# Connect DoneThat and Langfuse When **New Project** fires in [DoneThat](https://apiant.ai/connections/donethat), your agent runs **Get Project** in [Langfuse](https://apiant.ai/connections/langfuse), or **New Trace** in Langfuse to **Add Project** in DoneThat. Describe the whole flow and it is built, tested on every scenario and kept running. DoneThat **1** trigger DoneThat **6** actions Langfuse **1** trigger Langfuse **14** actions What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it. ## What do you want DoneThat and Langfuse to do together? Give your AI client this address. `https://mcp.apiant.ai` 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 DoneThat and Langfuse can do together ### From DoneThat to Langfuse - When **New Project** in DoneThat then **Get Project** in Langfuse - When **New Project** in DoneThat then **Add Comment** in Langfuse ### From Langfuse to DoneThat - When **New Trace** in Langfuse then **Add Project** in DoneThat - When **New Trace** in Langfuse then **Edit Project** in DoneThat 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 DoneThat and Langfuse ## Triggers and actions 2 triggers · 20 actions - Trigger **New Project** Triggers when a project is created within the lookback window. Recommended Zap poll interval: 1 hour or longer. - Action **Add Project** Creates a new DoneThat project. - Action **Archive Project** Archives or unarchives a DoneThat project. - Action **Edit Project** Updates an existing DoneThat project. - Action **Find Project** Find projects by name (optional filter). - Action **Get Summary** Returns the formatted DoneThat summary for a given date and level (day, week, month, quarter or year). - Action **Search** Search DoneThat task and activity history. - Trigger **New Trace** Polling trigger: fires for newly created traces (dedup by trace id / timestamp). - Action **Add Comment** Add a comment to a trace/observation/session/prompt object. - Action **Add Dataset** Create a new dataset. - Action **Add Dataset Item** Create an item (input/expected_output/metadata) in a dataset. - Action **Add Prompt** Create a new prompt version (text or chat). - Action **Add Score** Create a score attached to a trace/observation/session (numeric, categorical, or boolean). - Action **Delete Trace** Delete a trace by id. - Action **Get Project** Reads the Langfuse project that the connection's project-scoped API key belongs to. - Action **Get Prompt** Get a prompt by name (and optional version/label). - Action **Get Trace** Get a single trace by id, including nested observations/scores. - Action **List Dataset Items** List items in a dataset. - Action **List Datasets** List all datasets in the project. - Action **List Prompts** List all prompts in the project. - Action **List Scores** List scores with optional filters. - Action **List Traces** List traces with optional filters (user, session, tags, timerange). ## Each app on its own - [ **DoneThat** DoneThat is a time tracking tool that uses AI to understand screen activity and automatically organize work...](https://apiant.ai/connections/donethat) - [ **Langfuse** Langfuse is an open-source LLM engineering platform (GitHub) that helps teams collaboratively debug...](https://apiant.ai/connections/langfuse) Reviews ## What our customers say ## More from DoneThat - [ **DoneThat to HubSpot** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/donethat-to-hubspot) - [ **DoneThat to Salesforce** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/donethat-to-salesforce) - [ **DoneThat to Slack** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/donethat-to-slack) - [ **DoneThat to Google Sheets** Google Sheets](https://apiant.ai/connect/donethat-to-google-sheets) - [ **DoneThat to Gmail** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/donethat-to-gmail) - [ **DoneThat to Google Calendar** Google Calendar is a time management tool providing scheduling features, event reminders, and integration...](https://apiant.ai/connect/donethat-to-google-calendar) ## More into Langfuse - [ **Salesforce to Langfuse** Salesforce is a leading enterprise customer relationship management (CRM) platform.](https://apiant.ai/connect/salesforce-to-langfuse) - [ **Google Drive to Langfuse** Google Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...](https://apiant.ai/connect/google-drive-to-langfuse) - [ **HubSpot to Langfuse** HubSpot is your all-in-one stop for all of your marketing software needs.](https://apiant.ai/connect/hubspot-to-langfuse) - [ **Slack to Langfuse** Slack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...](https://apiant.ai/connect/slack-to-langfuse) - [ **Google Sheets to Langfuse** Google Sheets](https://apiant.ai/connect/google-sheets-to-langfuse) - [ **Gmail to Langfuse** Gmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...](https://apiant.ai/connect/gmail-to-langfuse) Questions ## DoneThat and Langfuse, answered ### ### What can start an automation from DoneThat? Any of DoneThat's 1 trigger in the catalog, including New Project. Describe the moment in plain language and your agent picks the right one. ### ### What can your agent do in Langfuse when something happens in DoneThat? Any of Langfuse's 14 actions, including Add Comment, Add Dataset, Add Dataset Item and Add Prompt. Your agent maps the data both ways and tests every scenario before it ships. ### ### Can it also run from Langfuse to DoneThat? Yes. When something happens in Langfuse, your agent can act in DoneThat too. This page covers both directions: Langfuse's triggers and DoneThat's actions are listed here as well. ### ### Do I have to build a connector for DoneThat or Langfuse? 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. ### ### 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.