Skip to main content
Version: 2.0

Agents

Vectara Agents enable enterprises to build sophisticated, enterprise-grade intelligent, applications that go beyond basic question answering. Agents interpret user input, reason through context, leverage external tools, and maintain continuity across multi-turn interactions.

Unlike traditional RAG systems that simply retrieve documents and pass them to a language model, Vectara agents provide orchestrated workflows capable of taking action, retrieving information, invoking APIs, or maintaining user sessions.

What are agents?

Agents provide a comprehensive framework for building AI-powered applications with the following capabilities:

  • Understand context: Maintain conversation history across multiple interactions.
  • Use tools: Access and manipulate data through a variety of tools including corpus search and web search.
  • Follow instructions: Execute complex workflows based on customizable instructions and templates.
  • Stream responses: Provide real-time updates as agents process requests.

What agents can accomplish

Desired outcomeWorkflow
Automate customer support workflows
  1. Agent handles L1 support
  2. Searches knowledge bases
  3. Escalates complex issues
  4. Creates tickets
Build intelligent research assistants
  1. Agent searches multiple data sources
  2. Synthesizes findings
  3. Maintains research context across sessions
Create workflow automation systems
  1. Agent triggers business processes
  2. Sends notifications
  3. Updates CRM systems based on natural language requests
Develop conversational enterprise tools
  1. Agent maintains context
  2. Handles multi-step processes
  3. Integrates with existing business systems
Deploy autonomous business processes
  1. Agent monitors conditions
  2. Makes decisions
  3. Executes actions without human intervention

How agents work

Agents access corpora using tools. Each tool is configured with explicit permissions to one or more corpora. When creating or configuring an agent, you select which tools the agent can use. This ensures:

  • Clear separation between orchestration logic (agents) and data access (tools/corpora).
  • Auditable permissions for every retrieval or external action
  • Reusable tools that can serve multiple agents

Agent concepts

Agents

Agents act as the orchestration layer of the platform:

  • Coordinate between different tools and data sources.
  • Maintain conversation context through sessions.
  • Follow customizable instructions to guide behavior.
  • Support streaming responses for real-time interaction.

Tools

Tools provide agents with capabilities to interact with data and external systems:

  • Corpora Search: Query your Vectara corpora with semantic search.
  • Web Search: Access current information from the internet.
  • MCP Tools: Integrate with external services through the Model Context Protocol (MCP).

Sessions

Sessions maintain the state of conversations:

  • Track all interactions (also known as events) within a conversation.
  • Preserve context across multiple turns.
  • Enable multi-turn reasoning and follow-up questions.

Instructions

Instructions guide agent behavior using Velocity templates:

  • Define the agent's persona and objectives.
  • Customize responses based on context.
  • Support dynamic variable substitution.

Getting Started

To build your first agent:

  1. Create an agent: Define the agent's name, description, and available tools.
  2. Configure tools: Set up corpus access permissions and any external integrations.
  3. Write instructions: Create templates that guide the agent's behavior.
  4. Test with sessions: Start conversations and iterate on your configuration.

Platform Benefits

  • Rapid Development: Build sophisticated AI applications without managing infrastructure
  • Enterprise Security: Role-based access control and audit trails
  • Scalability: Handle thousands of concurrent conversations
  • Flexibility: Customize every aspect of agent behavior
  • Integration Ready: Connect with existing systems through APIs and connectors