Beyond LLMs: Getting Started with Jev for AI Agents
Jev is emerging as a new approach to decision-making inside AI systems. While LLMs are powerful for generation and reasoning, not every step in an agent workflow necessarily needs a large language model.
So where does Jev fit? What is it actually designed to do? And when would you use Jev, an LLM, or both?
In this free live webinar, Jaime Buelta will break down the fundamentals of Jev and show how it can fit alongside LLMs, tools, and other components of an AI agent.
Rather than focusing only on what Jev is, the session will help you understand the architectural decisions behind using it and where it could be useful in real agent workflows.
What You’ll Learn
What Jev is and the problem it is designed to solve
How Jev differs from LLMs in the way it approaches decisions
When to use Jev, an LLM, or a combination of both
Where Jev can fit within a modern AI agent architecture
Practical use cases for Jev in agent workflows
How Jev can work alongside models, tools, and agent logic
A practical demonstration of Jev within a simple agent workflow
What to explore next when moving from Jev experiments to more complete agentic systems.
Who Is This For?
This session is designed for:
Software and Python developers exploring AI agents
AI/ML engineers interested in new agent architectures
Developers already building with LLMs who want to understand where Jev fits
Claude Code, Codex, LangGraph, and MCP users exploring the wider agent stack
Anyone who has been hearing about Jev and wants a practical explanation of what it actually does
You don’t need prior experience with Jev. A basic understanding of LLMs and AI agents will help, but the session will start with the fundamentals.
Jaime will walk through a simple agent scenario and show where Jev and an LLM play different roles, helping you see how the two approaches can complement each other rather than treating Jev as a replacement for LLMs.
By the end of the session, you’ll have a clearer understanding of what Jev is, where it fits, and when it might make sense to use it in an AI agent.
Meet Your Instructor
Jaime Buelta is a software architect, developer, author, and long-time Python practitioner.
His work spans Python development, software architecture, automation, microservices, and building scalable software systems. He is the author of Packt titles including Python Automation Cookbook and Python Architecture Patterns. His latest work around Python automation also covers AI models, MCP integrations, and the creation of AI agents.