--- title: "Connect Amazon SageMaker and Geekbot - APIANT.ai" description: "When \"New Training Job\" fires in Amazon SageMaker, your agent runs \"Get current user\" in Geekbot." canonical: "https://apiant.ai/connect/amazon-sagemaker-to-geekbot" --- # Connect Amazon SageMaker and Geekbot When **New Training Job** fires in [Amazon SageMaker](https://apiant.ai/connections/amazon-sagemaker), your agent runs **Get current user** in [Geekbot](https://apiant.ai/connections/geekbot), or **New Report** in Geekbot 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 Geekbot **1** trigger Geekbot **17** 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 Geekbot 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 Geekbot can do together ### From Amazon SageMaker to Geekbot - When **New Training Job** in Amazon SageMaker then **Get current user** in Geekbot - When **New Training Job** in Amazon SageMaker then **Add out-of-office period** in Geekbot ### From Geekbot to Amazon SageMaker - When **New Report** in Geekbot 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 Geekbot ## Triggers and actions 2 triggers · 18 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 **New Report** Triggers when a new standup report is submitted in Geekbot. - Action **Add out-of-office period** Schedules an out-of-office period for you or, if you are an admin, for another team member, covering whole days from the start date to the end date. - Action **Add poll** Creates a one-shot Geekbot poll that posts a question with answer choices to a channel. - Action **Add standup** Creates a new Geekbot standup with its questions, schedule and broadcast channel. - Action **Delete report** Deletes a standup report you authored, removing its broadcast message if one was posted. - Action **Delete standup** Deletes a standup and returns the details of the standup that was removed. You must have permission to edit the standup. - Action **Get current user** Returns the user who owns the connected API key, along with the team they belong to. - Action **Get poll** Returns one poll you created, including its schedule, channel, members and optionally its questions. - Action **Get report** Returns one submitted standup report, including who posted it, when, and the answer to each question. - Action **Get standup** Returns one standup by id, including its schedule, members, broadcast settings and optionally its questions. - Action **List out-of-office periods** Returns out-of-office periods for the team members you can view, ordered by start date, optionally narrowed by users, standups or a date window. - Action **List polls** Returns the active and paused polls you created in Geekbot, optionally filtered by state, channel, anonymity or creation date. - Action **List poll votes** Returns the vote results for a poll, grouped by broadcast and question. Without a date range it covers only the latest broadcast. - Action **List reports** Returns submitted Geekbot standup reports within a time window, optionally filtered by standup or user. - Action **List standups** Returns the active and paused standups visible to the connected user, with optional filters for state, anonymity, channel and creation date. - Action **List teams** Returns the Geekbot team tied to the connected API key, including its users who take part in at least one standup visible to the connected user. - Action **Start Report** Starts a standup immediately so its report questions go out, either to all of its participants or only to the users or emails you name. Returns the vendor's confirmation that the standup was queued. - Action **Update standup** Updates a standup's name, schedule, questions, channel and participants. Returns the updated standup. ## 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) - [ **Geekbot** Geekbot runs asynchronous standups, retrospectives, and surveys — enabling easy, effective, and transparent...](https://apiant.ai/connections/geekbot) 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 Geekbot - [ **ActiveCampaign to Geekbot** ActiveCampaign is a marketing automation, email marketing, and CRM platform.](https://apiant.ai/connect/activecampaign-to-geekbot) - [ **Airtable to Geekbot** Organize anything with Airtable, a modern database created for everyone.](https://apiant.ai/connect/airtable-to-geekbot) - [ **Asana to Geekbot** Asana is a collaborative information manager for workspace.](https://apiant.ai/connect/asana-to-geekbot) - [ **ClickUp to Geekbot** ClickUp is an all-in-one app to plan, track, and manage your work in a beautifully intuitive environment.](https://apiant.ai/connect/clickup-to-geekbot) - [ **Discord to Geekbot** Discord is an all-in-one voice and text chat for gamers.](https://apiant.ai/connect/discord-to-geekbot) - [ **Freshdesk to Geekbot** Freshdesk is a cloud-based customer support and helpdesk platform.](https://apiant.ai/connect/freshdesk-to-geekbot) Questions ## Amazon SageMaker and Geekbot, 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 Geekbot when something happens in Amazon SageMaker? Any of Geekbot's 17 actions, including Update standup, Add out-of-office period, Add poll and Add standup. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Geekbot to Amazon SageMaker? Yes. When something happens in Geekbot, your agent can act in Amazon SageMaker too. This page covers both directions: Geekbot's triggers and Amazon SageMaker's actions are listed here as well. ### ### Do I have to build a connector for Amazon SageMaker or Geekbot? 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 Geekbot 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.