From 0-100 in 3 days with thoughtful AI
The background
The journey begins…
Preparing AI
Building the dashboard
The result
The differentiators
Next?
The background
For years, I've advocated for building dashboards the right way: designing for specific personas, avoiding vanity metrics, choosing appropriate chart types, and preventing cognitive overload. I've written about these principles here and on my blog. For years, despite my best efforts (including one that won the "Visionary Award" in an employers hackathon), I've been disappointed with the released product. Lost vision by stakeholders, corners-cut "MVPs" released but never revisitied due to lack of resources, etc.
I decided to build one myself. There's just one problem: It's just me, and I don't code.
AI to the rescue.
The journey begins…
I knew AI would have to do some of the heavy lifting, but I'd seen plenty of AI-generated dashboards, and most suffered from the same problems:
Cognitive overload.
No clear target persona.
Useless metrics.
Poor data visualizations.
I'm not just using AI. I'm injecting years of UX experience into it in a way that few developers, product managers, security engineers, or even UX designers do. AI is a tool. How you use it makes all the difference.
Preparing AI to build the dashboard
I decided that the best way to get my expertise, methodology, and expertise into Claude, including what to avoid, was to create a fairly complex skill.
I also needed raw data, a design system, and a dashboard design outline with guidelines and guardrails beyond those already included in the skill.
So, before asking AI to build the dashboard, I needed five things:
A dashboard type
A vulnerability scanner dashboard: simple, but with transferable concepts.
A persona
Security Analyst: a common cybersecurity persona, straightforward, and yet one that many dashboards still get wrong.
Data to build the dashboard on
Based on my domain expertise, I started with basic vulnerability scanner output fields, had Claude to fill in any gaps (only 1 field), and it generated constrained dummy data as a CSV file.
A design system
I needed a design system that was not generic AI, avoided cognitive overload, had reserved colors for severities and errors, and was WCAG 2.1 AA compliant.
I provided Claude with curated visual samples, and prompted it to create a design system using my requirements and restrictions.
A dashboard creation skill
I started with my How to Build a Security Dashboard articles and distilled them into a simplified and optimized version. I had Claude optimize the skill again, and give me the .md file.
Building the dashboard
I uploaded the persona file, the CSV containing the scanner data, and the dashboard creation skill to Claude. I also told it to use the design system (which was the only one available anyway).
I provided the project brief, and referenced the uploaded files. After reviewing the key elements, some simple workflows and layouts, and re-iterated the persona's primary objective, I had Claude build the dashboard
The result
See the LIVE, interactive dashboard here!:
A simple workflow example:
I HIGHLY recommend that you skim over the workflow example here before exploring the dashboard, in order to uncover some of its features.
The Differentiators
What makes this dashboard different (by design) from 90%+ of the security dashboards out there?
Prioritization
Users need proper prioritization guidance, not just severity labels.
Get prioritization wrong, and you risk losing your customers' trust. Customers expect YOU to be the expert.
If you can't hire an actuarial scientist to develop a sound prioritization scheme, at least explain how your priority scores are calculated so users can make their own informed decisions. Transparency is key to trust. I had AI develop the scoring model. The dashboard details panels explain it right where users need it.
Here's how my dashboard helps users prioritize:
Start with what needs attention NOW. The first KPI immediately answers the question, "What do I need to do right now?" The others narrow the focus even further.
Explain the prioritization scheme. The methodology is visible right on the dashboard (via a tooltip), and also directly on the details side panel.
KPIs are interactive and actionable.
Highlight the biggest wins. A single fix can sometimes resolve dozens of issues at once. The dashboard surfaces and prioritizes these high-impact, low-effort fixes, something almost no other security dashboard does. We're talking the biggest bang for the buck here!
It doesn't overwhelm. It focuses.
Remediation
Some applications help with remediation; others don't. Some customers want that help, while others don't. And security professionals are understandably wary of granting security tools the permissions they need to make changes automatically.
I wanted to bridge that gap.
Users have the instructions and intelligence they need to fix issues themselves, right from the dashboard.
Users can create a ticket for someone else to handle the fix.
Users may also choose AI-automated remediation.
The things that I would do next if this were a real product
There are a number of things that I would do or suggest if this were a real product. You can find the list of those here.