Skip to main content

Coding Agent Engineering: From Prompt to Graph

A useful Coding Agent starts with a prompt, but reliable repository work quickly becomes a larger engineering problem. The system must choose context, retain the right information, expose capabilities, control permissions, iterate against feedback, and coordinate work that no longer fits inside one local loop.

This page is the map for AI Coding Club's Agent Engineering tutorials. It is organized by responsibility, not by product and not as a mandatory course ladder.

If the Loop and Graph terminology brought you here, start with Loop Engineering vs Graph Engineering. The article explains why Agent count, local feedback loops, and graph topology are different design dimensions.

The main layers

LayerThe question it ownsStart here
PromptWhat do I want the model to do now?Prompt Engineering 101
ContextWhat information should enter this task?The Power of Context — foundation lesson
MemoryWhat should persist, and what should expire?Coding Agent Memory
InstructionsWhich repository rules should always apply here?AGENTS.md Guide
Skills and toolsWhich reusable procedures, event controls, and external connections are available?Claude Code Skills, Hooks, and MCP
HarnessHow are context, tools, permissions, memory, execution, and verification assembled around the model?Coding Agent Harness Explained
LoopHow does one bounded unit of work improve through feedback and know when to stop or escalate?Coming next: Loop Engineering Guide
GraphHow do work units exchange state, run serially or concurrently, veto actions, and govern goal changes?Coming next: Graph Engineering Guide

The layers are related, but they do not replace one another. Better context does not remove the need for a Harness. A Graph does not replace the Loops inside it. Adding more Agents does not automatically create a Graph.

Assurance across every layer

Some responsibilities cut across the whole stack:

Observability and Eval-Driven Development will join this assurance layer in later tutorials.

Where to begin

  • New to AI-assisted coding: begin with Prompt and Context.
  • Already using terminal Agents: continue through Memory, Instructions, Skills, and Harness.
  • Designing unattended or multi-step systems: continue with Loop and Graph as those practical guides become available.

The durable question is not which new label wins. It is which responsibility your system has made explicit—and which one is still hidden inside the Agent's behavior.