AI glossary
Plain-English definitions for the terms people keep hearing.
You do not need to memorize these words. You only need enough understanding to make better decisions when using AI.
Basic AI terms
- AI
- Software that can perform tasks that usually require human-like reasoning, language, pattern recognition, or decision support.
- Generative AI
- AI that creates something new, such as text, images, summaries, plans, or code.
- Model
- The system behind the AI. A model is trained on patterns and uses those patterns to respond to requests.
- Prompt
- The instruction or question you give to an AI system.
- Output
- The result the AI gives back.
- Context
- The information the AI has available while answering or working on a task.
- Training
- The process of building a model by exposing it to large amounts of information.
- Inference
- The moment when a trained model is used to produce an answer or result.
- Hallucination
- When AI gives an answer that sounds confident but is wrong, unsupported, or invented.
- Grounding
- Giving AI specific information to work from, so its answer is tied more closely to real sources or documents.
Agent terms
- AI agent
- An AI system that can take steps toward a goal, not just answer a single question.
- Workflow
- A repeatable set of steps for getting work done.
- Tool
- Something an agent can use to complete a task, such as reading a file, checking a calendar, searching information, or preparing a draft.
- Action
- Something the agent does as part of a workflow.
- Approval
- A point where the user must say yes before the agent continues.
- Human in the loop
- A design where the person stays involved in important decisions instead of handing everything to the AI.
- Autonomy
- How much the agent can do on its own before it needs the user.
- Record
- A clear history of what happened during a workflow.
- Permission
- What the agent is allowed to see or do.
- Guardrail
- A limit that keeps an AI system from doing something unsafe, unwanted, or outside its purpose.
Local and cloud terms
- Local-first
- A design where work happens on the user's own computer whenever possible.
- Local model
- An AI model that runs on the user's own machine.
- Cloud model
- An AI model that runs on outside servers.
- Private data
- Information that should be handled carefully, such as business documents, client information, health information, financial details, credentials, or personal messages.
- Token
- A small piece of text that an AI model reads or produces. AI services often measure usage by tokens.
- Token cost
- The cost created when an AI service charges based on how much text is processed or produced.
- Routing
- Choosing which AI model or system should handle a task.
- Encryption
- A way of protecting information so it cannot be read without the right key.
Information and search terms
- Index
- A prepared map of information that helps software search through files or documents more quickly.
- Embedding
- A way of turning text into numbers so software can compare meaning.
- Vector database
- A database designed to search by meaning, not just exact words.
- Retrieval
- Finding relevant information before answering or doing a task.
- RAG
- Short for retrieval-augmented generation. It means the AI looks up relevant information first, then uses that information to produce a better answer.
OOMU terms
- OOMU Community Edition
- The open-source version of OOMU for individuals, builders, researchers, and small teams.
- OOMU Enterprise
- The version of OOMU for organizations that need deployment, access, visibility, security, and controls.
- Visual workflow
- A workflow the user can build and understand through visible steps.
- Local-first work
- Routine AI work that happens on the user's own computer whenever possible.
- Approval step
- A moment where OOMU stops and asks before continuing.
- Clear record
- A plain history of what OOMU did during a workflow.
- Cartridge
- A packaged set of workflow instructions, knowledge, and settings for a specific kind of work.
- Connector
- A way for OOMU to work with another app, file source, or service.
- GitHub repo
- The public place where the OOMU Community Edition source code can be viewed and improved.
Closing
The goal is not to make every user speak like an AI engineer.
The goal is to give people enough language to understand what the product is doing, ask better questions, and use AI with more confidence.
That is part of trust, too.