Agents and automation
AI that acts, not merely answers. Agents, workflows, orchestration, augmented automation: the operational patterns and their guardrails.
- Agent orchestrationAI agent orchestration is the coordination of several specialised agents, each responsible for part of a complex task, so they collaborate towards a common goal. A central orchestrator (or a supervisor agent) distributes the sub-tasks, supervises their execution, and aggregates the results.
- Agent SkillsAn Agent Skill is a folder containing a SKILL.md file and, where needed, scripts and resources, which teaches an AI agent to perform a task your way. The agent first loads only the name and description, then the detail when the task calls for it. The format, created by Anthropic, is an open standard.
- Agentic AIAgentic AI refers to the ability of an artificial intelligence system to pursue a goal autonomously: it plans steps, uses tools (software, databases, browser) and adjusts its actions based on the results it obtains. Where generative AI produces an answer to a request, agentic AI carries a task through to completion, under a level of human oversight defined in advance.
- Agentic loopThe agentic loop is the iterative cycle of an AI agent that acts, observes the result, and decides on the next action, until it reaches its goal or a stopping criterion. Without limits or observability, it can diverge into an infinite loop and consume in a few minutes the equivalent of several days of normal use.
- AI agentAn AI agent is an autonomous system that combines a language model with external tools to execute multi-step tasks: it analyses a request, plans an action sequence, executes, observes, and adapts its strategy. It differs from an assistant that merely responds.
- AI agent platformAn AI agent platform is an environment that allows enterprises to create, deploy, and operate autonomous AI agents. Three families exist in 2026: developer SDKs (Claude Agent SDK, LangGraph, AutoGen), no-code platforms (n8n, Make, Microsoft Copilot Studio), and self-hosted open-source integrated products (OpenClaw, OpenHands).
- AI workflowAn AI workflow is the structured sequence of several AI inference steps to accomplish a complex task, usually with external tools interleaved. It can be pre-defined (linear chain) or dynamic (orchestrated by an agent), and is the dominant operational mode of mature AI deployments in enterprise.
- Augmented automationAugmented automation is the use of AI to assist a human worker in performing a task, rather than to replace them. The human remains decision-maker and responsible, the AI accelerates, prepares, or validates.
- Autonomous Claude CodeIn autonomous mode, you no longer drive every step of Claude Code: you set a stop condition once, and a check (an evaluator model or a script) verifies it after each turn until the work is genuinely finished. Four levers make this loop automatic: /goal, /loop, /schedule and Stop hooks.
- Claude CodeClaude Code is Anthropic's agentic coding tool, launched in preview in February 2025 and generally available in May 2025. It runs in the terminal, code editors, the desktop app and the browser. It implements an autonomous coding agent that reads, writes, and executes code via the Claude API. To distinguish from the Claude model itself: Claude Code is the tool, Claude the model that drives it.
- CopilotAn AI copilot is an assistant that suggests, proposes, and completes actions to the user, who keeps control of the final decision and execution. It is distinct from the AI agent, which executes autonomously. The copilot is a prudent mode of use, the agent a delegated mode of use.
- Deep researchDeep research is an AI agent feature that autonomously carries out a multi-step search on the web, sometimes in your documents, then writes a report with its sources. It works for a few minutes, where a chatbot answers in seconds. It can still be wrong: its sources must be checked.
- Evidence-based claim resolutionAI claim resolution hands a specialised agent the claims whose outcome depends on a proof: it gets the evidence at the source, verifies it, applies the business rules and resolves the case in the existing tool, never refusing alone, escalating with the proof in hand when the case is doubtful.
- Vibe codingVibe coding is a way of building software by describing what you want to an AI, in everyday language, and accepting the code it produces without reading or understanding it. The term was coined by researcher Andrej Karpathy in February 2025; it suits rapid prototyping, much less applications intended for production.
- Visual AI agentA visual AI agent is an agent that takes the image (photo, video, screenshot, scanned document) as primary input: it perceives visual content, extracts its meaning, decides, then triggers an action in business tools, where a classical agent acts on text alone.