modified to original

matrixx136 · Dec 16, 2023 · eacfee6 · eacfee6
1 parent 4806979
commit eacfee6
Showing 1 changed file with 11 additions and 11 deletions.
diff --git a/12-designing-ux-for-ai-applications/README.md b/12-designing-ux-for-ai-applications/README.md
@@ -1,6 +1,6 @@
 # Designing UX for AI Applications
 
-[![Designing UX for AI Applications](../../images/12-lesson-banner.png?WT.mc_id=academic-105485-yoterada)](https://youtu.be/bO7h2_hOhR0?WT.mc_id=academic-105485-yoterada)
+[![Designing UX for AI Applications](./images/12-lesson-banner.png?WT.mc_id=academic-105485-koreyst)](https://youtu.be/bO7h2_hOhR0?WT.mc_id=academic-105485-koreyst)
 
 > *(Click the image above to view video of this lesson)*
 
@@ -25,7 +25,7 @@ After taking this lesson, you'll be able to:
 
 ### Prerequisite
 
-Take some time and read more about [user experience and design thinking.](https://learn.microsoft.com/training/modules/ux-design?WT.mc_id=academic-105485-yoterada)
+Take some time and read more about [user experience and design thinking.](https://learn.microsoft.com/training/modules/ux-design?WT.mc_id=academic-105485-koreyst)
 
 ## Introduction to User Experience and Understanding User Needs
 
@@ -49,7 +49,7 @@ Being accessible means extending the user experience to users with various abili
 
 Being pleasant means that the application is enjoyable to use. An appealing user experience can have a positive impact on the user encouraging them to return to the application and increasing business revenue.
 
-![image illustrating UX considerations in AI](../../images/uxinai.png?WT.mc_id=academic-105485-yoterada)
+![image illustrating UX considerations in AI](./images/uxinai.png?WT.mc_id=academic-105485-koreyst)
 
 Not every challenge can be solved with AI. AI comes in to augment your user experience, be it automating manual tasks, or personalizing user experiences.
 
@@ -63,25 +63,25 @@ Two ways to ensure that trust is put right at the center of design are explainab
 
 When AI helps inform decisions such as imparting knowledge to future generations, it is critical for teachers and parents to understand how AI decisions are made. This is explainability - understanding how AI applications make decisions. Designing for explainability includes adding details of examples of what an AI application can do. For example, instead of "Get started with AI teacher", the system can use: "Summarize your notes for easier revision using AI."
 
-![an app landing page with clear illustration of explainability in AI applications](../../images/explanability-in-ai.png?WT.mc_id=academic-105485-yoterada)
+![an app landing page with clear illustration of explainability in AI applications](./images/explanability-in-ai.png?WT.mc_id=academic-105485-koreyst)
 
 Another example is how AI uses user and personal data. For example, a user with the persona student may have limitations based on their persona. The AI may not be able to reveal answers to questions but may help guide the user to think through how they can solve a problem.
 
-![AI replying to questions based on persona](../../images/solving-questions.png?WT.mc_id=academic-105485-yoterada)
+![AI replying to questions based on persona](./images/solving-questions.png?WT.mc_id=academic-105485-koreyst)
 
 One last key part of explainability is the simplification of explanations. Students and teachers may not be AI experts, therefore explanations of what the application can or cannot do should be simplified and easy to understand.
 
-![simplified explanations on AI capabilities](../../images/simplified-explanations.png?WT.mc_id=academic-105485-yoterada)
+![simplified explanations on AI capabilities](./images/simplified-explanations.png?WT.mc_id=academic-105485-koreyst)
 
 ### Control
 
 Generative AI creates a collaboration between AI and the user, where for instance a user can modify prompts for different results. Additionally, once an output is generated, users should be able to modify the results giving them a sense of control. For example, when using Bing, you can tailor your prompt based on format, tone and length. Additionally, you can add changes to your output and modify the output as shown below:
 
-![Bing search results with options to modify the prompt and output](../../images/bing1.png?WT.mc_id=academic-105485-yoterada "Bing search results with options to modify the prompt and output")
+![Bing search results with options to modify the prompt and output](./images/bing1.png?WT.mc_id=academic-105485-koreyst "Bing search results with options to modify the prompt and output")
 
 Another feature in Bing that allows a user to have control over the application is the ability to opt in and opt out of the data AI uses. For a school application, a student might want to use their notes as well as the teachers' resources as revision material.
 
-![Bing search results with options to modify the prompt and output](../../images/bing2.png?WT.mc_id=academic-105485-yoterada "Bing search results with options to modify the prompt and output")
+![Bing search results with options to modify the prompt and output](./images/bing2.png?WT.mc_id=academic-105485-koreyst "Bing search results with options to modify the prompt and output")
 
 > When designing AI applications, intentionality is key in ensuring users do not over trust setting unrealistic expectations of its capabilities. One way to do this is by creating friction between the prompts and the results. Reminding the user, that this is AI and not a fellow human being
 
@@ -93,7 +93,7 @@ AI applications should be built in to receive and give feedback. This not only h
 
 Another way to handle this is to clearly communicate the capabilities and limitations of the system. When a user makes an error requesting something beyond the AI capabilities, there should also be a way to handle this, as shown below.
 
-![Giving feedback and handling errors](../../images/feedback-loops.png?WT.mc_id=academic-105485-yoterada)
+![Giving feedback and handling errors](./images/feedback-loops.png?WT.mc_id=academic-105485-koreyst)
 
 System errors are common with applications where the user might need assistance with information outside the scope of the AI or the application may have a limit of how many questions/subjects a user can generate summaries. For example, an AI application trained with data on limited subjects for example, History and Math may not be able to handle questions around Geography. To mitigate this, the AI system can give a response like: "Sorry, our product has been trained with data in the following subjects....., I cannot be able to respond to the question you asked."
 
@@ -115,6 +115,6 @@ Take any AI apps you've built so far, consider implementing the below steps in y
 
 ## Congratulations, you have finished this course
 
-After completing this lesson, check out our [Generative AI Learning collection](https://aka.ms/genai-collection?WT.mc_id=academic-105485-yoterada) to continue leveling up your Generative AI knowledge!
+After completing this lesson, check out our [Generative AI Learning collection](https://aka.ms/genai-collection?WT.mc_id=academic-105485-koreyst) to continue leveling up your Generative AI knowledge!
 
-Congratulations, you have completed this course! The building should not stop here. Hopefully, you have been inspired to start building your own Generative AI startup. Head over to the [Microsoft Founders Hub](https://aka.ms/genai-foundershub?WT.mc_id=academic-105485-yoterada) and apply for the program to receive support on your journey.
+Congratulations, you have completed this course! The building should not stop here. Hopefully, you have been inspired to start building your own Generative AI startup. Head over to the [Microsoft Founders Hub](https://aka.ms/genai-foundershub?WT.mc_id=academic-105485-koreyst) and apply for the program to receive support on your journey.