IMC/AI Foundations
01Start HereThe map + Core 10 02What AI Still Gets Wrong11 failure patterns 03All 30 TermsSearch the guide 04What Is an Agent?Agency, tools & autonomy

AI Foundations · A Working Glossary

The vocabulary every AI proposal assumes you already have. Now you do.

Every vendor pitch now leads with "AI." Not all of them mean the same thing by it. This reference breaks down the ten terms that show up most often in health IT procurement and delivery conversations — explained without the sales language, so you can ask sharper questions and evaluate what's actually on offer.

AI–01FOUNDATIONS

Model

The system doing the predicting

A model is the trained system that turns an input into an output — a set of statistical weights learned from data, not a piece of software running hand-written rules.

In practiceWhen a vendor says their platform "uses AI," ask which model, whose data trained it, and where it runs. The answer changes your privacy and procurement posture entirely.
Common mix-upThe model gets treated as the whole product. It's one component — the application wrapped around it does most of the work of making it safe and useful.
Cut through the hype"Powered by advanced AI" usually just means "we call an API."
AI–02FOUNDATIONS

LLM

Large language model

An LLM is a model trained on enormous volumes of text to predict what comes next — the technology behind tools like ChatGPT and Claude.

In practiceAn LLM can draft a stakeholder briefing or summarize a lengthy standards document in seconds — but it has no access to your organization's records unless something connects it to them.
Common mix-up"LLM" and "AI" get used interchangeably. LLMs are one category of AI — strong on language, not inherently strong on math, current facts, or structured data.
Cut through the hype"Our AI understands your business" often means "we fed it your documents."
AI–03MECHANICS

Token

The unit a model reads and writes in

A token is the small chunk of text — roughly a word or part of a word — that a model processes and generates, one at a time.

In practiceVendor pricing and "usage limits" are almost always quoted in tokens, not pages. Worth translating into a real document count before you sign anything.
Common mix-upA token isn't a word or a character — it's somewhere in between, which is why the same document can vary in token count across models.
Cut through the hype"Unlimited AI usage" almost never means unlimited tokens. Check the fine print.
AI–04MECHANICS

Prompt

The instruction that shapes the output

A prompt is the instruction or question given to a model — the input that determines what comes back out.

In practiceThe gap between a mediocre AI-drafted policy summary and a genuinely useful one is almost always the quality of the prompt, not the model behind it.
Common mix-upPeople treat prompting like a search query. It's closer to briefing a fast, literal new analyst — more context and structure produces a better result.
Cut through the hype"Prompt engineering" is a fancier name for writing clear instructions.
AI–05MECHANICS

Context

What the model can see when it answers

Context is the background information available to a model when it responds — prior messages, documents, or data supplied alongside the prompt.

In practiceA model asked about "the migration timeline" with nothing attached will guess. The same question with the actual project plan attached will answer accurately.
Common mix-upContext isn't memory. Most tools don't retain what you tell them once a session ends, unless the product is specifically built to persist it.
Cut through the hype"AI that knows your organization" usually means someone still has to feed it the right documents.
AI–06MECHANICS

Context Window

How much context fits at once

The context window is the total amount of text — prompt, documents, and conversation combined — a model can consider in a single exchange, measured in tokens.

In practiceA short context window means a long RFP or standards document has to be split into pieces. A longer one lets you hand over the whole thing at once.
Common mix-upA bigger window doesn't guarantee even attention to everything inside it — models can still skim past specifics buried in the middle of a long document.
Cut through the hype"Handles massive documents" is worth testing on your actual longest document, not taking on faith.
AI–07CAPABILITY

Reasoning

Working through a problem in steps

Reasoning describes a model working through intermediate steps before producing a final answer, rather than jumping straight to a response.

In practiceFor a multi-step task like reconciling data fields across two systems, a reasoning-capable model is more likely to catch inconsistencies than one that answers in a single pass.
Common mix-upVisible "reasoning" is still generated text, not verified logic. It should raise your confidence, not replace review — especially on anything regulatory or clinical.
Cut through the hype"AI that thinks" means it generates more intermediate text — not that it has checked its own work.
AI–08CAPABILITY

Harness

The scaffolding around the model

A harness is the surrounding software that manages a model's inputs, outputs, tools, and guardrails — the scaffolding that turns raw model output into a usable, controlled product.

In practiceTwo vendors can run the identical underlying model and deliver very different results, because the harness — how it's prompted, constrained, and connected to your systems — is where most of the engineering happens.
Common mix-upBuyers evaluate "the AI" when they should be evaluating the harness — the access controls, audit logging, and failure handling built around it.
Cut through the hype"Proprietary AI technology" often just means "our harness," not a custom model.
AI–09WORKFLOW

Project

A persistent, scoped workspace

In an AI tool, a project is a persistent workspace that groups a set of files, instructions, and conversations together, so the model has consistent context every time you return to it.

In practiceSetting up a project for a specific standards review or vendor evaluation means you're not re-explaining the background every session.
Common mix-upA project isn't the same as fine-tuning a model — it organizes what you feed the model, it doesn't change the model itself.
Cut through the hype"Custom AI for your team" frequently just means a well-organized project, not a bespoke model.
AI–10WORKFLOW

Agent

A model that takes multi-step action

An agent is a system that uses a model to take multi-step action toward a goal — searching, calling tools, and deciding what to do next with limited human input along the way.

In practiceAn agent might be asked to gather status from three systems and draft a summary, deciding on its own which lookups to run — a meaningfully different risk profile from a model that only answers what it's asked.
Common mix-upNot everything marketed as "agentic" actually takes independent action. Some products are still single-step assistants wearing agent branding.
Cut through the hype"Autonomous AI agent" should prompt one direct question: what can it actually do without a human approving each step?

Evaluating an AI-enabled vendor or proposal?

We help health authorities ask the right questions before the contract is signed — not after.

IMC holds no allegiance to any AI platform or vendor, so the read you get on a proposal is independent, grounded in what your organization actually needs.

Start a conversation