Build from the why — not from a stale brief

Notes, highlights, personas, journeys, user tests, tables, and files — one linked evidence layer.

A persistent store of facts, constraints, and decisions the AI always considers.

Dated outcomes with an owner, a priority, and a status — with the activities and to-dos that deliver them underneath.

See the whole plan as an outline, a month calendar, a gantt timeline, or the people doing the work.

Every version can say why it changed, what prompted it, and which source is behind it.

Pages, features, content, menus, and sitemaps — each with a stable ID and a documented why.

Build a page's structure as a tree of features and content — then view it on your live site.

Model navigation and information architecture with a visual IA map editor.

Model what exists and how people discover it — then place that model on a page.

Context-aware answers from your own graphs — with citations, not vibes.

Press Start and the Research and Experience agents seed both graphs from your sources.

Pick Fast, Sharp, or Capable per project — a dial for how hard the Agent thinks.

Break a goal down into milestones, activities, and to-dos — reviewed in a preview before any of it is saved.

AI drafts, you decide — answers and generations never overwrite your work.

Your assistant asks Crux why a page exists — and writes research, structure, and plans back into it.

Scan a live site into experience entities, and track which are synced to code.

Score a live page against a cited usability benchmark — findings land in the research graph.

Private by default; share projects with your organisation when the team needs them.

Shared org workspaces with pooled projects, credits, and centralised billing.

Transparent, metered AI usage with monthly allowances per plan — no surprise bills.

PII auto-redaction, prompt-injection blocking, no model training, strict tenant isolation.