Cerb videos: Build an AI support agent for your website; self-host with Docker
Check out our latest videos on self-hosting Cerb with Docker and building an AI support agent for your website!
We just posted two new videos on the YouTube channel:
Self-host Cerb with Docker
Cerb automates customer service inboxes and workflows. Code powerful automations in your browser with our KATA language, build interactive AI agents with tools, create personalized or team dashboards, and integrate with nearly any API.
When self-hosting, your first full-featured seat is free forever, anonymously, with no time limit.
The easiest way to get started is with a container platform like Docker. We recommend Docker Desktop for testing on your local machine.
This video provides a step-by-step walkthrough for deploying Cerb as a container using Docker on your own machine. There are also tips for moving into production.
We'll use Caddy as the web server for its simple configuration and automatic LetsEncrypt SSL certificate renewals. We'll use MySQL 8 for the database.
Build an AI support agent for your website
This is a deep dive of the new AI agent functionality in upcoming Cerb v11.1.
We create an agent from scratch using the new llm.agent: command. This gives us interchangeable LLM providers, memory, transcripts, and the ability to add automations as tools in just a few lines of code. The agent can be added to any website with a single script tag.
We build a quick tool for answering visitor questions based on website content and the latest documentation. This example uses our semantic search API, but you can also use search services like Tavily, Linkup, or Exa, to integrate your existing docs.
We review an efficient, agentic search strategy (tools vs. preemptive RAG), and gradually add functionality so you can learn how everything works.
You can follow along with a free, full-featured copy of Cerb in Docker: https://cerb.ai/docs/installation/docker/
Use version 11.1 tag from Docker Hub since these features are currently in beta.