Skip to Content
Welcome to the new Evolvable AI docs! đź‘‹

Agents

Overview

An Agent is an AI assistant that handles conversations. Each agent is configured with a language model, custom instructions, knowledge sources, tools, and safety rules.

Creating an Agent

  1. Open an agency from the Agencies page.
  2. In the Agents tab, click New Agent.
  3. Fill in the configuration tabs and click Save.

Configuration Tabs

General Info

FieldDescription
NameDisplay name of the agent.
AvatarOptional image for the agent.
DescriptionShort description of what the agent does.
ModelThe LLM used for responses (selected from configured models).
Custom InstructionsSystem prompt defining the agent’s behavior and persona.
Start MessageOpening message the agent sends when a conversation begins.
Max TokensMaximum tokens per response.
TemperatureControls response randomness (0 = deterministic, higher = more creative).
RAG EnabledWhether the agent uses uploaded documents as context.
Options EnabledEnables structured option buttons in responses.
Events EnabledAllows the agent to emit and respond to events.

Knowledge

Assign document tags to the agent. The agent will use documents with matching tags as context for responses (RAG). Go to Knowledge to upload and tag documents.

Actions

Configure automated actions the agent can trigger during a conversation.

Tools

Attach OpenAPI tools to the agent. These are external API endpoints the agent can call as part of its reasoning (function calling). Tools are defined in Settings → OpenAPI Tools.

Workflows

Attach Workflows the agent can trigger. When the agent determines a workflow should run, it invokes it as part of the conversation.

Integrations

Connect the agent to external messaging platforms:

  • Slack — Deploy the agent as a Slack bot.
  • WhatsApp — Deploy the agent as a WhatsApp bot.

Memory

Configure persistent memory for the agent. Agents with memory can recall facts across conversations.

Guardrails

Assign Guardrails to the agent. Guardrails are checked on every message (prompt phase) or response (response phase) to enforce content safety rules.

Evaluations

View and manage evaluation runs for the agent to assess response quality.

Testing an Agent

Click the Playground Chat button on the agent page to open a chat interface and test the agent’s responses directly.

Last updated on