Skip to content
AI Engineering Knowledge BaseAI Engineering Knowledge Base

The Four-Area Skills Map

The four areas are:

  1. Building and deploying AI applications
  2. Software engineering fundamentals
  3. Using coding agents
  4. Shaping the build

Ng presents these areas as mutually reinforcing. AI applications contain probabilistic components, so reliable engineering requires strong software foundations, disciplined evaluation and iterative improvement. Coding agents accelerate implementation, but make specification, architecture, verification and human judgement more important. Shaping the build connects engineering activity to genuine user and organisational value.

The detailed structures for Areas 2-4 in this site are a practical curriculum and knowledge architecture, not a claim that Ng specified each concept.

Cycle

Four Areas Reinforce Each Other

Shape the problem, build the AI capability, engineer the system, and use coding agents to accelerate verified change.

Area 1

Build AI applications

Add model capability, context, grounding, tools, evals and production controls.

Area 2

Engineer reliable systems

Use architecture, testing, security, data and operations to make software sustainable.

Area 3

Use coding agents

Direct agents through bounded tasks, context, tools, permissions and evidence.

Area 4

Shape the build

Turn ambiguous needs into valuable, feasible and responsible interventions.

  1. Shape
  2. Build
  3. Engineer
  4. Agent-assist
  5. Evaluate outcomes