— Door 04 · Capacity, honestly shown

One designer. A content team's throughput.

The honest pitch: AI handles the routine half — first-draft rewrites, readability scoring, metadata, link and consistency checks, content variants — so the human half (plain-language judgement, accessibility decisions, accuracy, public trust) gets all of me. The panel below is an illustrative concept, not live data.

Read the application →
▣ AI does the routine half
  • Draft a first-pass plain-language rewritedrafted
  • Score readability & flag jargonscored
  • Generate metadata & descriptive linkstagged
  • Check consistency against the style guidechecked
  • Produce content variants to testdrafted
♥ The human keeps what matters
  • Does this actually read plainly?human
  • Is it accurate & legally correct?with SMEs
  • Accessibility & inclusion decisionshuman + a11y team
  • Does it serve the whole user journey?human
  • Sign-off & public trusthuman

Workstream

Page → platform

audit → model → uplift

Reading level

Grade 17→6

demonstrated in Door 02

Content types

Reusable

fix the pattern, not the page

Unverified claims

0

the only acceptable number

AI content feed · illustrative

Readability flag

"This page reads at Grade 15 — I've drafted a Grade-6 rewrite and flagged the three jargon terms for your call on a plain-language alternative."

Accuracy check

"Two sentences in the rewrite touch on eligibility rules — flagged for SME confirmation and held out of publish until verified."

Pattern ready

"This page fits the 'task' component — I've restructured it into eligibility → steps → what's next, ready for your edit and the judgement only you can add."

How the engagement runs

Phase 1Audit content against the strategy & Style Manual · pick the high-impact pages
Phase 2Design the content model & components with the team
Phase 3Rewrite · AI drafts, I judge plain language & accessibility
Phase 4Verify accuracy with SMEs · accessibility check with specialists
Phase 5Publish, measure task success & iterate
See the rewrite → See the strategy →

A line I won't blur

AI accelerates content production. It never decides what's true, it never overrides accessibility, and it never substitutes for plain-language judgement. Every public-facing sentence — every eligibility rule, every legal claim — is verified by a human (me) in a tight loop with subject-matter experts and the accessibility team. This dashboard is a concept to show the workflow, not a live system.