AI Basics: The Most Important Terms
Understand key AI terminology like Large Language Models, prompts, and reasoning to learn how AI agents automate tasks with language models and tools
AI agents are more than chatbots. They combine language models with instructions, context, tools, and permissions to get things done in your work environment. This glossary explains the key terms and shows how they work together.
LLM: The Language Model Behind AI
LLM stands for "Large Language Model". An LLM is an AI model that's been trained on massive amounts of text. You give it a prompt and it predicts the probably next word step by step until the answer is complete.
Well-known models come from places like OpenAI, Anthropic, or Google. Provider and model are not the same thing. A provider can offer multiple models with different strengths, speeds, and costs.
Where a model runs doesn't depend solely on the provider. The same model can run in different regions or data centers depending on the provider, for example in the EU or in Germany. This means models can be used in compliance with GDPR independently of their original provider, under certain conditions.
An LLM by itself can generate text. It can't operate tools on its own, take action, or access your project data. That's where the other building blocks come in.
Tip: For simple tasks, a fast and cheap model often does the trick. More complex tasks might need a more powerful model.
Prompt
A prompt is the input you use to give the LLM a task. It can include a question, an instruction, or additional context, for example. The LLM processes this text and generates its answer based on it.
Reasoning
Reasoning refers to an AI model's ability to handle complex tasks across multiple processing steps. The model can analyze information, make connections, and develop a solution step by step.
Depending on the model and configuration, reasoning can be more or less pronounced. This can affect the quality, speed, and cost of an answer.
Stream
Stream refers to the step-by-step delivery of an AI response as it's being generated. Instead of waiting for the complete answer, parts that are already generated are displayed right away.
This means you see initial results sooner, even while the full processing is still running.
Chatbot: Ask Questions and Get Answers
A chatbot is an LLM with a user interface. You type something in, and the chatbot responds in natural language.
Beyond the LLM, a chatbot can have a system prompt and memory. This lets it take on a fixed role or remember information across multiple messages.
The key difference from an agent: A chatbot answers, but it doesn't act on its own. It won't create a task automatically or send an email, for example.
Chatbots are great for tasks where you provide the necessary context directly:
-
Quick text work like rephrasing or creating variations
-
Research for a specific question
-
Summaries of content that you provide yourself
-
Brainstorming and idea checking
AI Agent: AI That Gets Things Done
An AI agent is a configurable digital assistant. It consists of a language model equipped with an identity, instructions, access to selected information, and optional capabilities. This lets it plan tasks, execute multiple steps, and work with its environment.
Unlike a generic chatbot, an agent works within defined boundaries and can take actions on behalf of the user.
The difference is easy to remember:
-
Chatbot: You ask, it answers
-
Agent: You set a goal, it works toward it
An agent can decide on its own what information or tools it needs for the next step. It works in a loop: plan, act, check the result, and continue until the goal is reached. This so-called agent loop runs in a protected environment called a sandbox.
What building blocks make up an agent?
An agent consists of several building blocks that work together:
-
LLM For processing and text generation
-
System Prompt For role, rules, and goals
-
Context For the knowledge the agent needs for the task
-
Tools and MCP So the agent can act and use external systems
-
Skills For repeatable and consistent approaches
-
Memory For stored information over time
-
Trigger So the agent starts on demand, on schedule, or when an event occurs
-
Human in the Loop For defined human approvals at critical points
Important: More autonomy can make an agent more useful. At the same time, the demands on permissions, boundaries, control, and transparency increase.
System Prompt: The Fixed Guidelines
The system prompt is a fixed instruction in the background. It sets what role an agent has, how it should work, and what goal it pursues.
This turns a general language model into a specialized agent. A system prompt can include specifications for role, tone, guidelines, and working methods, for example.
Context: The Knowledge for the Current Task
Context is the sum of all information available to the LLM for a task. This can include your prompt, files, the conversation history so far, or connected tools.
More context isn't automatically better. Relevant and precisely prepared information provides better conditions than large amounts of contradictory or irrelevant data. Plus, every model has a limited context window.
