Human-in-the-loop
Human-in-the-loop is an operating model where people validate, correct, or approve AI outputs before final execution.
Optical Alignment
Design
Adjusting element positions based on visual perception rather than mathematical precision, making designs feel balanced. Optical alignment acknowledges that geometric centering doesn't always look centered to human eyes. Fine-tune alignments manually when mathematical precision creates visual imbalance.
Approval Modes
AI
Approval Modes are policy settings that control which operations an agent can run automatically and which require explicit human approval.
AI-Assisted Development
AI
A broad category covering any workflow where AI tools—from inline autocomplete to autonomous agents—collaborate with developers. The human retains control over architecture and review while AI handles repetitive patterns, boilerplate, and first drafts. AI-assisted development spans a spectrum from single-line suggestions to full feature generation, and is closely related to vibe coding, code completion, and agentic coding.
AI Pair Programmer
AI
An AI model integrated into a developer’s editor that participates in the coding process like a human pair—suggesting next steps, flagging potential bugs, explaining unfamiliar APIs, and generating boilerplate. GitHub Copilot popularized the term. Unlike agentic tools, an AI pair programmer typically acts reactively as the developer types rather than planning multi-step tasks autonomously.