AI Guides
AI terminology glossary
Align on AI vocabulary before buying or building workflows.
Guide notice
Guides provide decision frameworks and topic overviews. They link to related comparisons, tools, pricing, and benchmarks so you can verify details in context.
Editorial status
Published 2026-07-30 · Last reviewed 2026-07-30 · Next review due 2027-01-26
- Review cadence: Every 6 months
- Verification badge: Verified
- Review status: Current
- Evidence level: editorial
- Content owner: ONULSURI Editorial
Introduction
AI conversations stall when teams use the same words for different ideas. This glossary focuses on practical product and workflow terms used across ONULSURI guides.
Use these definitions as conversation starters, then verify vendor-specific meanings in current documentation.
Shared vocabulary prevents teams from arguing past each other — tokens vs words, agents vs chatbots, RAG vs 'chat with PDF.' Use precise terms in pilots and procurement notes, and treat marketing labels as claims to verify rather than technical guarantees.
Who it is for
- Buyers comparing AI products.
- Teams writing internal AI guidelines.
- Writers and educators explaining AI concepts.
- Enablement leads onboarding non-technical stakeholders to AI projects.
Decision framework
- Prefer operational definitions
Define terms by what users can observe: inputs, outputs, controls, and failure modes.
- Separate product from technique
Distinguish chat products from methods like RAG, prompting, or fine-tuning.
- Confirm vendor language
Check current docs when a vendor reuses a common term with a product-specific meaning.
- Link terms to next actions
After defining a term, point to the related guide that helps you use it.
- Link terms to your stack
Annotate glossary terms with the concrete products and workflows your organization uses.
Comparison overview
Model vs product
A model is the underlying system; a product wraps it with UX, tools, and policy.
Prompt vs system prompt
User prompts are per-task; system or custom instructions set durable behavior.
RAG vs fine-tuning
RAG retrieves evidence at runtime; fine-tuning changes model behavior offline.
Common mistake to avoid
Treating marketing labels as technical guarantees, or using 'AI' as a substitute for naming the job and tool.
Related AI tools
Related compare pages
Related pricing pages
Related benchmarks
Related prompt categories
FAQ
What is a token?
A chunk of text the model processes; usage and context limits are often measured in tokens.
What is an embedding?
A numeric representation of text used for similarity search and retrieval.
What is an agent?
A system that can plan steps and call tools, not only reply with a single answer.
Is this glossary exhaustive?
No. It covers high-frequency terms used in ONULSURI educational guides.
Should every team maintain its own glossary?
Prefer one shared glossary with owners. Team-specific examples can extend it without forking definitions.
Further reading
- LLM basics explained — Start with model fundamentals.
- RAG explained — Deepen retrieval vocabulary.
- Embeddings explained — Understand vector representations.
- AI Guides hub — Browse all educational guides.
Related hubs
- AI Hub — Overview of ONULSURI AI guides and where each section fits.
- AI Compare — Side-by-side comparisons of assistants and tools.
- AI Tool Directory — Category directory and tool overviews.
- AI Pricing — Plan structure and upgrade guidance without fabricated prices.
- AI Benchmarks — Transparent evaluation frameworks and scenario suites.
- Prompt Library — Reusable prompts for coding, writing, and everyday work.