Skip to main content
Agents are the core of the VIVI platform. An agent is your virtual team member that interacts with customers, employees, or systems. Agents combine several components, such as knowledge bases and prompts, into one system. These components allow your agent to deliver helpful, accurate, and efficient support. At a minimum, every agent requires a name, prompt, and model to be live. Once configured, you can use the Test Agent feature or Evaluations to validate responses before deployment. Unlike traditional decision trees or scripted bots, VIVI agents are dynamic — they reason, act, and adapt to context. Agents can be duplicated, customized, or scaled as your organization evolves.

​
Building Agents

When building your agent, you can customize every detail to match your organization’s standards, tone, and goals.
1

Choose a Name & Description

Choose a clear name and description that reflects the agent’s purpose.
2

Add a Prompt

Define the agent’s role, tone, and rules of engagement.
3

Select a Model

Choose the large language model that powers the agent.
4

Connect Knowledge Bases

Provide the internal sources of truth the agent can reference.
5

Enable Integrations

Connect apps, APIs, or even other agents for advanced actions.
6

Select Channel

Decide where the agent will be active (web chat, WhatsApp, API, etc.).
7

Test the Agent

Use the testing features to verify accuracy and performance before deployment.

​
Models

VIVI supports a range of large language models, each suited to specific use cases. Below is an overview of the current model lineup:
ModelInput (tokens)Maximum Output (tokens)Use Case
gpt-5.1-high272,000128,000Maximum intelligence with deep reasoning for difficult problems.
gpt-5.1-medium272,000128,000Balanced intelligence and reasoning for complex tasks.
gpt-5.1-low272,000128,000Efficient reasoning for moderately complex problems.
gpt-5.1272,000128,000Fastest and most capable model for all tasks, is not a reasoning model.
gpt-5-mini-high272,000128,000Strong reasoning for complex tasks at a low cost.
gpt-5-mini-medium272,000128,000Balanced reasoning for everyday complex problems.
gpt-5-mini-low272,000128,000Light reasoning for simple to moderate tasks.
gpt-5-mini-minimal272,000128,000Fast, cost-effective reasoning for simple agents.
gpt-realtime28,6728,191Instant, short-context, voice-first realtime agent. Contains 10 different voice options to cover a range of use cases and tones.

​
Best Practices

  • Use descriptive names so team members can quickly identify each agent’s role.
  • Choose large-context models for complex reasoning and smaller, faster models for lightweight workflows.
  • Test thoroughly after configuring each component to ensure accuracy and reliability.