---
schema_version: "1"
id: 1fdd582842ba4ee15e9995140f100380a8ab38cbde9376ba2bcd3d8e6cae7b44
title: Glossary
collection: developer
version: current
locale: en-us
portal_url: https://docs.salesforce.com/developer/current/en-us/salesforcedx/einsteinfordevs/guides/files/einstein-glossary.md
canonical_url: https://developer.salesforce.com/docs/platform/einstein-for-devs/guide/einstein-glossary.html
source_site: developer.salesforce.com
content_type: documentation
content_hash: 95e634508df57f1594cb9e811e145ce272a0b5c5316307155e70bd719a2de8db
products:
  - Agentforce Vibes Developer Guide (Deprecated)
  - salesforcedx
---
# Glossary

This glossary defines generative AI terms that appear throughout the Agentforce documentation.

**generative pre-trained transformer (GPT):** A family of language models developed by OpenAI that are generally trained on a large corpus of text data so they can generate human-like text.

**grounding:** The process used to inject domain-specific knowledge and customer information into the prompt.

**human in the loop (HITL):** A model that requires human interaction.

**intent:** A user’s goal for interacting with the AI assistant.

**large language model (LLM):** A language model consisting of a neural network with many parameters trained on large quantities of text.

**prompt:** A natural language description of the task to be done. An input to the LLM.

**prompt management:** The suite of tools used to build, manage, package, and share prompts, including the prompt templates and the prompt template store.

**prompt template:** A string with placeholders/tags that can be replaced with custom values to generate a final prompt. The template includes the hyperparameters associated with that prompt and your choice of model/vendor if you're not using default values.

**prompt chaining:** The method to select the right prompt engineering, which is a break-up of complex tasks into several intermediate steps, and then tie it back together in the hope that the AI generates a more concrete, customized, and thus better result. To get the best prompt, use the “Retry” option to regenerate code.

**semantic retrieval:** A scenario where a large language model uses all the knowledge that exists in a customer's CRM data. Each CRM user has access to a personalized generative AI.

**mcp(model context protocol):** An open standard that provides a universal, two-way connection between AI models, particularly large language models (LLMs), and external data sources and tools.