Zing Forum

Reading

Jido Phoenix: Deep Integration Practice of Real-Time Web Interfaces and AI Agent Frameworks

jido_phx is a Phoenix LiveView application that demonstrates the capabilities of the Jido agent framework. It achieves real-time UI synchronization and LLM-driven human-AI collaborative workflows through a signal-driven agent architecture, providing an excellent example for building interactive AI applications.

Jido框架Phoenix LiveViewAI代理实时协作人机工作流Elixir信号驱动状态机LLM工作流
Published 2026-04-29 06:44Recent activity 2026-04-29 09:54Estimated read 4 min
Jido Phoenix: Deep Integration Practice of Real-Time Web Interfaces and AI Agent Frameworks
1

Section 01

Introduction / Main Floor: Jido Phoenix: Deep Integration Practice of Real-Time Web Interfaces and AI Agent Frameworks

jido_phx is a Phoenix LiveView application that demonstrates the capabilities of the Jido agent framework. It achieves real-time UI synchronization and LLM-driven human-AI collaborative workflows through a signal-driven agent architecture, providing an excellent example for building interactive AI applications.

2

Section 02

Background: What Kind of Interface Do AI Agents Need?

Most current AI agents exist in the form of command lines or APIs. Users interact with them via text prompts, wait for responses, then proceed to the next round of dialogue. This model works for simple tasks but falls short for complex workflows—such as multi-step approvals or human-AI collaborative creation.

What we need is an interface that can reflect agent status in real time, support human-AI collaboration, and visualize workflows. This is exactly what the jido_phx project aims to demonstrate: how to deeply integrate AI agent frameworks with real-time web technologies.

3

Section 03

Project Overview

jido_phx is a Phoenix LiveView-based application that demonstrates the core capabilities of the Jido agent framework. It includes two main examples:

  1. Real-Time Counter: Demonstrates signal routing and state management
  2. PRD Generation Workflow: Demonstrates multi-agent collaboration and human-AI approval processes
4

Section 04

Technology Stack

Layer Technology Choice
Web Framework Phoenix 1.8 + Phoenix LiveView 1.1
Agent Framework Jido 2.0
LLM Client req_llm 1.0
Database PostgreSQL via Ecto
Frontend Styling Tailwind CSS
Build Tool esbuild
HTTP Server Bandit

This technology stack reflects the modern best practices of the Elixir ecosystem.

5

Section 05

Core Concept: Signal-Driven Agents

The core abstraction of the Jido framework is the "Signal". Agents do not directly respond to function calls; instead, they coordinate by sending and receiving signals. This model offers several advantages:

6

Section 06

Loose Coupling

Agents do not directly depend on each other; instead, they communicate via a signal bus. Adding new agents or modifying existing ones does not affect other components.

7

Section 07

Observability

All signal flows are traceable, facilitating debugging and auditing. The system can record the complete signal history and reproduce the agent decision-making process.

8

Section 08

Real-Time Synchronization

Phoenix PubSub allows signal changes to be pushed to all connected clients instantly, enabling true real-time collaboration.