Dialogs are guided, multi-step conversation flows. Unlike articles, which return a single answer to a matched intent, dialogs take the user through a sequence of steps — collecting information, making decisions, and delivering targeted responses. Dialogs are triggered from Events or Articles, or linked directly from other dialogs.
Output Nodes
Each step in a dialog can produce an output. Dialog output nodes support the same output types as Events and Articles:
-
Text / channel output — content delivered to the user at this step in the flow.
-
Add dialog — branches into another dialog.
-
Add agent — hands the conversation to a HALO agent. The agent handles subsequent turns until it completes, then control returns to AI Cloud's NLP flow.
-
Add tool — invokes a HALO tool with mapped input parameters. Output can be stored in a conversation variable. Control returns to the NLP flow immediately after the tool completes.
→ Using HALO Agents and Tools in Content
Context and Labels
Context variables can be applied to individual output nodes within a dialog, allowing the same dialog step to produce different outputs depending on conversation state. Labels can be added to the dialog as a whole for organisation.