# Apply Technique: Anthropic's 10-Step System Prompt Architecture
## What This Is
This guide details a professional method for writing instructions for an AI, known as a system prompt. By using a structured 10-step framework, you can define the AI's role, rules, and output format to ensure it behaves consistently and accurately in a business application, leading to more reliable results.
Source: https://aimaker.substack.com/p/the-10-step-system-prompt-structure-guide-anthropic-claude
## Before You Start
Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)
Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?
## Source Access Note
The source URL (https://aimaker.substack.com/p/the-10-step-system-prompt-structure-guide-anthropic-claude) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.
## What to Implement
This is an **AI Technique** — a pattern or methodology for working with AI models.
- Explain how this technique applies to my current project and what benefit it provides
- Implement it in a way that fits my existing codebase — suggest concrete files to modify or create
- If it requires specific model capabilities (structured output, function calling, etc.), verify my current provider supports them
- Show me a working example I can test immediately
## Additional Context
- Scan the current workspace for files containing system prompts, such as agent configurations (e.g., `CLAUDE.md`, `mcp.json`), prompt template files, or API calls that set a `system` parameter.
- Select a key system prompt from the user's project and analyze its structure. Report which of the 10 Anthropic framework elements (Role, Context, Task, Examples, etc.) are present or missing, and suggest improvements for clarity and robustness.
- Refactor the selected system prompt to explicitly include the missing structural elements, such as adding a `## Role` section, providing `## Examples` in XML tags, and defining an `## Output Format` section. Present the revised prompt to the user for review.
## Reference Implementation
```
|Element|Purpose|Example|
|-------|-------|---------------|
|**Role**|Establishes identity|"You are a coding expert specializing in front-end HTML/CSS."|
|**Context**|Provides background|"User prefers concise responses with UI suggestions."|
|**Input Data**|Supplies query data|"Process this website component description."|
|**Output Indicator**|Defines format|"Return HTML/CSS only in Markdown; no explanations."|
```
## Guidelines
- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it