{"id":27,"date":"2026-09-15T07:43:29","date_gmt":"2026-09-15T06:43:29","guid":{"rendered":"https:\/\/blogs.kent.ac.uk\/aiteam\/?p=27"},"modified":"2026-09-15T10:13:35","modified_gmt":"2026-09-15T09:13:35","slug":"building-a-more-accessible-digital-kent-with-ai","status":"publish","type":"post","link":"https:\/\/blogs.kent.ac.uk\/aiteam\/2026\/09\/15\/building-a-more-accessible-digital-kent-with-ai\/","title":{"rendered":"Building a more accessible digital Kent with AI"},"content":{"rendered":"

\u201cPlease check accessibility.\u201d<\/span><\/b>\u00a0<\/span><\/p><\/blockquote>\n

Jonathan Thirlwell types four words into Codex<\/a>.<\/span>\u00a0<\/span><\/p>\n

The AI opens a set of custom accessibility instructions he has created, examines the website code and starts comparing it with the standards Kent needs to meet. Instead of returning a list of unexplained warnings, it identifies the affected code, relates each problem to the relevant guidance and suggests what the development team can do next.<\/span>\u00a0<\/span><\/p>\n

A task that could involve moving between several testing tools, searching for explanations and tracing each problem through the code now begins with one straightforward request pulling in a ChatGPT Skill.<\/a><\/span>\u00a0<\/span><\/p>\n

The UX team’s accessibility challenges<\/h3>\n

Kent\u2019s websites need to meet the Web Content Accessibility Guidelines (WCAG) at level AA, as well as the University\u2019s own accessibility policies. These standards help make websites usable by as many people as possible, including disabled people.<\/p>\n

Automated checking tools such as Lighthouse<\/a> can help developers spot accessibility problems. But the results are not always straightforward. A failed check may tell the team that something is wrong without showing exactly where the problem is, which accessibility rule applies or how the code should be fixed.<\/p>\n

Checking and fixing these issues is essential, but it can also be repetitive and time-consuming. Changes within the team had left fewer people available to follow up accessibility issues, increasing the risk that routine checks could be missed.<\/p>\n

The UX team also faced a much larger technical challenge. Site Editor, the system used to build parts of Kent\u2019s website, had been created around a decade earlier. Over time, limited maintenance meant that both its code and the other software it relied on \u2013 known as software dependencies \u2013 had become increasingly outdated.<\/p>\n

The team could keep Site Editor running, but making significant improvements had become difficult. Rebuilding it from scratch, bringing in a contractor or rewriting the system in a more conventional way could have taken months and required substantial investment. There was also a risk that a project of that size would never be approved.<\/p>\n

\"\"<\/p>\n

Building a reusable accessibility skill in Codex<\/h3>\n

Jonathan\u00a0began by\u00a0working with Codex to create a reusable accessibility skill: a package of instructions that tells the AI what to examine and how to report its findings.<\/span>\u00a0<\/span><\/p>\n

Rather than\u00a0attempting\u00a0to write those instructions alone, he asked Codex to question him about the team\u2019s requirements. His answers helped shape a skill covering areas such as web content,\u00a0multimedia\u00a0and documents, alongside Kent\u2019s policies and the relevant WCAG standards.<\/span>\u00a0<\/span><\/p>\n

Now, when Jonathan asks Codex to check accessibility, it can:<\/span>\u00a0<\/span><\/p>\n