AI pair programming
AI pair programming is the practice of working alongside an AI coding assistant (Claude, Copilot, Cursor, Continue) as a continuous collaborator on coding tasks — suggesting completions, generating tests, explaining unfamiliar code, drafting refactors. Unlike human pair programming, the AI partner is available continuously, scales across timezones, and doesn't tire — but lacks long-term context about the team's conventions and the project's history.
Adoption data through 2025 shows AI pair programming is now the dominant assistance pattern for individual engineers, with measurable productivity effects strongest for routine tasks (boilerplate, test writing, syntactic transformations) and weakest for high-judgement work (architecture decisions, performance debugging). The practice changes the skill mix expected of engineers: less time on typing, more time on prompting, reviewing, and integrating AI output. Anti-patterns observed in deployed teams: accepting AI suggestions without reading them (introduces subtle bugs that compound); using AI to generate tests for AI-generated code (tests pass against the bug); skipping code review for AI-authored changes. Healthy pattern: AI generates, engineer reviews, human reviewer approves — the AI is a junior pair, not a senior one.
Related terms
- AI code review
AI code review is the use of large language models to review pull requests automatically — flagging bugs, suggesting improvements, checking for security issues, enforcing style.
- Pair programming
Pair programming has two engineers at one workstation, alternating between driver (typing) and navigator (reviewing, suggesting, thinking ahead).
- Prompt engineering for software teams
Prompt engineering for software teams is the discipline of writing prompts that consistently produce useful output from LLMs in engineering workflows — code generation, test authoring, PR review, technical writing.