Agent Graph Engineering, Part 1: The Stack, and Why Each Piece Is There

Description and use

<blockquote> <p><strong>TL;DR</strong> The stack is Python, Pydantic AI for agents, LangGraph for the flow, <a href="https://github.com/huynguyengl99/chanx" rel="noopener noreferrer">chanx</a> for typed streaming WebSockets and a generated frontend contract, OpenTelemetry into a trace store you own, pytest with a mocked LLM for fast tests, and real-model evals for regressions. Business logic stays in a separate service from the agent graph. The single idea holding it together: every boundary in the system is a declared, typed artifact rather than something you hold in your head. This post make

Problem

<blockquote> <p><strong>TL;DR</strong> The stack is Python, Pydantic AI for agents, LangGraph for the flow, <a href="https://github.com/huynguyengl99/chanx" rel="noopener noreferrer">chanx</a> for typed streaming WebSockets and a generated frontend contract, OpenTelemetry into a trace store you own, pytest with a mocked LLM for fast tests, and real-model evals for regressions. Business logic stays in a separate service from the agent graph. The single idea holding it together: every boundary in the system is a declared, typed artifact rather than something you hold in your head. This post make

Outcome

<blockquote> <p><strong>TL;DR</strong> The stack is Python, Pydantic AI for agents, LangGraph for the flow, <a href="https://github.com/huynguyengl99/chanx" rel="noopener noreferrer">chanx</a> for typed streaming WebSockets and a generated frontend contract, OpenTelemetry into a trace store you own, pytest with a mocked LLM for fast tests, and real-model evals for regressions. Business logic stays in a separate service from the agent graph. The single idea holding it together: every boundary in the system is a declared, typed artifact rather than something you hold in your head. This post make

Evidence

Agent Graph Engineering, Part 1: The Stack, and Why Each Piece Is There

Source