Skip to main content

Agents

What you'll learn
  • The two types of agents in AutoTalk: LLM agents and flow-based bots
  • When to use each type

Agents are automated assistants that handle conversations on your behalf. AutoTalk supports two types:

  • LLM Agents use large language models to generate dynamic, context-aware responses. They can understand context, call tools, and adapt to different situations.
  • Flow-based bots (like Typebot) follow pre-designed conversation scripts with buttons, menus, and branching logic.

LLM Agents vs. Flow-Based Bots

FeatureLLM AgentsFlow-Based Bots
Response styleDynamic, generatedPre-scripted
Setup complexityModerateVisual drag-and-drop
FlexibilityHigh — adapts to any questionFixed — follows defined paths
Best forSupport, sales, complex queriesSurveys, menus, simple flows
Tools & actionsYes — can call APIs, query dataLimited

Typebot (Flow-Based Bots)

Typebot is an open-source visual chatbot builder. You design conversation flows using a drag-and-drop editor with blocks for messages, questions, conditions, integrations, and more.

Setting up a Typebot bot

  1. Build your chatbot flow in the Typebot editor.
  2. In AutoTalk, go to Automations > Agents and click "Add new agents".
  3. Enter a Name for the bot.
  4. Select typebot from the Assistant Type dropdown.
  5. Configure the connection fields that appear (such as your Typebot bot URL or ID).
  6. Set the Log Level as needed.
  7. Save the bot.

When to use Typebot

Typebot is a good choice when:

  • You want a visual, drag-and-drop flow builder
  • Your conversation follows a fixed structure (intake forms, surveys, booking wizards)
  • You want an open-source solution you can self-host
  • Your team prefers designing flows visually rather than writing prompts
tip

You can combine Typebot bots with AI agents. For example, use a Typebot bot for structured onboarding on your website and an AI agent for open-ended WhatsApp support.

Next steps