The domain name to which the proxy is served | - #### Add CNAME Record to DNS To add a CNAME record to your DNS settings: diff --git a/src/engage/content/email/template.md b/src/engage/content/email/template.md index 02ffdb5b38..fbe4e116d3 100644 --- a/src/engage/content/email/template.md +++ b/src/engage/content/email/template.md @@ -142,4 +142,9 @@ Segment doesn't support profile traits in object and array datatypes in [Broadca - View some [email deliverability tips and tricks](https://docs.sendgrid.com/ui/sending-email/deliverability){:target="blank"} from SendGrid. - You can also use the Templates screen in Engage to [build SMS templates](/docs/engage/content/sms/template/). - + +## FAQs + +### Do updates to an email template automatically apply to Journey steps using it? + +When you add a template to a Journey step, it becomes a copy specific to that step. Changes made to the original template won’t update the Journey version, and edits made in the Journey step won’t affect the original template. This keeps your Journey changes separate while preserving the original for reuse. diff --git a/src/engage/journeys/event-triggered-journeys.md b/src/engage/journeys/event-triggered-journeys.md index 59716f8d2c..24de8a47e2 100644 --- a/src/engage/journeys/event-triggered-journeys.md +++ b/src/engage/journeys/event-triggered-journeys.md @@ -11,7 +11,7 @@ Unlike traditional audience-based journeys that rely on pre-defined user segment On this page, you'll learn how to create an event-triggered journey, configure entry conditions, and work with published event-triggered journeys. > info "Private Beta" -> Event-Triggered Journeys is in private beta, and Segment is actively working on this feature. Some functionality may change before it becomes generally available. +> Event-Triggered Journeys is in private beta, and Segment is actively working on this feature. Some functionality may change before it becomes generally available. During private beta, Event-Triggered Journeys is not HIPAA eligible. ## Overview diff --git a/src/privacy/faq.md b/src/privacy/faq.md index 760492fb7a..01eeab0b9a 100644 --- a/src/privacy/faq.md +++ b/src/privacy/faq.md @@ -2,49 +2,45 @@ title: Privacy Frequently Asked Questions --- -## Privacy Portal Questions +## Privacy Portal questions -### Why aren't fields from my Cloud Object Sources (such as Salesforce and Zendesk) showing up in the Privacy Portal Inbox and Inventory? +### Why aren't fields from my Cloud Object Sources (like Salesforce and Zendesk) showing up in the Privacy Portal Inbox and Inventory? -We do not currently support Cloud Object Sources in the Privacy Portal, but it's on our roadmap. Stay tuned for new features in the future. +The Privacy Portal doesn't doesn't support fields from Cloud Object Sources like Salesforce or Zendesk. -### Why is Segment suggesting my fields should be classified as Yellow or Red? +### Why does Segment suggest classifying my fields as Yellow or Red? -You can see a full list of the fields we exact-match and fuzzy-match against [by default](/docs/privacy/portal/#default-pii-matchers). These classifications are our best-guess suggestions, and you can easily change them by following the instructions to [change a recommended classification](/docs/privacy/portal/#change-a-recommended-classification). +Segment provides suggested classifications based on [default PII matchers](/docs/privacy/portal/#default-pii-matchers). These suggestions include exact and fuzzy matches for potential PII. You can update these classifications by following the instructions to [change a recommended classification](/docs/privacy/portal/#change-a-recommended-classification). ### Who can access the Privacy Portal? Only Workspace Owners can access the portal. -### Which Segment plan types get access to the Privacy Portal? +### Which Segment plan types include access to the Privacy Portal? -All Segment plans have access to the Privacy Portal, because we believe data -privacy should be a right, not an add-on. +All Segment plans include access to the Privacy Portal. Data privacy is a fundamental Segment feature, not an add-on. -### If I block data at the Source level, can I reverse it or get that data back using Segment's Data Replay feature? +### If I block data at the source level, can I reverse it or recover the data using Segment's Data Replay feature? -If you use Privacy Controls to block data at the Source level, the data never -enters Segment, and we cannot Replay that data for you. We recommend caution -when blocking data at the Source level. +When you block data at the source level using Privacy Controls, the data never enters Segment. As a result, Segment can't replay the data. Segment recommends exercising caution when blocking data at the source level. -### The Privacy Portal