Model

What it means

A model is a packaged set of learned weights and settings that maps prompts plus context to generated text, classifications, or tool calls.

Why designers should care

Model choice affects UX constraints: context limits, multimodal support, tool use, refusal behavior, and how often users see hallucinations or latency spikes.

Example

A “fast draft” mode uses a smaller model for instant outlines; “deep analysis” switches to a larger model with a progress indicator and higher quality bar stated in the UI.

Common mistakes

• • Promising parity across models without disclosing tradeoffs.
• • Changing models silently and breaking user workflows that depended on tone or format.
• • Ignoring model-specific failure modes in error copy and recovery flows.

Related terms

• Large Language Model (LLM): An LLM reads a sequence of tokens (words and symbols) and generates the next tokens, producing paragraphs, code, JSON, or tool requests from natural-language instructions.
• Inference: Each user request triggers inference: tokens in, tokens out, optionally interleaved with tool calls and retrieval.
• Fine-Tuning: Additional training (full or lightweight) on your labeled data so the model’s default behavior skews toward your product’s patterns.
• Latency: Network, queue, retrieval, tool calls, and generation length all add wait time before users can read, edit, or act on output.
• Token: Models process and bill text as tokens; a rough rule is ~¾ of a word per token in English, but code and symbols can consume more.