> 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/flow-studio/flow-studio.md).
# Start here
Flow Studio is where you automate the work around your agents. What a flow is, what it is made of, and how to build your first one.
**Flow Studio** is Dapta's automation builder. A **flow** is a sequence of steps that runs on its own: something happens, and Dapta does the rest — writes a row, sends an email, calls an API, places a call, posts to Slack.
An empty Flow Studio canvas — every flow starts here.
If an agent is the conversation, a flow is everything that has to happen around it.
## What a flow is made of
| Piece | What it does |
| --------------- | ----------------------------------------------------------------------------------- |
| **A trigger** | What starts the flow — a finished call, a webhook, a schedule, a form submission |
| **Nodes** | The steps in between: send an email, call a model, read or write a record, run code |
| **Connections** | The order the steps run in, and what data passes between them |
A flow always starts with one trigger and runs its nodes in order. You can test it before it goes live, and see every execution afterwards.
## What people automate with it
* Save what an agent collected on a call into Google Sheets or a CRM.
* Email or Slack the team the moment a qualified lead comes in.
* Feed a contact list into an outbound sequence.
* Expose an API endpoint that your own systems can call.
* Run any of the above on a schedule.
***
## Start here
{% content-ref url="/pages/vI6wP08DsQSlPdorkZqb" %}
[Understanding the basics of AI integrations](/flow-studio/understanding-the-basics-of-ai-integrations.md)
{% endcontent-ref %}
{% content-ref url="/pages/Pz7BppzrVK4WkgMcbq4s" %}
[Creating a New Flow in Flow Studio](/flow-studio/creating-a-new-flow-in-flow-studio.md)
{% endcontent-ref %}
{% content-ref url="/pages/PhTCpKrcrmDC04f2f00p" %}
[Setting Up Triggers in Flow Studio](/flow-studio/setting-up-triggers-in-flow-studio.md)
{% endcontent-ref %}
## The building blocks
{% content-ref url="/pages/cXdd8k8wANN4uqvxS2zu" %}
[Nodes](/flow-studio/nodes.md)
{% endcontent-ref %}
{% hint style="info" %}
You do not have to build flows by hand. Ask [Dapti](/dapti/capabilities/flow-studio.md) to design, deploy and test one for you from a chat.
{% endhint %}
---
# 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/flow-studio/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.
