19. Technical specifications for RAG

RAG allows your agent to respond using real information (documents) instead of relying only on general knowledge. This helps limit responsibilities and prevents the agent from hallucinating answers or falling short when it lacks sufficient information.

19.1. Supported file types

Currently, you can use:

• Word documents (.docx)
• PDFs
• Images

CoT defines how your agent thinks and acts during the conversation, it’s like training a new human agent to make calls.

A good CoT doesn’t just give instructions; it guides behavior, tone, and decision-making.

17. Best practices for an efficient CoT

17.1. Clearly define context and role

The agent must know:

• Who it is
• Who it represents
• The purpose of the call

Correct example

16. Setting up your first agent in Rootlenses Voice is a quick and simple process

In just a few steps, you can have an agent ready to make calls, test conversations, and start generating value from day one.

What can you achieve with your first agent?

With your Voice agent, you can:

• Automate outbound calls
• Test conversational flows in real time
• Validate scripts before scaling to production
• Integrate your own knowledge for more accurate responses