Microsoft Edge
DevTools
A Microsoft Edge engagement focused on AI‑driven in‑browser features, including real‑time content simplification, alongside integrated developer tooling and structured feedback systems.
In Detail
This engagement formed part of Microsoft's "Web We Want" initiative, which focuses on strengthening the relationship between developers and browser vendors in collaboration with the World Wide Web Foundation and W3C‑aligned stakeholders.
Working closely with external stakeholders and industry leaders, I helped identify and prioritise opportunities for exploration within the browser, shaping a roadmap of experiments and MVPs to improve both developer feedback loops and the wider browsing experience.
To support that work, I assembled and led a small external engineering team responsible for turning selected ideas into practical demonstrations and early‑stage implementations. My own hands‑on focus was on the developer tooling strand, helping define and deliver new capabilities integrated directly within Microsoft Edge DevTools.
In a subsequent engagement at Microsoft's Redmond campus three years later, I returned to work with stakeholders on further experimentation into AI applications within the browser runtime. A key prototype explored real‑time analysis of web pages, intelligently identifying and removing distracting or non‑essential elements to improve clarity, focus, and usability without requiring changes from site authors.
Together, these engagements formed part of a broader programme of exploratory work within Microsoft Edge, investigating how the browser could better support both developers and end users, several years before AI‑assisted browsing experiences became increasingly common across the industry.
AI‑Assisted Content Simplification
A prototype exploring how AI could operate directly within the browser to improve clarity and focus by interpreting and restructuring live web pages in real time.
The system analysed page structure and content to identify non‑essential or distracting elements, including adverts, overlays, and visual noise, and removed or suppressed them without requiring any changes from the site itself. This resulted in a cleaner, more readable experience, demonstrating how intelligent systems could augment the browsing experience at runtime rather than relying on upstream optimisation.
In‑Browser Developer Tooling
A set of in‑browser tools my team and I developed within Microsoft Edge DevTools to create a direct and structured feedback channel between developers and browser teams. Rather than relying on external issue trackers or fragmented reporting mechanisms, this approach embedded feedback capture directly into the developer workflow.
The tooling enabled developers to raise issues in context, preserving relevant page state and reducing friction in reporting. AI‑assisted analysis was used to help classify and enrich submissions, improving signal quality and making feedback more actionable at scale.
Developer Feedback Pipeline
My team and I developed a structured feedback pipeline connecting in‑browser developer tooling to internal Microsoft systems, transforming ad hoc reports into actionable product signals. Issues raised within DevTools were captured with contextual metadata, enriched through automated classification, and routed into triage workflows to help browser teams identify and prioritise real‑world problems.
The Outcome
Across two engagements with Microsoft Edge, my work took ideas from early exploration through to working prototypes and developer tooling, combining hands‑on engineering with technical leadership and collaboration across the organisation and the wider web community.
These projects explored ways for the browser itself to play a more active role for both developers and end users, from creating a more direct feedback channel between developers and browser teams to experimenting with AI‑assisted browsing within the browser runtime itself.
- "
I initially worked with John Kavanagh at Style.com where we built an e‑commerce site for Condé Nast. We built numerous versions of the site for prototypal purposes and finally went live with a version that contained the majority of work from John and his team. Always punctual, proactive and willing, he's definitely one to have in any development team. Since then we went on to work together again at HSBC where we built a number of key React components. He's a great team player who takes a lot of pride in his work, I'd highly recommend him."
- "
John Kavanagh is one of the most professional developers I have worked with. Add to this a synergy between some of the values which Underwired holds in high regard (perfectionism, creativity in all skillets and future facing) and you have someone I wouldn't hesitate to recommend for front‑end development work."
- "
Worked with John Kavanagh on a big Nando’s project, moving a legacy site off of Drupal and onto Vercel and Next.js.
His work and attitude are both stellar! Highly recommended."
- "
John Kavanagh is an incredibly talented and efficient developer with great expertise in Gatsby and Contentful. He is incredibly personable and also always willing to share his knowledge. I also appreciated his ability to communicate openly and in a way that allowed me to find a way forward with him.
It was a pleasure to work with John and I would welcome another opportunity to work with him again!"
- "
John Kavanagh was undoubtedly the best UI developer on the programme (often carrying the burden of his team) and played a crucial role in rebuilding the look and feel of the bank's global online platforms. John was always articulate, willing to speak his mind, helpful and always did an amazing job ‑ he clearly takes immense pride in his work (and rightly so!). His attention to detail and perfectionist attitude helped produce a product that we could be proud of, despite the extremely difficult environment we had to work in.
John would suit any senior or lead UI developer roles and I would have no hesitation in recommending him."
