HealthAtoms

TOPIC

Glossary terms

37 entries across the knowledge base

Interoperability & Standards
Terminologies & Code Systems
Data & Analytics
AI-Native Systems
Guardrails & safetyThe layers around a model that keep it in-scope, grounded and resistant to manipulation — engineering, not hope.concept · 3 min · practitionerAmbient documentationThe AI scribe: listen to the visit, draft the note — attacking healthcare's documentation burden at its source.concept · 3 min · foundationLLMOps & evalsThe operations discipline for AI features: versioned prompts, automated evals, monitoring and cost control — because 'it seemed fine in the demo' is not a deployment strategy.concept · 3 min · practitionerPrompt engineeringDesigning the input is designing the behaviour: instructions, context, examples and output contracts that make LLMs reliable.concept · 3 min · foundationFederated learningTrain one model across many hospitals without any of them sharing patient data — the model travels, the data stays.concept · 3 min · practitionerAI agents & tool useAn LLM in a loop: reason, call a tool, observe the result, repeat — turning a text generator into a system that does things.concept · 3 min · foundationEmbeddings & vector databasesTurn text into coordinates in meaning-space, then search by closeness — the index that makes semantic search and RAG work.concept · 3 min · foundationRetrieval-Augmented Generation (RAG)Ground an LLM's answer in your own documents: retrieve relevant passages first, then generate with them in context — citations included.concept · 3 min · foundationModel Context Protocol (MCP)The open standard that lets AI assistants plug into tools and data sources — USB-C for the agent era.concept · 3 min · foundation
Software & Tech Stack
Infrastructure & DevOps
IT & Security
IoT & Robotics
Computer Science