Not Every Other Dashboard

Design Intelligence for AI-built interfaces

The Frame

"Design a healthcare dashboard."
Now anyone can ask.

Developers can hand an AI that one prompt and get something usable. But expertise, not the ask, decides whether the result looks like every other dashboard on the internet — or like your vision.

The whole question this deck resolves: generic, or yours?

The bundle answers with seven named design advisory agents.

This isn't a vague promise. The Design Intelligence bundle ships seven design advisory agents — each a real agent file with a distinct, verifiable size.

Real expertise exists. So why does the AI still go generic?

Left to itself, the AI category-matches.

Ask for a healthcare dashboard and it researches other healthcare dashboards — then returns a "competent remix of existing work." Low innovation, because it inherits the category's assumptions.

To break out, research itself has to change.

Ask
"Design a healthcare dashboard"
Research
Other healthcare dashboards
Output
Competent remix of existing work
Innovation
Low — inherits category assumptions

Purpose-driven research pulls patterns from unexpected sources.

Instead of copying the category, the bundle prescribes a 20% category / 50% purpose-driven / 30% divergent blend — extracting Level 3–4 interaction and cognitive patterns, not just visual ones.

Fresh-but-grounded. But what keeps that judgment consistent?

20%
Category
50%
Purpose-driven
30%
Divergent
3–4
Pattern level (interaction / cognitive)

Every agent is anchored in explicit named frameworks.

Taste is stated and shared, not improvised. Agents reason through the Nine Dimensions and Five Pillars, so advisory judgment stays consistent and defensible.

Grounded judgment sets the bar. Now — who enforces it?

Nine Dimensions

Style · Motion · Voice · Space · Color · Typography · Proportion · Texture · Body

Five Pillars

Purpose · Craft · Constraints · Incompleteness · Humans

A silent three-layer design-check self-corrects before you see it.

Quality stops being a hope. design-check validates the work against the design system — hardcoded colors, wrong spacing, missing states, AI-fingerprint patterns — as silent agent self-correction.

Which is why the payoff feels like magic.

  1. Static Analysis — hardcoded colors, wrong spacing
  2. Structural Analysis — missing component states
  3. Visual Analysis — AI fingerprint patterns

You never see a report. You see finished work that already passes.

The 9.5/10 standard is enforced silently before the work ever reaches you. What's left is the part only you can do — the final 5%.

The bar is cleared quietly, and the result is still yours.

The system delivers
Work that already passes the 9.5/10 standard
You add — the final 5%
Purpose · Values · Cultural meaning
The Takeaway
"AI handles execution; you provide sensibility. The system ensures quality; you provide meaning."

The machine enforces the standard as a process; you supply the sensibility that makes it not every other dashboard.

Sources

Sources & Research Methodology

Primary source: colombod/amplifier-bundle-design-intelligence-enhanced (fresh gh clone: origin = colombod, upstream = anderlpz fork; README install line references microsoft/amplifier-bundle-design-intelligence).

Feature status: Phases 2.0–2.3 marked Complete (bundle.md version 2.3.0); phase 3.0 Feedback Planned, not shipped.

Timeline: initial commit 2025-12-23; latest 2026-05-20; 49 commits (git rev-list --count HEAD). Single git tag v2.1.0 despite bundle.md declaring v2.3.0.

Research performed:

Gaps: No quantitative benchmark proving output empirically reaches 9.5/10 was found — 9.5/10 is an explicit design standard/target repeated across docs, not a measured result. The 20/50/30 blend and Level 3–4 patterns are documented prescriptions, not measured outcomes. Canonical org attribution (colombod vs anderlpz vs microsoft) could not be independently disambiguated beyond git remote output.

More Amplifier Stories