classified my property as `Yellow`, but it's required for some of my destinations to function. What should I do? +### The Privacy Portal classified my property as Yellow, but my destinations require it to function. What should I do? -Segment classifications are simply recommendations. If an integration you rely -on requires a field that we recommend be classified as Yellow, you can override -the recommended setting to send that field downstream. +Segment classifications are recommendations. If a destination requires a field classified as Yellow, you can override the recommended classification to ensure the field gets sent downstream. -## User Deletion and Suppression Questions +## User deletion and suppression questions -### How can I find my user's userId? +### How can I find a specific `userId`? -The easiest way to find a customer's `userId` is by querying an existing tool. Specifically, you can use your Segment [data warehouse](https://segment.com/warehouses) to query the `users` table for another known item of information about the user (their email address, for example) and then use that row to find their userId. +To locate a specific `userId`, query your Segment [data warehouse](https://segment.com/warehouses){:target="_blank”} for the `users` table. Use other known details about the user, like their email address, to identify the correct row and retrieve the `userId`. ### How many deletion requests can I send? -You can send us batches of up to 5,000 `userIds`, or 4 MB, per payload. We process these batches asynchronously. [Contact Segment](https://segment.com/help/contact/){:target="_blank”} if you need to process more than 110,000 users within a 30 day period. -### Which Destinations can I send deletion requests to? +You can send batches of up to 5,000 `userIds`, or 4 MB, per payload. Segment processes these batches asynchronously. [Contact Segment](https://segment.com/help/contact/){:target="_blank”} if you need to process more than 110,000 users within a 30-day period. -In addition to your Raw Data destinations (Amazon S3 and Data Warehouses), we can forward requests to the following streaming destinations: +### Which destinations can I send deletion requests to? + +In addition to your Raw Data destinations (Amazon S3 and data warehouses), Segment can forward requests to the following streaming destinations: - Amplitude - Iterable @@ -60,25 +56,26 @@ In addition to your Raw Data destinations (Amazon S3 and Data Warehouses), we ca - Google Cloud PubSub - Friendbuy (Cloud Destination) -Segment cannot guarantee that data is deleted from your Destinations. When you issue a user deletion request, Segment forwards the request to supported streaming Destinations. You must still contact these Destinations to confirm that they've executed the request. +Segment forwards deletion requests but cannot guarantee that data is deleted from downstream destinations. You must contact these destinations to confirm that they executed the request. -### Which destinations require additional destination setting configuration? +### Which destinations require additional configuration to process deletion requests? #### Amplitude -If you have the Amplitude destination enabled in one or more sources, you must include Amplitude's secret key in each destination(s) settings so they can accept the deletion request. (You add it in the Amplitude destination settings, under "Secret Key"). You can find your Secret Key on the [General Settings](https://help.amplitude.com/hc/en-us/articles/235649848-Settings) of your Amplitude project. +To process deletion requests in Amplitude, add your Amplitude secret key to the destination settings under "Secret Key." You can find this key in your Amplitude project's [General Settings](https://help.amplitude.com/hc/en-us/articles/235649848-Settings){:target="_blank”}. + #### Google Analytics -To send user deletion requests to Google Analytics you must authenticate your Google Analytics account with Segment using OAuth. If you have the Google Analytics destination enabled in one or more sources, you must authenticate your account in each destination(s) settings. Navigate to the **User Deletion** settings in your Segment Google Analytics settings and use your email and password to authenticate your account. +To send deletion requests to Google Analytics, authenticate your account with Segment using OAuth. Go to the **User Deletion** settings in your Segment Google Analytics destination and use your email and password to complete authentication. + ### What regulation types does Segment support? Segment supports the following regulation types: -- **SUPPRESS_ONLY**: Suppress new data based on the `userId` without deleting existing data stored in your workspace and in downstream destinations. -- **UNSUPPRESS**: