> ## Documentation Index
> Fetch the complete documentation index at: https://docs.callivox.com/llms.txt
> Use this file to discover all available pages before exploring further.
# Flows
> Script a conversation step by step on the flow canvas, understand the node palette, and know when to let the AI cover what the script misses.
A flow is a conversation drawn as a diagram. Instead of trusting the AI to work out what to say
next, you lay out the steps — send this, ask that, branch on the answer — and the agent walks the
path. Flows belong to **Flow Agents**, created from the **+ New agent** menu.
## When to use a flow
Use a flow when the conversation has a shape you already know: an order-status check, a booking,
a qualification questionnaire, a returns process. You get the same steps every time, in the same
order, with the same wording.
Use a [Prompting Agent](/ai-agents/creating-an-agent) instead when customers arrive with open
questions you can't enumerate.
## The canvas
A Flow Agent opens straight onto its **Flow** tab. Drag nodes from the palette, connect the output
of one to the input of the next, and click into a node to configure it. The canvas has its own
**Save** and **Publish** controls — a flow doesn't go live until you publish it.
Because the canvas owns its own saving, the editor's **Test** button is hidden while the Flow tab
is open. Leaving the tab with unsaved work raises **Discard unsaved changes?** first.
## The node palette
Nodes are grouped by what they do.
| Node | What it does |
| --------- | --------------------------------- |
| **Start** | "Where every conversation begins" |
Every flow has exactly one Start node.
| Node | What it does |
| ----------------- | ----------------------------------------- |
| **Send Text** | "Send a plain text message" |
| **Send Media** | "Send an image, video, audio or document" |
| **Send Location** | "Send a pin on the map" |
These say something and move straight on to the next node.
| Node | What it does |
| -------------------- | ----------------------------------------------------- |
| **Ask Buttons** | "Prompt with up to 3 reply buttons" |
| **Ask List** | "Prompt with a single-select list (≤10 rows/section)" |
| **Ask Text** | "Ask an open question and capture the answer" |
| **Ask Dynamic List** | "A single-select list built from API data" |
These wait for the customer. Buttons and lists each get one output per choice, so the flow
branches on what the customer picks. **Ask Dynamic List** builds its options at run time from
a system of yours — useful for available appointment slots or a live product list.
The limits of 3 buttons and 10 list rows per section come from the messaging channels
themselves, and the canvas warns you when you exceed them.
| Node | What it does |
| -------------------- | ---------------------------------------------------------- |
| **AI Collect** | "Goal-driven collection into variables" |
| **AI Intent Branch** | "Classify free text into outcomes" |
| **AI Answer (KB)** | "Bounded Q\&A from the knowledge base" |
| **Route to Folder** | "Move the chat to a folder; the folder's agent takes over" |
| **Handoff to Human** | "Assign to a person and stop auto-replies" |
These bring judgement into an otherwise fixed script. **AI Collect** keeps asking until it has
the variables you listed. **AI Intent Branch** reads free text and sends the conversation down
the branch that matches. **AI Answer (KB)** answers from your
[knowledge base](/ai-agents/prompt-knowledge-and-tools) and nothing else, with a
**No-answer reply** for when the knowledge base has nothing.
**Route to Folder** and **Handoff to Human** both end the flow — one passes the conversation to
whichever agent owns that folder, the other passes it to a person.
| Node | What it does |
| ---------------- | ----------------------------------------- |
| **Condition** | "Branch on a variable or the last answer" |
| **Set Variable** | "Assign a flow variable" |
| **HTTP Request** | "Call an API and save its JSON response" |
| **End** | "Terminate the conversation flow" |
**HTTP Request** has two outputs — one for a successful call and one for an error — so you can
tell the customer something sensible when your system is down.
Every branching node also gets a trailing **else** output, which catches anything that didn't match
one of your named branches. Connect it — an unconnected `else` is where conversations go to die.
## Building a simple flow
Here is an order-status check, end to end.
Drag a **Send Text** node and connect it to **Start**. "Hi! I can check an order for you."
Add an **Ask Buttons** node with two buttons: `Track my order` and `Something else`. The node
now has an output per button.
From the `Track my order` output, add an **Ask Text** node — "What's your order number?" — and
save the answer into a variable.
Add an **HTTP Request** node that calls your order system with that variable, and keep the
response.
From the success output, add a **Send Text** node that reads the status back to the customer.
From the error output, add a **Handoff to Human** node so a person can pick it up.
Send the `Something else` output — and the `else` output — to **Handoff to Human** too.
Nothing you draw affects live conversations until you publish.
## When Hybrid is the right choice
A pure flow only knows the paths you drew. Customers don't. Someone will answer "actually can I
change the delivery address?" in the middle of your order-status branch, and a strict flow has
nothing to say.
The **General** tab of a Flow Agent has a switch for exactly this:
> **Let AI handle off-script messages** — When on, the agent follows your flow but falls back to
> the AI for anything the flow doesn't cover (Hybrid). When off, it sticks strictly to the flow.
The process is regulated, scripted or contractual, and an improvised answer would be a problem.
A strict flow never says anything you didn't write.
The flow covers the common path but customers wander. The agent stays on the script where the
script applies and answers freely where it doesn't.
With Hybrid on, the agent also gains a **Prompt & Tools** tab — the fallback replies use the same
system prompt, knowledge base and tools as a Prompting Agent, so fill those in too.
## Next steps
Needed for Hybrid fallbacks and AI nodes.
Where **Route to Folder** sends a conversation.