home/roleplay/prompting-system-readme

PROMPTING SYSTEM README

GPTClaudeGemini··▲ 645 copies·updated 2026-07-14

prompting-system-readme.prompt

<sub>🧭 **Navigation:**</sub><br>
<sub>[Home](../../../README.md) | [Vision LLM Theory](../../../VISION_LLM_THEORY_README.md) | [Local Testing](../../../local_testing/LOCAL_TESTING_README.md) | [Deployment UI](../../ui/DEPLOYMENT_UI_README.md) | [Deployment](../../DEPLOYMENT_README.md) | [CDK Stacks](../../stacks/STACKS_README.md) | [Runtime](../../runtime/RUNTIME_README.md) | [S3 Files](../S3_FILES_README.md) | [Lambda Analyzers](../../lambdas/LAMBDA_ANALYZERS.md) | 🔵 **Prompting System**</sub>

---

# 📝 Prompting System Architecture

This document explains the design principles, structure, and rationale behind the modular prompting system used by all analyzers.

## 🎯 Core Design Principles

### 1. 🧩 Separation of Concerns

Prompts are decomposed into discrete, single-purpose files rather than monolithic prompts. This enables:
- 🔄 Independent iteration on specific aspects
- ♻️ Reuse of common components across analyzers
- 🧪 Easier testing and debugging
- 👥 Clear ownership of prompt sections

### 2. 🏗️ Composition Over Inheritance

The system composes final prompts from multiple files at runtime:

when to use it

Community prompt sourced from the open-source GitHub repo aws-samples/sample-badgers (Apache-2.0). A "PROMPTING SYSTEM README" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.