Stop the ongoing suppression of a `userId`. -- **SUPPRESS_WITH_DELETE**: Suppress new data based on the `userId` and also delete all existing data for that ID from your workspace and our internal archives. While Segment forwards the deletion request to your downstream destinations, Segment cannot guarantee deletion in your third-party tools. -- **DELETE_INTERNAL**: Deletes user data from within Segment archives only and not from any connected destinations. +- **SUPPRESS_ONLY**: Suppresses new data for a `userId` without deleting existing data in your workspace or downstream destinations. +- **UNSUPPRESS**: Stops ongoing suppression of a `userId`. +- **SUPPRESS_WITH_DELETE**: Suppresses new data for a `userId` and deletes all existing data for that ID in your workspace and Segment's internal archives. Segment forwards the deletion request to downstream destinations but can't guarantee deletion in third-party tools. +- **DELETE_INTERNAL**: Deletes user data only from Segment archives, without affecting downstream destinations. - **DELETE_ONLY**: Deletes user data from Segment and your connected warehouses. Also sends a deletion request to your downstream destinations. - > info "" -> Using **SUPPRESS_WITH_DELETE** or **DELETE_ONLY** regulation types might lead to additional charges levied by your destination providers. +> Using **SUPPRESS_WITH_DELETE** or **DELETE_ONLY** regulation types might lead to additional charges levied by your destination providers. \ No newline at end of file diff --git a/src/unify/Traits/predictions/using-predictions.md b/src/unify/Traits/predictions/using-predictions.md index 1614e31c76..35e9f2f1d3 100644 --- a/src/unify/Traits/predictions/using-predictions.md +++ b/src/unify/Traits/predictions/using-predictions.md @@ -7,24 +7,44 @@ redirect_from: ## Working with Predictions in Segment -Segment creates Predictions as Computed Traits, with scores saved to user profiles as a percentage cohort. For example, `0.8` on a user's profile indicates that the user is in the the cohort's 80th percentile, or the top 20%. +Predictions are stored as [computed traits](/docs/unify/Traits/computed-traits/) in user profiles, with scores represented as percentage cohorts. For example, a score of `0.8` indicates the user is in the 80th percentile, or the top 20% of the cohort. -Once you've selected a cohort, you can use Predictions in concert with other Segment features: +After selecting a cohort, use Predictions with the following Segment features: -- [Audiences](/docs/engage/audiences/), which you can create with predictions as a base. As part of Engage, Segment also offers prebuilt [Suggested Predictive Audiences](/docs/unify/traits/predictions/suggested-predictive-audiences/). +- [Audiences](/docs/engage/audiences/), build new audiences using Predictions as a base. Segment also provides prebuilt [Suggested Predictive Audiences](/docs/unify/traits/predictions/suggested-predictive-audiences/) as part of Engage.. - [Journeys](/docs/engage/journeys/); use Predictions in Journeys to trigger [Engage marketing campaigns](/docs/engage/campaigns/) when users enter a high-percentage cohort, or send promotional material if a customer shows interest and has a high propensity to buy. - [Destinations](/docs/connections/destinations/); send your Predictions downstream to [Warehouses](/docs/connections/storage/warehouses/), support systems, and ad platforms. ### Prediction tab -Once Segment has generated your prediction, you can access it in your Trait's **Prediction** tab. The Prediction tab gives you actionable insight into your prediction. +You can access generated Predictions in the **Prediction** tab of your Trait. The Prediction tab gives you actionable insight into your prediction. ![The Explore your prediction section of the Computed Trait Prediction tab](../../images/explore_prediction.png) The **Explore your prediction** section of the Prediction tab visualizes prediction data and lets you create Audiences to target. An interactive chart displays a percentile cohort score that indicates the likelihood of users in each group to convert on your chosen goal. You can choose the top 20%, bottom 80%, or create custom ranges for specific use cases. You can then create an Audience from the group you've selected, letting you send efficient, targeted marketing campaigns within Journeys. You can also send your prediction data to downstream destinations. - + +### Model monitoring + +Predictions rank your customers by their likelihood to perform a specific conversion event, from most to least likely. + +For each custom prediction, Segment monitors the percentile cohort where customers were ranked when they performed the predicted conversion event. After around 7 days, Segment creates a graph data visualization, allowing you to