[{"content":"Write your text here.\nWhat is RAG? # During the course, I was introduced to Retrieval-Augmented Generation (RAG) as a way to improve how Large Language Models generate answers.\nOne of the main problems with LLMs is that they can sometimes produce incorrect or outdated information. RAG helps with this by retrieving relevant information from an external source before generating a response. This means the model does not rely only on its built-in knowledge, but can also use specific documents or data as context.\nI found this approach especially interesting because it makes chatbot systems more reliable and more useful in practice. It also creates a clearer separation between the language model and the knowledge source, which makes the system easier to update and maintain.\n","externalUrl":null,"permalink":"/Portfolio/posts/02-intro-rag-reflection/","section":"Posts","summary":"","title":"Intro RAG Reflection","type":"posts"},{"content":" RAG Chatbot in Dify # In this project, I created a small RAG chatbot in Dify. The purpose was to understand how a chatbot can use uploaded or imported content as its knowledge base instead of relying only on general model knowledge.\nI worked on setting up the chatbot, importing data, splitting the text into smaller chunks, and making the content searchable. This allowed the chatbot to retrieve relevant text passages and use them as context when generating answers.\nThe project gave me a better understanding of how retrieval, indexing, and generation work together in a RAG-based solution.\n","date":"24 April 2026","externalUrl":null,"permalink":"/Portfolio/posts/03-rag-demo-reflection/","section":"Posts","summary":"","title":"RAG Chatbot in Dify","type":"posts"},{"content":" First Experiences with Code Agents # In this reflection, I want to describe my first experience with using code agents in practice. Overall, the experience has been positive, and I can see that code agents can be very useful when working on programming tasks.\nOne of the most important things I learned is that the quality of the response depends a lot on the prompt. If the instructions are unclear or too vague, the chatbot or code agent can misunderstand the task and produce an answer that is not very helpful. Because of this, it is important to be specific and explain the task clearly.\nMy first impression is that code agents can save time and help with both small and larger tasks, but they work best when they are guided well. This means that the user still plays an important role in giving direction, checking the output, and improving the prompt when needed.\nOverall, I think using code agents has been a good experience so far. It has shown me that AI can be a useful support tool in development, but also that good prompting is necessary to get accurate and relevant results.\n","date":"3 May 2026","externalUrl":null,"permalink":"/Portfolio/posts/04-code-agents-reflection/","section":"Posts","summary":"","title":"First Experiences with Code Agents","type":"posts"},{"content":" AI-Driven Application with External API # In this post, I reflect on how I worked with an AI-driven application that combines a Large Language Model with an external API. The purpose of this kind of solution is not only to generate text, but also to connect the model to real data from another system.\nThe application was designed so that the LLM could support the user by understanding prompts and helping generate useful responses, while the external API provided additional data or functionality. This made the application more dynamic, because it was able to do more than rely only on the model\u0026rsquo;s built-in knowledge.\nThrough this work, I gained a better understanding of how AI applications can be structured in practice. I saw how the LLM can act as an intelligent interface, while the API makes it possible to retrieve or send information between systems. This combination shows how AI can be used as part of a broader software solution.\nOverall, the project helped me understand that AI-driven applications become much more powerful when they are connected to external tools and services. It also showed me the importance of designing the interaction carefully, so the model and the API work together in a useful and reliable way.\n","date":"3 May 2026","externalUrl":null,"permalink":"/Portfolio/posts/05-ai-driven-api-application/","section":"Posts","summary":"","title":"AI-Driven Application with External API","type":"posts"},{"content":" Madiha's Portfolio Course Portfolio A collection of assignments, reflections, and project notes from my course in AI-driven applications. The site brings my work together in one place and shows how my understanding develops from week to week. Browse all posts Latest project AI-driven applications RAG Reflections and coursework Featured work # AIDA Portfolio An introduction to the portfolio and my expectations for the course.\nRAG Reflection A short reflection on retrieval-augmented generation and why it matters.\nRAG Demo A summary of my Dify chatbot project and what I learned from building it.\nCode Agents A short reflection on my first experiences using code agents and why prompting matters.\nAI Application API A reflection on building an AI-driven application that combines an LLM with an external API.\n","date":"3 May 2026","externalUrl":null,"permalink":"/Portfolio/","section":"","summary":"","title":"","type":"page"},{"content":"","date":"3 May 2026","externalUrl":null,"permalink":"/Portfolio/posts/","section":"Posts","summary":"","title":"Posts","type":"posts"},{"content":"As part of the introduction to AI-driven applications, we were introduced to the concept of Large Language Models (LLMs) and their role in modern software development.\nFrom my understanding, an LLM is a model trained on large amounts of text data, which enables it to predict and generate human-like language.\nThrough this course, I expect to learn how AI can be integrated into software solutions and how LLMs can be used as part of a structured development process. This portfolio will document that learning journey through reflections and projects.\n","externalUrl":null,"permalink":"/Portfolio/posts/01-intro-aida-portfolio/","section":"Posts","summary":"","title":"About","type":"posts"},{"content":"","externalUrl":null,"permalink":"/Portfolio/authors/","section":"Authors","summary":"","title":"Authors","type":"authors"},{"content":"","externalUrl":null,"permalink":"/Portfolio/categories/","section":"Categories","summary":"","title":"Categories","type":"categories"},{"content":"","externalUrl":null,"permalink":"/Portfolio/series/","section":"Series","summary":"","title":"Series","type":"series"},{"content":"","externalUrl":null,"permalink":"/Portfolio/tags/","section":"Tags","summary":"","title":"Tags","type":"tags"}]