Agents

What is an Agent?

An Agent is a self-contained AI entity that perceives user inputs, reasons about goals, and executes actions to complete tasks autonomously. Unlike static APIs or simple chatbots, an Agent can:

  • Chain multiple steps — e.g., read a document, extract data, validate it against rules, and generate recommendations.
  • Persist context across interactions through short-term chat history.
  • Adapt dynamically based on instruction changes, new actions, or external triggers.
  • Delegate work to other Workflows, or external APIs via configurable Actions.

Key Terms Glossary

TermDefinition
OrchestratorThe primary LLM node responsible for intent understanding and action routing.
PlannerAn optional LLM node that decomposes complex requests into a step-by-step sequence of actions. Conversational interaction and parameter collection are handled by the Orchestrator.
FormatterAn optional LLM node that converts raw responses into markdown or other human-readable formats for cleaner, more structured output.
RendererAn optional LLM node that converts raw responses into rich chat output such as interactive forms, cards, charts, and quick replies.
ActionA callable tool (Workflow or API) that the Agent can invoke to interact with external systems.
Strict ModeA per-action flag ensuring the Agent will not invoke that action until every required input parameter has been explicitly provided by the user.
Input SchemaA JSON structure defining what arguments an Action expects. The Agent uses this to extract parameters from the user's message.
Output SchemaA JSON structure defining what data an Action returns.
History ContextThe number of recent conversation turns passed to the Orchestrator as context for each new request.
Chat SessionAn isolated conversation thread in the Builder's test chat. Multiple sessions can be created to test different scenarios.

Was this page helpful?

Need help?

Check our troubleshooting guide or browse frequently asked questions.

© 2026 Vue.AI. All rights reserved.