The Cost of Accessibility in AI — Jemima Abu, CAIS

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: The Cost of Accessibility in AI — Jemima Abu, CAIS · Channel: AI Engineer · 09:44 · Watch on YouTube

Topics: AI agents, Prompt and context engineering, Software engineering with AI

Summary

Jemima Abu argues that accessibility should be built into AI-generated products from the start: inaccessible products exclude users and can cost more time and money to develop. In an experiment on a work codebase, using an accessibility skill reduced the agent’s cost by 58% and took about a third of the time, though she cautions that this one-off test is not empirical proof. She explains how agents can inherit inaccessible patterns and produce verbose custom code, then recommends defining requirements, auditing existing code, using reusable components, and applying accessibility guidance. AI-generated code still needs manual testing, but accessibility skills can help make products usable by more people.

Key points

Accessibility means a product can be used by anyone regardless of disability; without it, some people cannot use the product.
A WebAIM study cited in the talk found accessibility issues on 96% of homepages among the top one million websites.
In the speaker’s one-off experiment, an accessibility skill reduced agent cost by 58% and cut completion time to about a third.
The experiment was not conducted in a constrained environment, so it does not establish empirical proof that accessible development is always cheaper.
AI agents can reproduce inaccessible assumptions in an existing codebase and may write verbose custom implementations instead of using native semantic elements.
Accessibility works best when included throughout the product process, from business idea and design through development and QA, rather than added at the end.
Inaccessible products can exclude potential customers, require costly refactoring, and expose businesses to legal consequences.
Recommended steps include defining platform-specific requirements, auditing and fixing the existing codebase, using reusable components, and enforcing an accessibility skill.
Use semantic HTML where possible, reserve ARIA for cases semantic HTML cannot express, support keyboard interaction, label elements for screen readers, and audit before running code.
AI skills can help, but they do not replace manual accessibility testing.

Chapters

Start	Chapter	Summary
00:00	Why accessibility matters in AI development	The speaker defines accessibility, highlights widespread website accessibility issues, and introduces an experiment comparing AI-agent development with and without an accessibility skill.
02:33	Guiding AI agents and avoiding inaccessible defaults	Using an analogy about preparing a toddler for an errand, the speaker explains why agents need guidance and how they can inherit human biases or generate unnecessarily verbose code.
05:37	Build accessibility in from the start	The speaker compares accessibility to baking blueberries into a muffin and describes the costs of retrofitting, excluding customers, and facing legal consequences.
07:08	Practical guidance for accessible AI-generated code	The speaker recommends defining requirements, auditing code, using reusable components and accessibility skills, and combining automated checks with manual testing.

Quotes

Accessibility is the quality of being able to be used by anyone regardless of disability. — 00:00

there was also a 58% reduction in cost when using that skill. — 01:31

For it to be an accessible website, you need to put accessibility at the forefront at every build process. — 05:06

Every interactive element, if it can be operated by a mouse, it should also be operated by a keyboard. — 09:12

So, just make sure that your solution is useful to as many people as possible. — 09:44

Concepts and entities

Jemima Abu, AI Engineer, CAIS, Modern Web Guidance, WebAIM, Americans with Disabilities Act, HTML semântico, ARIA

Full transcript (original language)

00:00 Hi all, my name is Rima, and I’m going to be talking to you about the cost of accessibility in AI, or as I like to call it, stop wasting tokens on building products that people can’t use. Because at the end of the day, what is accessibility? Accessibility is the quality of being able to be used by anyone regardless of disability. So, what this means is that when you build a product that is inaccessible, that product is inherently useless because people cannot use it. I think this is a very prevalent talk, especially in these days of vibe coding and prompt engineering and AI basically writing all the code for us. We need to ensure that

00:30 even with all the code being written by AI, we’re still building for humans, and we’re ensuring that humans are able to use the products that we are building. It’s all very well and good to vibe good five different apps in one day, but if people can’t use those apps, then is there really any point? A study by WebAIM shows that 96% of the homepages of the top 1 million websites in the world have some form of accessibility issue or another. Now, I’m someone that goes around a lot and speaks about accessibility, and whenever I ask why don’t people build websites to be accessible, I usually hear it takes too long. While I will agree that

01:00 accessibility is a labor and time-intensive process, I do think that now that we’re at the stage of AI writing most of our code, it’s actually easier to make things accessible. If anything, I would say it costs more time and more money to build inaccessible websites. So, I decided to carry out a little experiment using the code base at work. So, I gave this prompt to the agents. It’s just a simple prompt with no guidelines, implement this design from Figma. And they ran it twice. The first time without any accessibility skill, and the second time by using the skill that I had written. And what I noticed was that not only was it faster for the agent to build the accessible

