Panaseer Cyber Advisor
From complex security data to intelligent conversations
I led the end-to-end design of Cyber Advisor, a generative AI assistant that transforms how security leaders explore their data, uncover insights, and decide what to do next.
Role: Lead Product Designer
Scope: Discovery, strategy, UX/UI, prototyping and launch
Collaboration: Product, Engineering, Data Science and customers
Technology: Generative AI / LLM
Context and User story: CISOs carry one of the most demanding jobs in any organisation. They face constant threats and relentless pressure to prevent the next breach, and in board meetings they’re expected to answer quick, high-level questions about the organisation’s cyber posture.
Many are business leaders as much as security leaders, balancing risk against budget and explaining cyber posture in terms the business understands. Yet the data they depend on lives in a complex platform built around dashboards, tables and technical metrics. Getting a clear answer usually meant asking a security analyst to pull the numbers and explain them, which took time CISOs didn’t have.
INSPIRATION AND MOTIVATION
For Cyber Advisor, I drew inspiration from the user interviews and prototype testing I ran with CISOs and Data Security Managers. My goal was to empower security leaders to make faster, more informed decisions. CISOs are under constant pressure to keep the business safe, so I was motivated to make their jobs less overwhelming by turning complex data into clear, trusted answers. Through our collaboration on R&D, I saw security teams engage with our AI-powered features and share high NPS scores. That shows me how thoughtful, human-centered design can turn uncertainty into confidence, and it motivates me to keep building not only for our users, but with them.
OPPORTUNITY

Cybersecurity teams had data.
What they needed was a faster way to understand their data.
Security leaders work with enormous amounts of information spread across dashboards, reports and metrics. Finding the right answer often meant navigating multiple views, understanding technical terminology and manually connecting the dots.
I saw an opportunity to change how people interacted with this data.
Rather than making users learn how to navigate the platform, what if the platform could understand what users wanted to know?
The vision was to create an AI-powered experience where security professionals could simply ask questions and receive meaningful answers grounded in their own data.
The design challenge
How might we make complex cybersecurity intelligence accessible through natural language, without compromising trust, accuracy or transparency?
ROLE AND RESEARCH APPROACH
I owned the end-to-end product design, from early discovery and opportunity definition through prototyping, customer validation and launch.
End-to-end
Product design ownership
Cross-functional
Product, engineering and data science
Customer-led
Research and design partners
AI-first
LLM-powered product experience
To understand what would earn their trust, I followed a human-centered design approach and built one feature at a time with our users. (See the Key Drivers feature, which focused on root-cause analysis.)
Designing through the Innovation Lab
I started with people - not prompts. In January 2026, I established the AI Innovation Lab at Panaseer, where for almost six months we experimented with customers on agentic and gen-AI features.
I invited our users into the R&D process so I could learn about their specific pains and needs, and so they could imagine and test how AI could empower their roles. Eventually, I could see a correlation between the collaboration we had and their AI acceptance, as they shared their own ideas with us and even brainstormed AI agents on every page of the complex, data-heavy product - which then became Cyber Advisor.
Learning from their reactions and building alongside them, we noticed that our users wanted to turn tables, numbers, and complex dashboard navigation into a simple natural language interface. They wanted an AI agent to scan all their data and give them the right answer immediately, along with direction on the next steps to remediate their environment. That became Cyber Advisor.

During the research, we noticed that although the experience is familiar and easy to use, a blank prompt box can be intimidating, and users needed a little guidance to get started. To solve this, we added suggested starter questions to the UI, such as “What’s my EDR coverage per BU?”, which lowered the barrier to the first prompt and helped drive adoption even higher.
Designing for trust, not just intelligence
An AI answer is only useful if people can trust it.
In cybersecurity, inaccurate or misleading information can have serious consequences.
I worked closely with data scientists and engineers to establish standards for the AI experience, including:
-
Accuracy: defining response-quality metrics and guardrails, with a reported target of 95% accuracy.
-
Readability: establishing tone-of-voice and Markdown standards.
-
Transparency: making information sources visible.
-
Graceful failure: designing clear responses when the AI couldn't confidently answer.
-
Iteration: using customer feedback to improve the experience.
This work also contributed to the wider design system, establishing standards that could be reused across future generative AI features.
Making innovation repeatable.
Cyber Advisor wasn't just a new feature. It was an opportunity to establish how we approached AI product innovation.
Through the AI Innovation Lab, I helped create a collaborative process involving Product, Engineering, Data Science and customers.
We tested early concepts, gathered feedback and iterated before committing to larger development efforts.
The design partners were able to start using Cyber Advisor within two weeks of launch.
This approach helped us reduce AI feature delivery time by 50% (from four sprints to two). Read more on my LinkedIn post



FROM EXPERIMENTATION TO LAUNCH
From individual AI feature to a unified conversational experience
MetricIQ insights:
Before we developed the Cyber Advisor, we had 3 different gen-AI features on different pages of the product. I set up many feedback sessions after the release to make sure we built not just another AI tool, but the most valuable and accurate features for our customers. MetricIQ is an AI-powered natural language summary of the most important risks so the CISO can focus on taking rapid action to fix them. My key learning was that our users were missing one big thing: continuous prompt interaction. They wanted to ask follow-up questions and go deeper into their data. That insight became the foundation for Cyber Advisor.

Cyber Advisor everywhere:
During research and prototype testing, one of the most common ideas I heard from our users was that they wanted the AI agent to be visible on every page of the UI. Based on that feedback, right after releasing Cyber Advisor, we added a mini window that appears on every page and understands the context of the page it's on, so users can ask questions wherever they are in the product and get super-tailored information in seconds. As an outcome, the adoption of the Cyber Advisor increased across all users.

PRODUCT DELIVERABLE, IMPACT & LEARNINGS
The impact
A new way to interact with cybersecurity intelligence.
The project delivered value at both product and organisational levels.
95% Accuracy Target
Response-quality target and guardrails.
50% Faster Delivery
AI feature delivery was reduced from 4 sprints to 2.
2 Weeks Early Adoption
Design partners using the product within two weeks of launch.
End-to-End Innovation
A repeatable AI product development approach.
Beyond the feature itself, the project helped establish a foundation for future AI experiences through shared quality standards, customer collaboration and a faster innovation process.
Reflection
Great AI experiences start with understanding people, not technology.
Cyber Advisor reinforced something I strongly believe in: the role of product design isn't simply to make technology easier to use, but to make complex things meaningful and accessible.
One of my biggest learnings was the importance of bringing customers into the innovation process early. By involving them in experimentation, we didn't just validate ideas; we built trust, challenged assumptions and discovered opportunities we might otherwise have missed.
It also changed how I think about AI product design. Intelligence alone doesn't create a great experience. Trust, transparency, context and consistency are equally important.
Finally, this project taught me that innovation shouldn't be a one-off exercise. By bringing Product, Engineering, Data Science and customers together, I helped establish a more collaborative and repeatable approach to building AI-powered experiences.
For me, the real success wasn't just launching Cyber Advisor. It was helping shape a new way of thinking, designing and building products.









