analytics-dictionary / tool overview / ai

Claude

Claude is a family of AI models and assistants from Anthropic.

Written by Reflective Data experts · updated Oct 5, 2026

It is used for writing, analysis, coding and as the reasoning engine inside agents, available through chat apps and an API. Anthropic also created the Model Context Protocol.

Teams choose models per task, so many companies work with several AI labs rather than one.

AI agent Large language model (LLM)Model Context Protocol (MCP)

// how we can help

We build company brains, agent harnesses and AI bots on top of data you can trust. AI services → · The data platform behind it

Chunking

Chunking is splitting documents into smaller pieces so they can be indexed and retrieved for AI…

knowledge-graph.md

Knowledge graph

A knowledge graph represents entities and the relationships between them, such as customers, products and orders.

gemini.md

Gemini

Gemini is Google family of AI models and assistant, available across Google products and through APIs.

hallucination.md

Hallucination

A hallucination is when an AI model produces confident but incorrect or invented information.

human-in-the-loop.md

Human in the loop

Human in the loop means a person reviews or approves an AI output or action before…

ai-guardrails.md

AI guardrails

Guardrails are the rules and checks that keep an AI system within safe and intended behaviour.

← full analytics dictionary