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

Subagents are narrowly scoped AI assistants that can be invoked by a primary agent to perform specific subtasks more efficiently.

Slash Commands are user-invoked commands that start with a slash and execute predefined workflows, tools, or agent behaviors.

Agent Memory is persisted context that allows an AI agent to remember preferences, facts, and workflow state across sessions.

An agent handoff is the transfer of context, files, or tasks from one AI agent to another so work can continue without losing project intent.

An agent handoff keeps a workflow moving when a task needs a different tool, model, or specialist. In Framer, this can mean passing site context from a design-focused agent to a coding or CMS-focused agent while preserving the user’s goals and constraints.

An agent workflow is a sequence of AI-assisted steps for planning, editing, reviewing, and shipping work in a digital project.

An agent workflow breaks complex website work into smaller actions such as scanning pages, updating CMS items, improving layout, and reviewing changes. Clear workflows help teams use AI without giving up control over quality or publishing decisions.

An agent guardrail is a boundary that prevents unsafe, unwanted, or inconsistent AI behavior during project work.

Agent guardrails can stop destructive edits, prevent duplicate CMS entries, preserve brand rules, or require review before publishing. They are especially useful when agents work across large websites or shared team projects.

An agent trigger is an event or command that starts an automated AI action, such as updating content or checking a project.

Agent triggers can be manual, scheduled, or connected to outside systems. In a website workflow, a trigger might start a content import, run a QA pass, or ask an agent to update CMS entries after source data changes.