# Lamina Glossary

> Canonical definitions for terms used across Lamina — generative media for agents, creative APIs, MCP, brand DNA, virtual try-on, and adjacent concepts.

Canonical page: https://uselamina.ai/glossary

## Terms

- [Agent-callable API](https://uselamina.ai/glossary/agent-callable-api) — An agent-callable API is one designed to be invoked by an autonomous LLM agent rather than a human developer. It exposes typed tool schemas, returns structured outputs an agent can parse, supports idempotency keys for safe retries, and handles long-running jobs through streaming or polling instead of blocking.
- [Brand Kit](https://uselamina.ai/glossary/brand-kit) — A brand kit is the structured representation of a brand — palette, typography, voice, do/don't rules, reference shots, and product fidelity constraints — that an agent attaches to every run. It anchors generative outputs in a known visual identity so the same brief produces brand-consistent assets across channels.
- [Brief](https://uselamina.ai/glossary/brief) — A brief is the natural-language prompt plus structured parameters passed into a creative app. Briefs describe what to make ("linen tee on weathered teak, north light, 35mm") and how to constrain it (variants, ratios, models). Combined with a brand kit and a seed, the same brief produces a deterministic run.
- [Creative API](https://uselamina.ai/glossary/creative-api) — A Creative API is a developer interface that wraps multiple generative models, brand context, evaluation, and distribution behind a single endpoint. Instead of calling raw model endpoints — Sora, Veo, FLUX, Runway — directly, you call a creative app like productShoot or virtualTryOn and the API handles routing, evaluating, and delivering the result.
- [Creative App](https://uselamina.ai/glossary/creative-app) — A creative app is a reusable, named generative-media workflow — productShoot, virtualTryOn, brandFilm — that bundles model routing, prompt scaffolding, brand context, and output formatting into a single callable unit. You call apps, not models, so the same call survives a model upgrade and produces consistent on-brand outputs.
- [Generative media for agents](https://uselamina.ai/glossary/generative-media-for-agents) — Generative media for agents is the category of image, video, audio, and 3D APIs designed to be called by autonomous AI agents — not humans clicking a UI. They expose tools through MCP, return structured outputs an LLM can parse, and tolerate retries, long jobs, and failure modes only an agent encounters.
- [Idempotent generation](https://uselamina.ai/glossary/idempotent-generation) — Idempotent generation is the property that the same generative-media call — same brief, brand, seed, and idempotency key — returns the same result on retry instead of producing a new (and billed) output. It's a survival requirement for agents, which retry on timeout and would otherwise create duplicate runs.
- [MCP server](https://uselamina.ai/glossary/mcp-server) — An MCP server is a process that exposes tools, resources, and prompts to an LLM client over the Model Context Protocol — Anthropic's open standard, donated to the Linux Foundation in December 2025. MCP servers let agents in Claude, Cursor, Windsurf, and VS Code call your API as native tools.
- [Modality](https://uselamina.ai/glossary/modality) — A modality is the type of media a model produces: image, video, audio, 3D, or text. Generative-media platforms route a single brief across multiple modalities — for example, a still hero image and a 9:16 reel from the same brand kit — without rewriting prompts for each one.
- [Run](https://uselamina.ai/glossary/run) — A run is one execution of a creative app — a single call with a brief, a brand kit, and parameters that produces one or more media assets. Every run has an id, a phase stream (queued → composing → rendering → done), and an evaluation score against the attached brand rubric.

## Related

- [HTML index](https://uselamina.ai/glossary)
- [Use cases](https://uselamina.ai/use-cases) · [Integrations](https://uselamina.ai/integrations) · [FAQ](https://uselamina.ai/faq)
- [llms.txt](https://uselamina.ai/llms.txt) · [llms-full.txt](https://uselamina.ai/llms-full.txt)