# Definable AI Glossary

> 8 terms covering multi-agent workflows, model routing, RAG, integrations, and AI orchestration.

## All terms

- [Retrieval-Augmented Generation](https://definable.ai/glossary/rag-retrieval-augmented-generation/) — RAG (Retrieval-Augmented Generation) is an AI technique that retrieves relevant information from a knowledge source and uses it to ground the model's response — producing answers backed by your own documents instead of relying only on what the model memorized during training.
- [AI Knowledge Base](https://definable.ai/glossary/knowledge-base/) — An AI knowledge base is a searchable index of your company's documents, databases, and data sources that an AI model can query in natural language — turning static content into an interactive, citable resource.
- [Workflow Automation](https://definable.ai/glossary/workflow-automation/) — Workflow automation is the use of software to execute a series of tasks across multiple apps without human intervention — replacing repetitive manual work with reliable, repeatable processes.
- [AI Agent](https://definable.ai/glossary/ai-agent/) — An AI agent is an autonomous software system that uses a language model to reason about a goal, decide which tools to use, and execute multi-step tasks — operating on behalf of a user without requiring step-by-step instructions.
- [Model Context Protocol](https://definable.ai/glossary/model-context-protocol-mcp/) — Model Context Protocol (MCP) is an open standard introduced by Anthropic in 2024 that lets AI assistants discover and use external tools — like USB-C for AI, providing a universal way to plug models into apps and data sources.
- [Multi-Model AI](https://definable.ai/glossary/multi-model-ai/) — Multi-model AI is the practice of using different language models for different tasks within a single platform — picking the best model for each job instead of locking yourself into one provider's ecosystem.
- [AI Hallucination](https://definable.ai/glossary/ai-hallucination/) — An AI hallucination is when a language model generates information that sounds plausible but is factually incorrect, fabricated, or inconsistent with reality — often delivered with high confidence.
- [AI Credits](https://definable.ai/glossary/ai-credits/) — AI credits are a usage-based currency that AI platforms use to meter consumption — different actions (chat, image generation, video, embedding) consume different amounts of credits, giving users flexibility without per-action billing.

## Related

- HTML glossary: https://definable.ai/glossary/
- Per-term markdown: https://definable.ai/glossary/<slug>.md/
- Workflow: https://definable.ai/workflow/