01:31 skill, but there was also a 58% reduction in cost when using that skill. And we can take a look at the data here. We see that not only was it cheaper, but it also took a third of the time to finish the prompt while using the accessibility skill. So, in conclusion, we can’t say that it is actually cheaper for AI agents to build accessible websites. We can’t say that, but we won’t say that because this was a one-off experiment, and it was not carried out in a constrained environment, so it cannot serve as empirical data that proves the of But, when we look into the reasons why it took the AI agent much longer to carry out the prompts without any accessibility skills, then we can have a

02:02 better idea of why exactly it is faster to build accessible websites. But, before we get into that, hi, my name is Joreima Abu. I am a product engineer at Case and an alternative investment platform. I’m also a Google Dev Expert, a Microsoft MVP, and a certified professional in accessibility core competencies. Basically, I like to go around talking about how to make the web a more accessible place. Also, I will give a slight disclaimer. While a lot of my examples relating to accessibility will be web-based because that is my area of expertise, this can also apply regardless of whatever platform you’re working on, whether that’s mobile or hardware or anything at all. So, let’s

02:33 get back to it. This is your AI agent. Now, it’s a super intelligent tool that can do almost anything in the world, but at the same time, it’s just 3 years old. And much like a baby, AI is very impressionable. If you tell it enough times that the sky is red, eventually it will start to accept that the sky is red. What this means is as the responsible developers in charge, we have to make sure that we’re providing the right skills and guidance for AI agents to build the product that we want them to build. There’s a Japanese show on Netflix that I love called Old Enough. It’s basically about toddlers being sent on their first errand. It can be like a 3-year-old

03:04 being sent to a supermarket to purchase groceries. And one thing I like about the show is that you can always see the steps that the parents have put in place before they send them on that first errand. So, it could be that the child has gone with their parents to the supermarket multiple times, or they provide a list that’s very clearly detailed that shows them where the supermarket is, what they need to get there, what paths to avoid, and it basically makes it a lot easier for the child to carry out that errand. It’s the same thing with an agent. When you’re given an instruction to an agent, if I’m saying build this webpage or implement this design, if I provide the right skills and prompts, it makes it a lot

03:35 easier for that agent to avoid going down the wrong path and for the finished product to look like what I intended it to look like. So, let’s take a look at what happens when we don’t provide any form of guidance for our agents in developing products. Firstly, human bias becomes AI bias. For years, humans have been developing websites or products that are inaccessible because frankly we just don’t think that way. Especially as developers, we tend to have a it works for me mindset. So I’m like this thing works on my laptop and it works the way I intended it to work and I’m not going to check anything else. I don’t concern myself with if it works for screen readers or if it works in low light

04:05 environments. I’m just like it works, it’s built, I’m done. Whenever you build like that or if you have a code base that reflects that kind of mentality, once you put an AI agent in that code base, it’s going to absorb all your biases. It’s going to say, “Oh, we don’t need to make these things accessible because that has not that been mentioned in the past. So I’m just going to build things anyhow.” And then the more you use that AI agent to generate codes, the more you build a code base that is inherently inaccessible because accessibility was never constraint in the first place. Secondly, and this is something that I really noticed in the experiment, AI tends to default to a lot

04:35 of verbose code. If you don’t provide any particular prompt or guidelines for your agent, it will reinvent the wheel as many times as it wants to. So even if you tell it just build a simple accordion component or build a modal component, it’s not going to bother checking is there already an existing semantic elements that can give me the same functionality? It’s just going to build one from scratch. AI loves to write code. So it’ll go off and write as many things as it wants. And as you can see here, if you are trying to recreate a semantic element, it takes a lot more time and effort because number one, you have to carry out a lot more testing,

05:06 you have to implement a lot more features to replicate the native functionality, and it’s just a very cumbersome process. So these are some of the things that you want to ensure you’re focusing on when you’re providing prompts to your agent. I saw an analogy once that said an accessible website is like a blueberry muffin. If someone hands you a plain muffin that they’ve shoved a bunch of blueberries on, similar to the picture on the right, that’s not a blueberry muffin. For it to be a proper blueberry muffin like the one on the left, then the blueberries need to have been baked in from the start. It’s the same thing with an accessible website. If you have a fully built website and then once it’s done, you start shoving in area labels in

