Skip to main content

Analysis of Websites using Generative AI - compare poltical websites usability



Image created using DALL-E - love the bad spelling

I want to explore using Generative AI to explore and compare websites. So I used using Google Gemini because of it its ability to work easily with websites.I choose UK three political party websites purely to compare like with like.


Prompt 1:Analyse the following webpages website 1 https://www.conservatives.com/ , website 2 https://www.libdems.org.uk/  and website 3 https://labour.org.uk/ from a web user's perspective. For each website produce a report containing 2 tables. The first Table list issues with the site; for each issues provide at least three examples and then provide a list of potential solutions. Table 2 strengths of the site with each strength provide at least three examples. Add in any commentary

Results
It produced two tables per website and provided a summary comparing them at the end. Direct political statements were not produce.



Now trying out personas and testing the website the politics side not filtered out

Promopt

Persona 1: 55 year old mechanical engineer, has worked 20 years in industry and 15 years as a lecturer in a small University. Persona 2: 67 year woman recently retired as a district nurse. Persona 3: 18 year old poltics student in their first year at University. For each persona decided which of the website suit them best


Results 

Persona 1: Match to https://www.conservatives.com/  largely because of suspected political leanings.

Persona 2: Match to https://www.libdems.org.uk/ largely because of suspected political leanings.

Persona 3: Match to https://labour.org.uk/ largely because of suspected political leanings.


Change the prompt now: 

Repeat the exercise but base the decision completely on the usability of the websites

Persona 1: 55-year-old mechanical engineer

Best-suited website: The Conservative Party website.

  • Reasoning: The Conservative Party website is generally well-organized and easy to navigate. Its clear structure and straightforward language make it accessible to a wide range of users, including those who may not be tech-savvy.

Persona 2: 67-year-old retired district nurse

Best-suited website: The Liberal Democrats website.

  • Reasoning: The Liberal Democrats website also has a user-friendly design, with clear navigation and easy-to-read text. Its focus on accessibility features, such as large text options and high-contrast themes, may be particularly beneficial for older users like Persona 2.

Persona 3: 18-year-old politics student

Best-suited website: The Labour Party website.

  • Reasoning: While all three websites have a relatively user-friendly interface, the Labour Party website may be slightly more appealing to younger users due to its more modern design and use of social media integration. Its emphasis on visual content and interactive elements could also make it more engaging for this demographic.

It is interesting that the two matched. Now let's see if we can get it produce an examples how the other websites can appeal to other personas.

Using the personas for the websites not suggested for each persona, provide a list of ways the websites could be improved to attract the other personas. The solutions suggestions are purely based on user experience not political leanings of the personas.


improving Website Usability for Unsuitable Personas

Conservative Party Website (for Persona 2 and Persona 3)

  • Persona 2 (retired district nurse):

    • Accessibility: Ensure the website is fully accessible to users with disabilities, including those with visual impairments or mobility limitations.
    • Healthcare focus: Highlight the party's healthcare policies and initiatives, emphasizing how they address the needs of older adults and those with chronic health conditions.
    • Community engagement: Provide information about the party's local community outreach programs and how individuals can get involved in volunteering or advocacy efforts.
  • Persona 3 (politics student):

    • Youth-focused content: Create a dedicated section or blog for young people, featuring articles, videos, and interactive content related to issues that matter to them.
    • Student resources: Offer resources for students, such as information on scholarships, internships, and career advice.
    • Social media engagement: Increase the party's presence on social media platforms that are popular among young people, such as Instagram and TikTok.

Liberal Democrats Website (for Persona 1 and Persona 3)

  • Persona 1 (mechanical engineer):

    • Economic policy: Provide more detailed information about the party's economic policies, including its stance on taxation, investment, and infrastructure.
    • Business engagement: Highlight the party's support for businesses and entrepreneurs, showcasing examples of successful businesses that have thrived under Liberal Democrat policies.
    • Technology and innovation: Address the importance of technology and innovation in driving economic growth and creating jobs.
  • Persona 3 (politics student):

    • Youth-focused content: Similar to the Conservative Party website, create a dedicated section or blog for young people, featuring articles, videos, and interactive content related to issues that matter to them.
    • Student resources: Offer resources for students, such as information on scholarships, internships, and career advice.
    • Social media engagement: Increase the party's presence on social media platforms that are popular among young people, such as Instagram and TikTok.

