Author's): Eivind Kjosbakken
Originally published in Towards Artificial Intelligence.
Create AI workflows with agent platforms
With the advent of powerful AI models such as GPT-5 and Gemini 2.5 Pro, we are also seeing an increase in the number of agent platforms to leverage these models. These frameworks make working with AI models easier by eliminating many challenges such as tool invocation, agent state handling, and human-in-the-loop configurations.
This article discusses LangGraph, an agentic AI platform that simplifies the creation of AI workflows by solving the challenges of tool usage, state management, and user interaction. Discusses the basics of LangGraph, its advantages including ease of setup and open source availability, as well as some disadvantages such as remaining boilerplate code and specific errors encountered during implementation. Ultimately, it highlights the balance between abstraction and control in creating efficient agentic systems.
Read the entire blog for free on Medium.
Published via Towards AI
