Have you ever wondered how to build a self-clearing chat flow? I don't think so. Because who needs that anyway? Here's an example. You can see that first, a few messages are sent to the chat. Afterward, a short timer is triggered, which ultimately leads to the clear node.
This chatbot waits for your input. It then creates a message with the content you entered. After you enter a message, the bot first responds. A call-edge then restores the prompt to its default state. Because the prompt no longer contains any data, the connection to the message is severed. This means the message is no longer part of the current context. The message is set to be resent when the context resumes.
This chat will wait until you type the correct password. Hey? Can you find it? If the password is incorrect, a message will be sent and the prompt will be reset so you can try again. This is just an example. Please never store sensitive information in a public Wanderer flow.
This example shows how you can quickly turn a public API into a chatbot.
When users send a prompt to this agent, a GPT node will attempt to determine the intents. Task nodes ensure that multiple intents can be processed smoothly one after the other.
This agent contains a prompt that accepts text from the user. This text is then passed to various Contains nodes. These nodes examine whether certain keywords are present in the text and activate other branches accordingly.
An OR gate is a logical structure. It describes how different conditions can occur for the same event to be triggered. OR gates are represented in this system using 'may edges'.
GPT nodes can be used to generate dynamic prompts from the flow. These are answered by ChatGpt. You can then use the response in the flow.
This flow contains a switch. You can use 'call edges' to turn the switch on or off. When this happens is determined by a simple question. You can turn the switch on or off from the chat.
A branch structure is like the branches of a tree. They branch out further and further.
In a star structure, there is a central node from which the signals are sent outward. You can see that the connected nodes are processed in parallel. The respective layers are discovered simultaneously and sorted and executed according to the order of the widest edges.
This flow is part of the tutorial, which can be loaded within the builder.