evaluate the prediction’s accuracy based on real workspace data. + +![Bar chart showing conversion history across percentile cohorts. The top 10% cohort has the highest number of conversions, followed by the 81-90% cohort, with decreasing conversions as cohorts move lower in the percentile range.](../../images/model_monitoring.png) + +For example, suppose you're predicting the likelihood of customers completing an `order_completed` event. The graph shows that: + +- Customers in the 91–100% cohort performed the event about 6,700 times. +- Customers in the 81–90% cohort performed the event about 3,900 times. +- Customers in the 71–80% cohort performed the event about 3,000 times. + +This pattern shows that the prediction was extremely accurate in identifying customers most likely to convert. Ideally, most graphs will show a similar trend, where the highest-ranked cohorts have the most conversion activity. + +However, this pattern can change depending on how you use Predictions. For example, if you run a marketing campaign targeting the bottom 10% cohort, you might see an increase in conversions for that group instead. + +Like any AI or machine learning tool, Predictions may not always be perfect. Start small, test your predictions, and refine your approach as needed. Model monitoring makes it easier to measure and improve the accuracy of your predictions. + #### Model statistics The Predictions tab's **Understand your prediction** section provides insights into the performance of the underlying predictive model. This information helps you understand the data points that contribute to the prediction results. @@ -33,7 +53,7 @@ The Predictions tab's **Understand your prediction** section provides insights i The Understand your prediction dashboard displays the following model metrics: -- **AUC**, or Area under [the ROC curve](https://en.wikipedia.org/wiki/Receiver_operating_characteristic){:target="_blank"}; AUC lands between 0 and 1, where 1 is a perfect future prediction, and 0 represents the opposite. Higher AUC indicates better predictions. +- **AUC**, or Area under [the ROC curve](https://en.wikipedia.org/wiki/Receiver_operating_characteristic){:target="_blank"}; AUC values range from 0 to 1, with 1 indicating a perfect prediction and 0 indicating the opposite. Higher AUC indicates better predictions. - **Lift Quality**, which measures the effectiveness of a predictive model. Segment calculates lift quality as the ratio between the results obtained with and without the predictive model. Higher lift quality indicates better predictions. - **Log Loss**; the more a predicted probability diverges from the actual value, the higher the log-loss value will be. Lower log loss indicates better predictions. - **Top contributing events**; this graph visually describes the events factored into the model, as well as the associated weights used to create the prediction. @@ -72,7 +92,7 @@ Predictions may not be as beneficial in the following situations: ## FAQs -#### What type of machine learning model do you use? +#### What type of machine learning model does Segment use? Segment uses a binary classification model that uses decision trees. @@ -92,7 +112,7 @@ These data science statistics measure the effectiveness of Segment's predictions The Prediction Quality Score factors AUC, log loss, and lift quality to determine whether Segment recommends using the prediction. A model can have a score of Poor, Fair, Good, or Excellent. -#### How do you store trait values? +#### How does Segment store trait values? The created trait value represents the user's percentile cohort. This value will refresh when we re score the customers based on your refresh cadence. If you see `0.85` on a user's profile, this means the user is in the 85th percentile, or the top 15% for the prediction. diff --git a/src/unify/debugger.md b/src/unify/debugger.md index 62d2047919..aa03eada66 100644 --- a/src/unify/debugger.md +++ b/src/unify/debugger.md @@ -5,7 +5,7 @@ redirect_from: - "/personas/debugger" --- -The Profile Source Debugger enables you to inspect and monitor events that Segment sends downstream +The Profile Source Debugger enables you to inspect and monitor events that Segment sends downstream. Because Segment generates a unique source for every destination connected to a Space, the Debugger gives you insight into how Segment sends events before they reach their destination. Even when a destination is removed, you can't delete and shouldn't disable this source for Segment to function as designed. The source will be reused by Segment as needed. diff --git a/src/unify/images/model_monitoring.png b/src/unify/images/model_monitoring.png new file mode 100644 index 0000000000..bd41d5f9e5 Binary files /dev/null and b/src/unify/images/model_monitoring.png differ