Agent vs Workflow Explainer
Interactive browser visualization of LLM agent loops and workflows
Visit tdu-naifen.github.io ↗What is Agent vs Workflow Explainer?
An interactive educational tool that demonstrates how LLM agents and workflows operate differently. Users can watch agent loops execute step-by-step in their browser, seeing how agents think, generate tool calls, and act iteratively until completing a task, versus how workflows follow fixed predetermined pipelines. The site includes runnable examples like tool-using agents, autonomous search, RAG pipelines, and safety patterns.
Built with WebGPU for in-browser execution, the tool lets you load Gemma 4 locally to observe real agent behavior. The maker built it using Claude Code.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Agent vs Workflow Explainer automatically. Evidence: HN post: "Decided to spawn a /goal command on Claude code and made this.". View source.
Similar vibe-coded apps
#6 this week523 free lessons building AI systems from math and first principles
A 25 cm open-source biped robot trained with reinforcement learning
Project-based course on building reliable AI coding agent environments
Learn AI coding by building real products, from zero to shipped
Visualize agent loops with local LLM inference and token-level transparency
C. elegans brain simulation steering a language model in your browser
Interactive climate simulation built from first-principles physics