--- title: "Connect Amazon SageMaker and PostHog - APIANT.ai" description: "When \"New Training Job\" fires in Amazon SageMaker, your agent runs \"Capture Event\" in PostHog." canonical: "https://apiant.ai/connect/amazon-sagemaker-to-posthog" --- # Connect Amazon SageMaker and PostHog When **New Training Job** fires in [Amazon SageMaker](https://apiant.ai/connections/amazon-sagemaker), your agent runs **Capture Event** in [PostHog](https://apiant.ai/connections/posthog), or **Action Performed** in PostHog to **Invoke Endpoint** in Amazon SageMaker. Describe the whole flow and it is built, tested on every scenario and kept running. Amazon SageMaker **1** trigger Amazon SageMaker **1** action PostHog **1** trigger PostHog **9** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want Amazon SageMaker and PostHog to do together? Give your AI client this address. `https://mcp.apiant.ai` One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser. ### Set it up in your client ### Claude Code Run this in the directory you want to work in. `claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai` Start Claude Code there, approve the server, and sign in in the browser page it opens. [Claude Code guide (opens in a new tab)](https://apiant.ai/docs/mcp/claude-code) ### Claude, web and desktop Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Cursor Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Zed Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Codex and the ChatGPT desktop app Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) ### Any other MCP client Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection. [Setup guide (opens in a new tab)](https://apiant.ai/docs/mcp) Example flows ## What Amazon SageMaker and PostHog can do together ### From Amazon SageMaker to PostHog - When **New Training Job** in Amazon SageMaker then **Capture Event** in PostHog - When **New Training Job** in Amazon SageMaker then **Add annotation** in PostHog ### From PostHog to Amazon SageMaker - When **Action Performed** in PostHog then **Invoke Endpoint** in Amazon SageMaker Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships. Everything your agent can do with Amazon SageMaker and PostHog ## Triggers and actions 2 triggers · 10 actions - Trigger **New Training Job** Triggers when a new SageMaker training job is created. - Action **Invoke Endpoint** Sends input to a deployed Amazon SageMaker model endpoint and returns its prediction. - Trigger **Action Performed** Triggers when an action is performed by a user. - Action **Add annotation** Create a new annotation on the project timeline (content, date_marker, scope). - Action **Capture Event** Captures an event. - Action **Evaluate feature flags** Evaluate all feature flag values for a given distinct_id/person, returning flag states for use in automation branching. - Action **Get person** Retrieve a single person by ID. - Action **List annotations** List annotations in the project. - Action **List cohorts** List cohorts defined in the project. - Action **List feature flags** List feature flags defined in the project. - Action **List insights** List saved insights (charts/graphs) in the project. - Action **List persons** List/search persons in the project, optionally filtered by distinct_id or properties. ## Each app on its own - [ **Amazon SageMaker** Amazon SageMaker is a cloud platform for building, training, and deploying machine learning models at scale](https://apiant.ai/connections/amazon-sagemaker) - [ **PostHog** PostHog is the single platform for building successful products.](https://apiant.ai/connections/posthog) Reviews ## What our customers say ## More from Amazon SageMaker - [ **Amazon SageMaker to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/amazon-sagemaker-to-hubspot) - [ **Amazon SageMaker to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/amazon-sagemaker-to-salesforce) - [ **Amazon SageMaker to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/amazon-sagemaker-to-slack) - [ **Amazon SageMaker to Google Sheets** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/amazon-sagemaker-to-google-sheets) - [ **Amazon SageMaker to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/amazon-sagemaker-to-gmail) - [ **Amazon SageMaker to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/amazon-sagemaker-to-google-calendar) ## More into PostHog - [ **Google Sheets to PostHog** Google Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.](https://apiant.ai/connect/google-sheets-to-posthog) - [ **HubSpot to PostHog** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-posthog) - [ **Salesforce to PostHog** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-posthog) - [ **Google Calendar to PostHog** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/google-calendar-to-posthog) - [ **Google Drive to PostHog** Google Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...](https://apiant.ai/connect/google-drive-to-posthog) - [ **Mailchimp to PostHog** Mailchimp marketing automation and email platform.](https://apiant.ai/connect/mailchimp-to-posthog) Questions ## Amazon SageMaker and PostHog, answered ### ### What can start an automation from Amazon SageMaker? Any of Amazon SageMaker's 1 trigger in the catalog, including New Training Job. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in PostHog when something happens in Amazon SageMaker? Any of PostHog's 9 actions, including Add annotation, Capture Event, Evaluate feature flags and Get person. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from PostHog to Amazon SageMaker? Yes. When something happens in PostHog, your agent can act in Amazon SageMaker too. This page covers both directions: PostHog's triggers and Amazon SageMaker's actions are listed here as well. ### ### Do I have to build a connector for Amazon SageMaker or PostHog? No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running. ### ### Can my AI client use Amazon SageMaker and PostHog without building an automation? Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both. ### ### What happens when something fails? Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships. ### ### Is there a free plan? Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.