Skip to content
Agentic Workflowdocs
v0.9.0Install free

nodes / builtin / trigger

Chat Trigger

Run the flow on each chat message from the user.

Trigger ExtensionWeb app

Turn a workflow into a chatbot: every message you send runs the workflow once.

The Chat Trigger opens a chat window. Each message you send starts one run of the workflow, from this trigger only, with your text in chatInput.

In AWFlow 0.9 the run has a reply channel back to the chat. The reply comes from the reply step: a Respond to Chat step, or else the last AI step on the trigger’s path. It streams into the chat as it is written, and tool calls show as short chips. Stop stops the run; the part of the reply already written is kept and marked as stopped.

  • New Chat Triggers (version 2) don’t need a Chat Memory. Without one, the chat keeps the session’s messages until it is closed. Connect a Chat Memory to keep the conversation for later (and to see it on the Memory page).
  • Chat Triggers saved before 0.9 keep needing a Chat Memory, shared with the agent that answers: the agent saves both messages there and the chat window reads them back. Update in the step’s header moves to version 2.

Turn on Show in Aria (with a one-line Description) and, once the workflow is On, it appears in Aria’s list next to your agents, with a workflow badge, and in @mentions. A workflow chat in Aria is a chat with its own thread: each message runs the saved workflow from this trigger, with the active tab’s address and title. Each reply shows Ran N steps · time · View run. If the workflow is Off, the chat offers Turn it on. Typing @support-bot … in any Aria chat runs that workflow for one message and posts its reply. See Chat with Aria.

Under Attachments (off by default), let people send files (choose the File types and the Largest file (MB)) and the page you are on (the tab, with or without the selected text). Files reach the run under $binary (file0, file1…) with a files summary; the page arrives as page (url, title, text, selection), marked as untrusted content for AI steps. Attachments work in the canvas chat and in Aria workflow chats.

Where you can chat:

  • On the canvas. Run opens the chat when the Chat Trigger is the only trigger. You can also pick it in the trigger picker or press the node’s Run step button.
  • On web pages (extension). When the workflow is On, a chat bubble appears on pages matching URL Patterns. If several chat workflows match, the bubble lets you pick one. You can also right-click and choose Open chat. The run still happens in the AWFlow app tab, and the page’s url, title and tabId are passed to the trigger.
  • Build an assistant you can talk to while designing a workflow.
  • Put a helper on specific websites, for example your internal tools, using URL Patterns.
  • Give an agent a running conversation, so each message builds on the earlier ones.

For a one-off question without a chat window, start the agent from When I press Run or From the right-click menu instead.

SettingTypeWhat it does
Assistant name Text Default: Assistant
Icon TextEmoji or image URL shown in the chat header.
Greeting Long text Default: How can I help you today?
Input placeholder Text Default: Type a message…
Starter prompts TagsSuggested prompts shown before the conversation begins.
Allow clearing the conversation Toggle Default: On
Show in Aria ToggleChat with this workflow from Aria, next to your agents (while it is on).
Attachments GroupWhat people can send with a message.
Attachments › Accept files Toggle Default: Off
Attachments › File types Tags Default: ["image/*","application/pdf","text/csv","text/plain","application/json"]
Attachments › Largest file (MB) Number Default: 10
Attachments › The page you are on ChoiceOptions: Off, This tab, This tab and the selection. Default: Off
Description TextOne line under its name in Aria.
URL Patterns Tags Default: ["<all_urls>"]

Assistant name, Icon, Greeting, Input placeholder and Starter prompts only change how the chat window looks. URL Patterns decides on which pages the chat bubble shows (<all_urls> means every page); it uses the form https://*.example.com/*.

  • Output

Each output item has these fields:

FieldTypeWhat it holds
triggerType Always "chat"
triggeredAt Text
chatInput TextThe message the user sent
sessionId TextThe connected Chat Memory conversation
url Text
title Text
tabId Number
$binary Key-value pairs
files List of entriesThe files sent with the message
page ObjectThe page the user shared, its text fenced as untrusted data
Shape of an output item
{
"triggerType": "chat",
"triggeredAt": "…",
"chatInput": "…",
"sessionId": "…",
"url": "…",
"title": "…",
"tabId": 0,
"$binary": {},
"files": [],
"page": {}
}

Set the agent’s prompt to {{ $input.chatInput }}. sessionId is empty when the memory uses This run only storage. url, title and tabId are only set when you chat from a web page.

SlotAcceptsConnections
Memory (required)chat memoryOne node.

Connect a Chat Memory to the Memory slot, and connect the same Chat Memory node to the memory slot of the agent that answers (Tools Agent or RAG Agent). Use Conversation storage (pick a conversation, or leave it empty to give the node its own) or Key storage with a fixed key.

Workflows built with the older Local Memory, Persistent Chat Memory or Window Buffer Memory keep working; those nodes are now upgraded to Chat Memory.

  1. Add a Chat Trigger.
  2. Add a Chat Memory with Conversation storage and connect it to the trigger’s Memory slot.
  3. Add a Tools Agent after the trigger, connect a chat model, and connect the same Chat Memory to its memory slot.
  4. Set the agent’s prompt to {{ $input.chatInput }}.
  5. Press Run and start chatting.
  • “Dependency memory is required”, or the chat says no Chat Memory is connected. Connect a Chat Memory to the trigger’s Memory slot.
  • Nothing appears, not even my own message. The trigger does not save messages; the agent does. Check that an agent runs on every message and uses the same memory node as the trigger.
  • The agent answers but the chat stays empty. The agent uses a different memory, conversation or key than the trigger.
  • The chat forgets earlier messages. The memory uses This run only or a key written as an expression. Use Conversation storage or a fixed key.
  • Each message shows twice, or several replies appear. Every agent connected to the same memory saves its own copy. Use one agent per conversation.
  • On a web page, the “thinking” indicator never stops. The run failed before a reply was saved. Press stop, then check the run in the execution history. Stop only resets the chat window; a run that is still going keeps going.
  • No chat bubble on a page. Turn the workflow On and check that a URL Patterns entry matches the page.

See also Memory & Context.

Edit page

Last updated:

Was this page useful?
Ask Aria about Chat Trigger