Lexicon
The map of notions
Read the map bottom-up: everything rests on the model, everything is decided in the organization. Blue lines connect what builds on what; red dashes flag the terms mistaken for one another.
IV · The organization
How people work with it: the team.
- AssistantAI in an advisory posture: it answers when asked, one request at a time, and the human keeps their hands on the wheel between steps. Most enterprise usage starts here.
- Human oversightThe organization of control when AI does the work: who checks what, at which moments, with what power to stop. It is what turns a delegation into measured trust.
- Agentic workflowA business process redesigned so that agents own entire steps of it, under defined oversight, rather than a chat bolted onto the side of the existing process.
III · Orchestration
How you put it to work: the workshop.
- HarnessThe working environment built around an AI model: its tools, its access rights, its rules and its guardrails.
- AgentAn AI model allowed to chain actions toward a goal (act, observe the result, correct) instead of answering once and stopping.
- Agentic loopThe cycle that turns AI from talk into action: act, observe the result, correct, repeat, until the goal is reached or the blockage is acknowledged.
- ToolA capacity for action the harness puts in the model's hands: search the web, read a file, write to the CRM, trigger a payment. Without tools a model talks; with them, it acts.
- MCPAn open standard acting as a universal socket between models and your systems: instead of one custom integration per tool and per product, one common socket everyone knows how to plug into.
II · Access
How you talk to it: the counter.
- APIThe counter through which one piece of software talks to another. For AI, it is the channel your products and internal tools use to send requests to the model, on demand, billed by the token.
- TokenThe model's unit of account: a fragment of text worth about three quarters of a word on average. Everything is measured in tokens: document length, limits, and the bill.
- Context windowEverything the model has in front of it when it answers: your request, the documents provided, the history of the exchange. Whatever is not in it does not exist for the model.
- PromptThe brief you give the model: the request, the context, the constraints and the expected format. The quality of the answer is largely decided by the quality of that brief.
- InferenceThe moment the model works: it receives a context and produces its answer, token by token. Every request is one inference, and each one has a cost.
I · The model
What gets trained: the engine.
- LLMThe engine: a statistical model trained on vast amounts of text, able to produce language. It is the thing every generative-AI product puts to work.
- Frontier modelA model from the most advanced generation of the moment, the one pushing the frontier of what AI can do, at a training cost only a handful of players can afford.
- Open weightA model whose weights are published: anyone can download it and run it on their own machines, without ever holding the full recipe of how it was made.
- WeightsThe billions of numerical parameters adjusted during training: the very substance of the model. Whoever holds the weights file holds the model.
- TrainingThe manufacturing phase of a model: months of computation over vast amounts of data to adjust its weights. It happens once, and it is what costs fortunes.