Sources

Initial Sources

Primary Organising Source

• Andrew Ng, DeepLearning.AI, The AI Engineering Skills Map in The Batch (2026).
• Andrew Ng, writing overview and detailed follow-up on building and deploying AI applications (2026).
• Andrew Ng, AI Engineering Skills Map: Building and Deploying AI Applications (2026).
• Petra Heck, Fontys University of Applied Sciences, Competences for the AI-Augmented Software Engineer (2026).
• Martínez-Fernández et al., Software Engineering for AI-Based Systems: A Survey, ACM Transactions on Software Engineering and Methodology (2022).

This knowledge base recognises Andrew Ng and DeepLearning.AI as the source for the four-area AI Engineering Skills Map and for the detailed Area 1 emphasis on building and deploying AI applications. The more detailed concept structures for software engineering fundamentals, coding agents and shaping the build are a reasoned extension for this site, not a claim that Ng or DeepLearning.AI authored, reviewed or endorsed every page.

Supporting Sources

• OpenAI, Codex best practices.
• OpenAI, Custom instructions with AGENTS.md.
• OpenAI, Customization: project guidance, skills, MCP and subagents.
• OpenAI, Subagents.
• OpenAI, Codex configuration reference.
• OpenAI, Evaluation best practices.
• Anthropic, Claude Code overview.
• Anthropic, How Claude remembers your project.
• Anthropic, Create custom subagents.
• Google Cloud, Gemini Code Assist agent mode overview.
• Google Cloud, Use Gemini Code Assist agent mode.
• Google Cloud, Gemini Code Assist code customization overview.

Source Maintenance Note

The field changes rapidly. Tool-specific configuration and product behaviour should be dated and periodically verified against primary documentation. The conceptual distinction between problem shaping, AI application behaviour, software quality and agent-assisted implementation is intended to remain more durable.