Colour tokens

Ground

ground

#F8F4EC

ground-alt

#F0EAD8

ground-deep

#E5DCC8

Ink

ink

#1C1208

ink-mid

#3D2C18

ink-muted

#7A6548

ink-ghost

#B8A88A

Amber -- the marigold flower

amber

#C07A0A

amber-mid

#A86308

amber-deep

#7A4400

amber-lt

#FDE9B8

amber-pale

#FEF5DF

Forest -- oak leaf

forest

#2D5016

forest-mid

#3D6B20

forest-lt

#C8DFB0

Wood -- walnut to oak

wood-dark

#2C1810

wood-mid

#5C3420

wood-oak

#8B5E3C

wood-lt

#C49A6C

Typography

Display slogan

Knewave
clamp(3rem, 9vw, 6rem)
leading-tight

Marigold ⚘

Hero body

EB Garamond 400
text-md / leading-base

Model weights are the fat layer. Workflows are thin clients over a shared substrate. The eval is the task specification.

Section head

EB Garamond 600
text-xl / leading-snug

All computation is model inference.

Pillar head

EB Garamond 600
text-lg / leading-snug

Inference API

Body copy

EB Garamond 400
text-base / leading-base

Typed operations over self-hosted open-weight models. One container image, one EFS weight cache, per-model isolation. The marginal cost of adding a model falls with each one added.

Section label

Trebuchet MS
text-xs / tracking-widest
uppercase

What runs on it

Amber label

Trebuchet MS
text-xs / tracking-widest
uppercase / amber

Private model hosting. Workflows. Evals.

Pillar number

Trebuchet MS
text-xs / tracking-wide
amber

01

Italic body

EB Garamond 400i
text-base / leading-base
Used for emphasis within prose

Syntactic compatibility and semantic compatibility are separate concerns. The system enforces the former and is silent on the latter.

Components -- light ground

Buttons

Tags

img2txt instruct tts image-embed text-eval text-similarity

Ornament divider

⚘   ◆   ⚘

Pillar grid

01

Inference API

Async, typed, multi-modal. Text, image, audio, depth.

02

Workflow execution

Declarative YAML pipelines. Workflows are thin clients.

03

Evals

The eval is the task specification. Data plus labels plus model.

Cards

Document Q&A

Extract, answer, and embed document content in one pipeline.

img2txt instruct

Accessibility audio

Alt-text and audio descriptions in multiple languages from one image.

img2txt tts

Components -- dark panel (wood-dark)

Tags on dark

img2txt instruct tts

Typography on dark

Production AI pipelines
done properly.

Model weights are the fat layer. Workflows are thin clients. All computation is model inference.

Pillar grid on dark

01

Prototype

Validate AI concepts rapidly in realistic conditions.

02

Production

Secure infrastructure and robust cloud deployment.

03

Scale

Optimise for growth and operational reliability.

Decorative patterns

Section header strip -- amber rule

Section border -- oak dash

Both patterns are CSS-only. The amber strip marks top-of-page and major section breaks. The oak dash marks sub-section boundaries where a full rule is too heavy.

Core vocabulary in use

These phrases should recur across product copy, articles, and documentation. See TERMINOLOGY.md.

Model weights are the fat layer.

Value and generality sit in the weights, not in the applications above them. The foundation model is infrastructure.

Workflows are thin clients.

An application that calls a model does not own the capability it is using. It is a declaration of intent over a shared substrate.

The eval is the task specification.

The labelled dataset is the formal statement of what "correct" means for a pipeline. Not a downstream quality gate -- the primary artefact of any engagement.

All computation is model inference.

No regex branches, no hard-coded rule sets, no custom classifiers. Every decision in a pipeline is the output of a model that can be inspected, replaced, or retrained.

Data plus labels plus model equals evals.

The compact form. Useful as a pull-quote or a sentence that stands alone. Avoid writing it as a formal equation outside technical contexts.