KlicForge documentation
Build, configure and operate AI agents for your business — guides for everyone from first-time users to developers integrating KlicForge.
KlicForge lets you build AI agents that answer questions, capture information and take actions across chat channels — configured from a dashboard, without writing code.
What do you want to do?
Create an AI agent
Build, ground, test and publish your first agent.
Connect a channel
Put your agent on your website, Telegram or WhatsApp.
Integrate KlicForge
Embed the widget SDK, connect your own tools, or wire up an MCP server.
Manage your organization
Members and roles, plans, usage and security.
Troubleshoot an issue
Work through common problems by symptom.
Understand usage
How KlicForge counts interactions against your plan.
The core ideas
An agent is the unit you build and deploy. It combines:
- Knowledge sources — your content, so it answers from your material rather than guesswork.
- Skills — instruction modules shaping how it behaves.
- Tools — functions it can call to look things up and take actions.
- Data tables — structured storage it can read and write during a conversation.
- Guardrails — safety controls enforced by the runtime, not just requested in a prompt.
You then put it in front of people on a channel, test it with evaluations, and let it reach out with scheduled tasks.
New here?
Start with the quickstart for the short version, or create your first agent for a full walkthrough.
Unsure what a word means? The glossary lists KlicForge's terms alongside the names they are commonly called elsewhere.