Agentic Coding

A step beyond code completion, agentic coding lets an AI agent take multi-step actions—reading files, running tests, fixing errors, and committing changes—with the developer reviewing at checkpoints rather than writing every instruction. Tools like Claude Code and Cursor’s Composer operate in this mode. Agentic coding accelerates complex tasks but requires clear goals, sandboxing, and human review to avoid unintended side effects.

Related terms

Wireframer

Framer's AI-powered feature that generates layout wireframes from text descriptions, accelerating the design process. Wireframer quickly explores structural options before committing to detailed design. Use generated wireframes as starting points for customization.

Workshop

Framer's collaborative design environment enabling multiple team members to work simultaneously on projects. Workshop facilitates design reviews, handoffs, and team alignment. Use workshop features for feedback and collaborative iteration.

AGENTS.md

AGENTS.md is a project instruction file that gives AI coding agents task context, workflow rules, and constraints so agent behavior aligns with team standards.

Agent Skills

Agent Skills are modular capability definitions that package domain-specific guidance, tools, and patterns for recurring agent tasks.