Memory: Stored Context
Memory refers to stored context connected to an agent. It can contain information or earlier interactions that are reused in future conversations.
The difference from regular context: Memory persists across individual tasks or conversations. Not every piece of information needs to be stored permanently.
Skill: Reusable Instruction
A skill is a reusable instruction. It describes how an agent should complete a task according to a specific standard.
For example, an LLM can write code. A skill can additionally define what structure, naming conventions, and tests apply. For an agency, a skill might define how a briefing is checked against their own template.
Skills help with three main things:
-
Consistency The task gets done according to your desired standard
-
Reliability and Efficiency Repeated adjustments and explanations are reduced
-
Reuse and Sharing A skill created once can be used by the team
-
Company-Specific Customization Your own templates, processes, terminology
-
Modular and Expandable New capabilities can be added without changing the core system
Skills extend an agent's abilities without you needing to change its basic configuration.
Skills vs. Tools
-
Tool: What an agent can do, like a web search, for example
-
Skill: The instruction for how it should properly use that capability
Tools and Capabilities: What an Agent Can Use
Capabilities is the umbrella term for the abilities available to an agent. This includes skills, built-in tools, and connectors.
The core principle is: Abilities are granted explicitly, not assumed. You decide which tools, context, and permissions an agent gets. This gives you control over what the agent can and can't do.
Connectors and Connections to Other Systems
A connector establishes the connection to external services or systems. This lets an agent access data or functionality outside of awork.
A connection is a single authenticated identity for that connector.
One connector can have multiple connections.
The connector's connection status and whether it's linked to a particular agent are managed separately.
MCP: The Common Interface for AI
MCP stands for "Model Context Protocol". It's an open standard that connects AI agents to external tools and data sources through a common interface.
Simply put, MCP is like USB-C for AI: a standard that many systems can plug into. Technically, MCP connects a tool's API to the agent. This lets the agent read data or trigger actions without needing a custom integration built for each tool.
MCP is especially relevant when an agent needs to work across multiple systems, like with a project management tool, CRM, or Slack.
Trigger and Scheduled Executions: What Starts an Agent
A trigger determines when an agent becomes active. It can start on demand or be triggered by an event or schedule.
A scheduled execution is for recurring or proactive tasks. An agent can be configured to carry out certain work regularly without you having to start it manually each time.
For example, an agent might react to a new file or run a specific workflow regularly.
Human in the Loop: Human Control at Important Points
Human in the Loop is a deliberately set control point. The agent stops and waits for a human decision before continuing.
You define in advance where this approval is needed. An agent might set a status or prepare a document, while an email to a customer can only be sent after human approval.
The principle is simple: The agent works, humans decide at the critical junctures.
Thread and Run: How Agent Executions Are Documented
A thread is a conversation history with an agent. Threads document the exchange between you and the agent and make it possible to trace earlier conversations. A scheduled agent execution also appears as a thread.
A run is a single execution within a thread. A thread can contain multiple runs. Each run has an owner.
How the AI Building Blocks Work Together
An agent works in a loop.
-
A trigger starts the agent
-
The LLM processes the system prompt, context, and task
-
The agent uses tools or skills as needed
-
The result flows back and the agent decides on the next step
-
At defined points, it waits for a Human in the Loop
-
Relevant information can be retained in memory
That's exactly where the difference between a chatbot and an agent lies: The chatbot generates an answer. The agent can work through a task across multiple steps.
FAQ
What is a Skill?
A skill is a reusable instruction that defines how an agent should complete a task according to a specific standard.
What is MCP?
MCP is an open standard that connects AI agents to external tools and data sources through a common interface.
Why does an agent need a Human in the Loop?
So a human can decide at important points before the agent continues. This lets you deliberately add human approval to critical actions.
What's the difference between a Tool and a Skill?
A tool gives an agent a capability. A skill describes how it should use that capability or complete a task according to a specific standard.
What is a Thread?
A thread is the history of an interaction with an agent. Scheduled agent runs are also displayed as threads.
What is an Agent Run?
A run is a single execution within a thread. A thread can contain multiple runs.
Powered by happysupport.ai