> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/dapta-mcp/skills/flow-studio.md). # Flow Studio Build and deploy Flow Studio automations from a chat, change one part of an existing flow without rewriting it, and inspect or report on the flows you already run. Ask Claude to design new automations, change the ones you have, and understand how they are running. Three guides cover this area. {% hint style="info" %} Building, changing, archiving or running a flow uses a **preview, then confirm** flow. Running a flow is also flagged as reaching outside Dapta, because a flow can send messages or place calls. {% endhint %} ### Build a flow **Guide:** `flow-studio-flow-builder` **What it does:** Designs and builds Flow Studio automations for you. It asks about your goal, trigger, and integrations, then assembles a working flow (for example, pull leads from Google Sheets, loop through them, place voice calls, then update your CRM) and deploys it after you approve. Claude also places the nodes on the canvas, so the flow opens laid out in Flow Studio: each step below the one before it, with the branches of a condition side by side. **Use it when:** You want to create a new automation, build a flow from a use case or a spec you paste in, organize flows into a folder, or run a flow. **Try saying:** * "Build me a flow that calls leads from a Google Sheet and updates the row with the result." * "Create an automation that emails a summary after each WhatsApp conversation." * "Run the lead-import flow with this test input." **You get back:** A summary of the flow it designed, a status table of which integration credentials are connected versus missing, a preview of what will be created or changed, and after you approve, the deployed flow and a checklist of any fields you still need to configure in Flow Studio. **Writes data?** Yes, via preview then confirm. **Behind the scenes:** `search_flow_templates`, `get_flow_template_by_id`, `search_node_templates`, `get_node_template_by_id` (proven building blocks), `get_workspace_integrations` (credentials), `validate_flow_structure`, then `preview_create_flow` and `commit_create_flow`, `preview_create_flow_folder` and `commit_create_flow_folder`, `preview_update_flow` and `commit_update_flow`, `preview_execute_flow` and `commit_execute_flow`. *** ### Change one part of a flow **Guide:** `flow-patching` **What it does:** Changes one part of an existing flow without rewriting it. Claude reads the wiring, drills into a single node, and sends only the operations needed, so everything you did not name is preserved exactly. If somebody changed the flow in Flow Studio in the meantime, the change is refused instead of silently reverting their work. Steps Claude adds are placed on the canvas next to the rest, and nodes that already have a place stay where they are. Claude can also lay out a whole flow that opens as a pile of cards. This guide also covers archiving a flow, or a whole folder with every flow and sub-folder in it, with callers and schedules shown first. Archived flows go to the **Trash** in Flow Studio, where you can restore them. A folder with more than 50 flows is archived one sub-folder at a time. **Use it when:** You want to add a step, change a filter, edit one node, tidy up a flow's layout, archive a flow or a folder, or go back to an earlier version. **Try saying:** * "Add a follow-up email step to my appointment-reminder flow." * "Change the filter in the second step so it only keeps leads from Mexico." * "Archive the old onboarding flow. What depends on it?" * "Archive the Q1 campaigns folder." * "My lead-routing flow opens as a pile of cards. Lay it out." **You get back:** A preview of the exact change, and after you confirm, the updated flow. **Writes data?** Yes, via preview then confirm. **Behind the scenes:** `get_flow_graph`, `get_flow_node`, `preview_patch_flow` and `commit_patch_flow`, `preview_archive_flow` and `commit_archive_flow`, `search_agents_referencing`, `diff_flow_versions`, `preview_rollback_flow` and `commit_rollback_flow`. *** ### Inspect and report **Guide:** `flow-studio-analytics` **What it does:** Inspects and reports on your existing Flow Studio automations. Lists your flows and folders, explains what a flow does, shows execution health, run history, version history, configured integrations, schedules and webhook details. Read-only. **Use it when:** You want to list or count your flows, see how often a flow runs and its error rate, read the last runs of a flow, find out who last edited a flow, check connected integrations, or get a flow's input schema or webhook URL. **Try saying:** * "List all the automations in my workspace." * "Show me the last runs of the call-automation flow. Did any fail?" * "Which of my flows mention this spreadsheet?" **You get back:** Flow lists grouped by folder, per-flow execution stats, a list of recent runs with the detail of any one of them, version history, an integrations list, and flow input schemas or webhook URLs on request. **Writes data?** No, read-only. **Behind the scenes:** `get_workspace_flows`, `search_flows`, `get_flow_details`, `get_flow_execution_stats`, `get_flow_execution_logs`, `get_flow_execution_detail`, `get_flow_versions`, `get_flow_version`, `get_workspace_integrations`, `get_flow_webhook_url`, `get_flow_input_schema`, `get_scheduled_task`. *** ## Related {% content-ref url="/pages/YZKIrjeQMTstQL5d5t3v" %} [Dapta Databases](/dapta-mcp/skills/dapta-databases.md) {% endcontent-ref %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.dapta.ai/dapta-mcp/skills/flow-studio.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.