Labour Party Website (for Persona 1 and Persona 2)

  • Persona 1 (mechanical engineer):

    • Economic policy: Provide more detailed information about the party's economic policies, including its stance on taxation, investment, and infrastructure.
    • Business engagement: Highlight the party's support for businesses and entrepreneurs, showcasing examples of successful businesses that have thrived under Labour policies.
    • Technology and innovation: Address the importance of technology and innovation in driving economic growth and creating jobs.
  • Persona 2 (retired district nurse):

    • Healthcare focus: Highlight the party's healthcare policies and initiatives, emphasizing how they address the needs of older adults and those with chronic health conditions.
    • Community engagement: Provide information about the party's local community outreach programs and how individuals can get involved in volunteering or advocacy efforts.
    • Accessibility: Ensure the website is fully accessible to users with disabilities, including those with visual impairments or mobility limitations.



Fun to play with these, not sure I think the phrase unsuitable personas in the last example :-)


All opinions in this blog are the Author's and should not in any way be seen as reflecting the views of any organisation the Author has any association with. Twitter @scottturneruon The comments produced by the generative AI are also not the opinions of the Author and are provided for illustrative use only.

Comments

Popular posts from this blog

Using an LLM to Find Themes using Thematic Analysis in an Academic Career

B rief recap In an earlier post, “Same prompt, four AIs: why answers aren’t always the same” , I looked at what happened when the same prompt was given to four different LLMs. Unsurprisingly, perhaps, the answers were not identical. That raised an interesting follow-on question: what was the prompt actually trying to do? The answer is that it was trying to support a form of thematic analysis. In that case, the object of analysis was an academic profile, including my Google Scholar profile. The version I discuss here is a modified prompt, used with Claude.ai, where I uploaded a CV and asked the system to find other appropriate public resources connected with a named person and institution. The aim was not simply to summarise the CV, but to identify visible and less visible themes across a whole career. Why use thematic analysis? Thematic analysis is widely used by academics, especially in qualitative research. Braun and Clarke’s well-known paper, Using thematic analysis in psy...

Prompt Engineering, Context Engineering and Agentic AI in Higher Education: A Short Briefing

AI in Education Prompt engineering, context engineering and agentic AI are often used interchangeably, but the literature treats them as distinct. Prompt engineering concerns crafting effective single instructions to a model (Glean, 2026). Context engineering is the broader discipline of designing and managing the entire informational environment around a model—memory, retrieval, tool outputs and conversation state—rather than a one-off instruction (Abstracta, 2026); prompt engineering operates within the context window, while context engineering determines what fills it (arXiv:2606.12422, 2026). Agentic AI describes systems that plan and execute multi-step tasks with delegated autonomy, raising organisational questions of accountability rather than purely technical ones (MIT Sloan, 2026; Palo Alto Networks, 2026). There is genuine debate about prompt engineering's durability. IEEE Spectrum (2025) reported research suggesting prompting is increasingly performed by models themse...

AI as a Mirror: Transforming Vague Student Ideas into a More Rigorous Project Agreement

The Problem: The "Generic App" and the "Time Sink" We’ve all been there: a student walks into a 1-to-1 with a vague desire to "do something with AI" or "build a fitness app." You spend 45 minutes trying to find a technical "hook" that justifies a Level 6 or Level 7 grade, only for the student to drift back into "CRUD app" territory by week three. The Philosophy: AI as a Mirror Instead of you doing the heavy lifting, this workflow uses AI as a Mirror . It reflects the student’s own skills and career goals back to them, but with the structural rigour of a virtual supervisory team. It’s not about the AI "giving" the idea; it’s about the AI forcing the student to defend and refine their own concepts until they hold water. The Framework: 3 Months of Rigour This prompt is specifically designed for intensive/conversion MSc or summer capstone projects . It assumes a tight 12-week implementation window. By forcing the AI to w...