Create Custom Autonomous Agents
Posted: Thu Dec 05, 2024 6:27 am
Solutions Engineer's Guide to Autonomous Nodes
This guide aims to help bot creators create AI agents in Botpress Studio.
I don't know
autonomous nodes" on blue and black background
The botpress autonomous node allows you to create functional AI agents, not chatbots, but autonomous agents that make decisions based on the available context.
By providing clear instructions and integrating tools, bot creators can use autonomous nodes to profile a chatbot's behavior.
The node is designed to manage both decision sri lanka phone numbers making and execution by understanding user input, responding with appropriate data, and leveraging its tools.
If you are interested in using a standalone node, you are in the right place. In this article, I'm going to lay the groundwork for using our agentic powerhouse platform feature.
Create AI agents
start now
no credit card needed
main features of the autonomous node
1. LLM based on decisions
An autonomous node uses the capabilities of an LLM to make intelligent decisions.
2. Autonomous behavior
An autonomous node can execute actions without manual intervention based on user instructions and input.
3. Tools
the autonomous node understands and uses specific tools: for example, it can query knowledge bases, perform Internet searches, and execute workflow transitions.
4. Personalization
By setting up an autonomous node with an appropriate person and detailed instructions, you can ensure that it behaves on-brand and in-scope during conversations.
5. Write and run code
the autonomous node can generate and execute custom code to perform tasks.
6. Self-correction
If the autonomous node finds itself going down a wrong path, it has the ability to self-correct and recover from errors.
configuration settings
Each autonomous node requires careful configuration to align its behavior with business needs.
The most important part of creating a standalone node is writing the proper instructions. Instructions help the agent understand who you are and guide them in making decisions.
The instruction box of an autonomous node.
The instruction box of an autonomous node.
Instruction box
In the instruction box, provide clear guidelines. The more specific the instructions, the better the agent's decision making will be.
Example: "You are a helpful assistant who always answers questions using the 'knowledgeagent.knowledgequery' tool. If the user says 'search', use the 'browser.websearch' tool."
Allow conversation
The allow conversation option allows the autonomous node to communicate directly with users. If disabled, the node only processes commands and executes its internal logic without sending messages to users.
Know the tools
Depending on the instructions you give it, an autonomous node is equipped with various tools that it can call.
Each tool performs a specific action: understanding when and how to use them is essential to drive node decisions.
The 7 most common tools
global.reflect: Allows the llmz engine to reflect before continuing.
Browser.websearch: Allows the agent to search the web for answers.
Knowledgeagent.knowledgequery: Queries an internal knowledge base for relevant information.
Clock.setreminder – Set a reminder for future tasks or responses.
Workflow.transition - Executes a workflow transition, moving from one part of the conversation to another based on user input.
Chat.sendtext – Send a text message to the user as a reply.
Chat.waitforuserinput: Stops execution and waits for the user to enter more data.
The tools section of an autonomous node.
The tools section of an autonomous node.
By specifying which tool to use in response to user actions, you can control the flow and results of the conversation.
This guide aims to help bot creators create AI agents in Botpress Studio.
I don't know
autonomous nodes" on blue and black background
The botpress autonomous node allows you to create functional AI agents, not chatbots, but autonomous agents that make decisions based on the available context.
By providing clear instructions and integrating tools, bot creators can use autonomous nodes to profile a chatbot's behavior.
The node is designed to manage both decision sri lanka phone numbers making and execution by understanding user input, responding with appropriate data, and leveraging its tools.
If you are interested in using a standalone node, you are in the right place. In this article, I'm going to lay the groundwork for using our agentic powerhouse platform feature.
Create AI agents
start now
no credit card needed
main features of the autonomous node
1. LLM based on decisions
An autonomous node uses the capabilities of an LLM to make intelligent decisions.
2. Autonomous behavior
An autonomous node can execute actions without manual intervention based on user instructions and input.
3. Tools
the autonomous node understands and uses specific tools: for example, it can query knowledge bases, perform Internet searches, and execute workflow transitions.
4. Personalization
By setting up an autonomous node with an appropriate person and detailed instructions, you can ensure that it behaves on-brand and in-scope during conversations.
5. Write and run code
the autonomous node can generate and execute custom code to perform tasks.
6. Self-correction
If the autonomous node finds itself going down a wrong path, it has the ability to self-correct and recover from errors.
configuration settings
Each autonomous node requires careful configuration to align its behavior with business needs.
The most important part of creating a standalone node is writing the proper instructions. Instructions help the agent understand who you are and guide them in making decisions.
The instruction box of an autonomous node.
The instruction box of an autonomous node.
Instruction box
In the instruction box, provide clear guidelines. The more specific the instructions, the better the agent's decision making will be.
Example: "You are a helpful assistant who always answers questions using the 'knowledgeagent.knowledgequery' tool. If the user says 'search', use the 'browser.websearch' tool."
Allow conversation
The allow conversation option allows the autonomous node to communicate directly with users. If disabled, the node only processes commands and executes its internal logic without sending messages to users.
Know the tools
Depending on the instructions you give it, an autonomous node is equipped with various tools that it can call.
Each tool performs a specific action: understanding when and how to use them is essential to drive node decisions.
The 7 most common tools
global.reflect: Allows the llmz engine to reflect before continuing.
Browser.websearch: Allows the agent to search the web for answers.
Knowledgeagent.knowledgequery: Queries an internal knowledge base for relevant information.
Clock.setreminder – Set a reminder for future tasks or responses.
Workflow.transition - Executes a workflow transition, moving from one part of the conversation to another based on user input.
Chat.sendtext – Send a text message to the user as a reply.
Chat.waitforuserinput: Stops execution and waits for the user to enter more data.
The tools section of an autonomous node.
The tools section of an autonomous node.
By specifying which tool to use in response to user actions, you can control the flow and results of the conversation.