All articles on how to create & orchestrate LLM-powered AI Agents
- Getting Started with AI Agents
- Prerequisites: Set up your AI Agent's brain
- Create your AI Agent's persona
- Give your AI Agent a Job
- Make knowledge available to your AI Agent
- Give your AI Agent access to memory
- Deploy and use your AI Agent
- Improve your AI Agent’s skills using Tool Actions
- Enable your AI Agent to understand images
- Talk to your AI Agent via voice or phone
- Debugging your AI Agent
An AI Agent can handle multiple jobs. Task- or job-specific details are defined in the AI Agent Node. Only task-specific details should be configured in individual Nodes, while overarching aspects that apply to all uses of the AI Agent should be set directly in the AI Agent itself.
-
Add an AI Agent Node to your Flow.
If you’ve completed the previous steps, open the newly created Flow, typically named after your agent, via sidebar and then Build -> Flows. This Flow already has an AI Agent Node. You can also always create a new Flow and add one or more AI Agent Nodes.
-
Assign the AI Agent.
Assign your AI Agent to the AI Agent Node to enable it to perform the specified job.
-
Job Title, Description, Instructions and Context.
In the AI Agent Node, you’ll find various settings to define the job and more. Start by giving the job a name, such as “Customer Support Specialist,” and providing a detailed description. The description offers a general, job-posting-like overview, while the instructions outline specific guidance on when and how the AI Agent should perform their job. For now, we’ll leave all settings unchanged.
Now you can experiment with your AI Agent in the interaction panel, testing different descriptions and instructions to explore their effects.
➡️ What's next? Provide your AI Agent with knowledge.
Comments
0 comments