AI UX Agents and Workflows Glossary
Multi-step AI systems that plan, use tools, and hand off work across people and software until a task is done.
32 terms
- Agents and workflows
A2A (Agent-to-Agent)
A2A (agent-to-agent) communication is when one AI agent delegates tasks, shares context, or negotiates outcomes with another agent instead of only talking to the user.
- Agents and workflows
Action Receipt
An action receipt is a plain-language record of what an agent did, when, and with what permissions—like a bank notification, not a server log.
- Agents and workflows
Agent
An agent is an AI system that plans steps, uses tools, and acts across multiple turns to complete a goal, not just answer a question.
- Agents and workflows
Agentic UX
Agentic UX is the design of interfaces for software that plans and acts on a user's behalf—tools, files, APIs, and multi-step workflows—not only text replies.
- Agents and workflows
Autonomy Slider
An autonomy slider lets users set how independently an agent may act—from suggest-only to draft to execute—often per task or surface.
- Agents and workflows
Background Agent
A background agent (or cloud agent) runs a task outside the active chat—on a remote VM, queued worker, or local process—while the user works elsewhere.
- Agents and workflows
Canvas
Canvas is a dedicated side surface—panel, tab, or split view—where AI output lives as an editable artifact separate from the chat stream.
- Agents and workflows
Claw
In agent tooling, a claw is the reach of an AI orchestrator into your environment: spawning sessions, running commands, editing files, or driving browsers on your behalf.
- Agents and workflows
CLI (Command-Line Interface)
A CLI is a text-based interface where users (or agents) run commands in a terminal instead of clicking through GUI screens.
- Agents and workflows
Composer
The composer is the primary input surface where users assign tasks to AI: type prompts, attach files, pick modes, arm connectors, and send.
- Agents and workflows
Connector
A connector is an integration that lets an AI product read from or write to an external app—email, calendar, Slack, Figma, Stripe, or internal APIs.
- Agents and workflows
Diff / Patch Review
Diff or patch review is the UX pattern where users inspect line-by-line changes an agent proposed—code, copy, config—and accept or reject each hunk before apply.
- Agents and workflows
Fork
Forking in AI chat means branching the conversation or task at a decision point—creating a new path without losing the original thread.
- Agents and workflows
Git
Git is version control software that tracks changes to code and files over time through commits, branches, and merges.
- Agents and workflows
Handoff
Handoff is the structured transfer of context, decisions, and artifacts from one step—or one role—to the next in an AI-assisted workflow.
- Agents and workflows
Harness
A harness is the runtime environment that wraps a model with tools, policies, memory, and orchestration so agents can act inside your product or repo.
- Agents and workflows
Hooks / Automations
Hooks (or automations) are event-triggered agent runs—on save, commit, schedule, or CI signal—that execute predefined skills or prompts without manual chat.
- Agents and workflows
Intent Preview
Intent preview shows what an agent plans to do before it executes—especially for multi-step or irreversible actions.
- Agents and workflows
Loop Engineering
Loop engineering is designing iterative cycles where an AI observes context, acts, checks results, and repeats until a task completes or a human stops it.
- Agents and workflows
MCP (Model Context Protocol)
MCP (Model Context Protocol) is an open standard for connecting AI assistants to external tools, data sources, and services through a shared protocol.
- Agents and workflows
Multitask
Multitask (in AI tools) means running multiple agent jobs in parallel or background—separate threads, files, or repos—without blocking the main conversation.
- Agents and workflows
Orchestration
Orchestration is how an AI product coordinates multiple models, tools, retrieval steps, and human checkpoints into one coherent run.
- Agents and workflows
Plan Mode vs. Agent Mode
Plan mode is when the AI proposes steps, scope, and files before executing; agent mode is when it runs tools and edits immediately within policy.
- Agents and workflows
Project Rules
Project rules are always-on instructions that shape agent behavior for a repo or workspace—often stored as .cursor/rules, AGENTS.md, or team policy files.
- Agents and workflows
Responsive Salience
Responsive salience is when an AI interface automatically increases or decreases oversight UI—explanations, approvals, transparency—based on task risk and user context.
- Agents and workflows
Sandbox
A sandbox is an isolated execution environment where agents run code, browse, or call APIs with limited blast radius—no production data, no unrestricted network.
- Agents and workflows
Subagent
A subagent is a child agent session spawned by a parent orchestrator to handle a subtask—tests, research, lint fixes—while the parent coordinates the overall goal.
- Agents and workflows
Thread / Session
A thread (or session) is a bounded conversation or task run with its own history, memory scope, and artifacts—distinct from other parallel chats.
- Agents and workflows
Tool Permissions
Tool permissions are granular controls for which external actions an agent may perform—read email vs send email, list files vs delete files.
- Agents and workflows
Tool Use
Tool use is when a model invokes external functions (search, calculators, APIs, code runners) to go beyond plain text generation.
- Agents and workflows
Workflow
An AI workflow is a multi-step process that combines prompts, tools, human review, and structured handoffs to reach an outcome, not a single chat reply.
- Agents and workflows
Worktree
A git worktree is a separate working directory tied to the same repository, often on its own branch, so multiple tasks can run in parallel without stashing changes.