All templates
FeaturedAI#Agent#Beginner#Chatbot#Memory#OpenAI

Build Your First AI Agent

A beginner-friendly interactive AI agent with conversation memory — type a message and get context-aware replies.

Workflow at a glance

The full canvas, before you import it

Click any node to see its config.

#Agent#Beginner#Chatbot#Memory#OpenAI

Click a node to select it — same as the Heym editor; the panel shows its settings.

3 nodes · Free & source-available

Build Your First AI Agent

The simplest way to get a conversational AI agent running in Heym. Type a message, the Agent replies, and conversation history is preserved across turns so every follow-up stays in context.

What this workflow does

  1. YourMessage — type any question or command
  2. ChatAgent — processes your input with a helpful assistant persona and built-in memory
  3. AgentReply — surfaces the final answer

Use cases

  • Learning how Heym Agent nodes work before adding integrations
  • Prototyping a chatbot before wiring it to Telegram, Slack, or a web channel
  • Exploring prompt engineering with a live feedback loop

Setup

  1. Open the ChatAgent node and connect an OpenAI-compatible credential.
  2. Edit the system instruction to change the persona, language, or domain focus.
  3. Run the workflow manually from the editor — type your message in the YourMessage node and click Run.

Notes

  • The Agent node keeps a rolling conversation buffer across manual runs in the same session.
  • Swap GLM-4.7 for any OpenAI-compatible model in the Agent node model dropdown.
  • To add Telegram or Slack as the trigger, replace YourMessage with a TelegramTrigger or SlackTrigger node.

How to import this template

  1. 1Click Import → Copy JSON on this page.
  2. 2Open your Heym and navigate to a workflow canvas.
  3. 3PressCmd+V/Ctrl+V— nodes appear instantly.
  4. 4Add your API keys in the node config panels and click Run.
More workflow templates
View all templates
Heym
incident analysis · production AI
Observed across 100s of AI rollouts

AI workflows don't fail because of prompts.
They fail because of orchestration.

symptom · glue code01
5 tools
Scripts, vector DB, approval bot, tracing, browser runner — none of them talk.
symptom · visibility02
~0%
Observable behavior across the stack. Debugging is guesswork.
with heym · one runtime
1 canvas
Agents, RAG, HITL, MCP, traces & evals. Self-hosted. Observable.
AI-Native RuntimeProduction-Grade
github.com/heymrun/heym