Token

What it means

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.

Why designers should care

Design for limits: character counters, summarization steps, file chunking, and honest messaging when context is trimmed, not mysterious cut-off replies.

Example

A research copilot shows “Using 12 of 40 pages from your upload” and offers to focus on selected sections before running analysis, preventing silent truncation.

Common mistakes

• • Unlimited paste areas with no feedback until the model errors.
• • Equating “characters” with model capacity in user-facing help text.
• • Ignoring token cost in agent loops that chain many automatic steps.

Related terms

• Context Window: Everything sent to the model must fit inside the context window; overflow is truncated, summarized, or rejected depending on product policy.
• 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.
• Latency: Network, queue, retrieval, tool calls, and generation length all add wait time before users can read, edit, or act on output.
• Retrieval-Augmented Generation (RAG): RAG = search step + generation step: find chunks likely to contain the answer, inject them into the prompt, then produce a reply grounded in those sources.
• Inference: Each user request triggers inference: tokens in, tokens out, optionally interleaved with tool calls and retrieval.