# Apply Technique: Hybrid AI Development: Use Claude for Architecture and Codex for Execution
## What This Is
This technique combines two different AI coding assistants to improve software development. Use the Claude AI for high-level planning and complex code refactoring, similar to a senior architect, and use the Codex AI for writing and debugging smaller, specific pieces of code. This 'hybrid' approach leverages the unique strengths of each AI to deliver better results faster.
Source: https://www.youtube.com/watch?v=smMC1W-Mjt4
## 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://www.youtube.com/watch?v=smMC1W-Mjt4) 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
- Define a complex development task suitable for a hybrid AI approach, such as 'Refactor the authentication module to support OAuth2' or 'Build a new real-time analytics dashboard'.
- Invoke a Claude-based agent with the defined task. Instruct it to generate a high-level architectural plan, including file structures, function signatures, API contracts, and data models. Save this output to a PLAN.md file.
- For each component outlined in PLAN.md, invoke a Codex-based agent. Provide the specific function signature and requirements from the plan, instructing it to generate the implementation code and integrate it into the file structure.
## 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