05:37 different places, that is not an accessible website. For it to be an accessible website, you need to put accessibility at the forefront at every build process. And this does not just apply to developers, accessibility is the responsibility of everyone. So, you want to make sure that even from the business idea to design to QA, that we’re ensuring that we’re looking for accessibility and testing that can this product be used by everyone in the exact same way. And that issue with waiting till the end to consider accessibility is that you waste a lot of time on regressive testing. So, if you’ve waited until your website is fully built and then you start testing and going back to

06:07 fix issues, you end up refactoring and rewriting a lot more code than you’d have had to do if you don’t build it to be accessible from the start. And then of course, there are business consequences to building inaccessible products. The thing I hear sometimes is that a business might say, “Oh, but we don’t have to consider accessibility because none of our users rely on assistive technologies.” And I think that’s very funny because it’s sort of a self-fulfilling prophecy. It’s not that your users don’t rely on assistive technologies, it’s that people with assistive technologies cannot use your website in the first place, so they just never go to it. Imagine a business that didn’t have a door. You would never get

06:38 any customers. How would they get in the building? It’s the same thing with building an inaccessible product. If you build a product that people cannot use, then people will not use it. And then finally, there are legal repercussions to not making your website accessible. In the United States, the Americans with Disabilities Act states that any public-facing products must be accessible and can be used by people with disabilities, or you could face fines and even lawsuits. But on the plus side, you could get to use this really cute sticker on Microsoft Teams, so you know, weigh your options. Based on all this, we can see that it actually is a lot more expensive to be building products that aren’t accessible. You’re

07:08 exposing yourself to losing money from customers, possible lawsuits where you have to pay fines, you’re spending more time building code and refactoring things. So, if you do build your product to be accessible from the start, it’s going to be a lot faster and a lot cheaper. So, now that we know all that, how can we actually ensure that our AI agents are building things to be accessible? Because everyone’s code base is different and we can be working with different technologies, I’m just going to give an overarching general view of how to get your AI agents to produce accessible code. So firstly, you need to define your accessibility requirements.

07:38 Accessibility requirements differ based on what platform you’re working on. So, you do need to carry out research and ensure that you know what accessibility requirements you’re supposed to be meeting for the platform you are building for. Once that’s done, you need to audit your existing code base. So, if you’re going to introduce an AI agent into your code base, you need to ensure that you don’t have any pre-existing issues that the AI agent might copy as what it thinks is best behavior. So, you can use automated tools to carry out accessibility testing, or you can even tell your AI agent to do it. But, you want to identify any existing issues and then fix them before you start writing new

08:10 features. Then, you want to implement some sort of reusable system. This is a very nice to have, but basically, if you’re going to work with accessibility, it’s a lot easier to fix things in one component that is used in multiple places as opposed to making fixes to the same components across different files. So, just having an implemented design system or any form of reusable component library is going to save you a lot more time in the long run when making things accessible. And then finally, you want to enforce a mandatory accessibility skill. This is a skill that your AI agents will basically use anytime you’re running anything

08:41 related to maybe generating UI or writing code that requires accessibility. One skill that I really like to use is the Modern Web Guidance skill from Chrome. It’s basically a skill that ensures that your agent is using the newest HTML and CSS features as opposed to custom JavaScript implementations. You can also have a lightweight version of an accessibility skill. I think this is very important, especially if you’re like vibe coding or you’re not working in a big code base. You just want something quick that your agent can refer to and not carry out a lot of in-depth research. This is what I would recommend for meeting like bare minimum accessibility requirements. So, you want to make sure that you’re using semantic HTML wherever possible, only reaching for ARIA when

09:12 semantic HTML can’t express the behavior. Every interactive element, if it can be operated by a mouse, it should also be operated by a keyboard. You also make sure that elements are properly labeled and can be read by screen readers. And then finally, before running the code, your agent should carry out an audit against all those steps. Of course, this is not enough to build a fully accessible website. You still need to carry out a lot of manual testing yourself because it’s not possible for a one tool to make a website fully accessible. But, just having these skills in place can help a lot more than not having them there at all. Regardless of why you use AI, most times the goal is to solve a particular

09:44 problem. So, just make sure that your solution is useful to as many people as possible. So, build things to be accessible. And that is all. Thank you so much for listening to my talk. I hope you enjoyed it. If you do have any questions, feel free to reach out to me online at Jemima Abu. That’s LinkedIn, Twitter, or GitHub. I would love to hear from you. Okay, bye.