Designing a teaching assistant agent.

Designing a teaching assistant agent. 

Repetitive Task

The selected repetitive task is data entry and validation. This task consists of receiving information from forms, emails, or documents; entering it into a spreadsheet or system; checking that the required fields are complete; identifying errors or missing information; and organizing the final result for later use. 

Why It Is Repetitive                                                                                                                                                    This task is repetitive because it follows the same sequence of steps every time: collect the input, review the information, apply validation rules, correct or flag errors, and produce an organized output. Since the process has clear inputs, defined actions, and expected results, it can be represented as an algorithm. 

Why It Can Be Automated or Supported by an Agent                                                                                      An agent can support or automate this task because the rules are predictable and can be converted into logical instructions. For example, the agent can verify whether mandatory fields are completed, detect inconsistent formats, classify information, generate alerts, and prepare a clean final report. This reduces manual work, minimizes human error, and allows people to focus on decisions that require judgment or creativity. 

This task can be described using the basic structure of an algorithm: input, process, and output. The input is the raw data received; the process is the validation and organization of that data; and the output is a completed and reliable record. A flowchart could also be used to visualize decisions such as: Is the information complete? Is the format correct? Should the record be accepted or returned for correction? 

Data entry and validation is a strong candidate for automation because it is structured, rule-based, and frequently repeated. By using an agent, the process becomes faster, more consistent, and easier to monitor, improving efficiency in academic, administrative, or business environments. 

Step-by-Step Logic:

The agent follows a simple step-by-step logic to help the user prepare coffee at home. First, the process starts when the user needs coffee. Then, the agent checks if there is coffee available. If there is no coffee, the agent tells the user to buy coffee. If there is coffee, the agent continues with the preparation process by telling the user to heat water, mix the coffee with water, and serve the coffee. The process ends when the coffee is ready.

In if/else logic, the agent works like this:

• If there is coffee, the agent continues with the preparation steps.

• Else, the agent tells the user to buy coffee.

The final result is a prepared cup of coffee.

Reflection

This agent could help teachers use their lesson plan in a more organized way. Even when the teacher already has the official planning document, the agent can help guide the class step by step. It can support the teacher in organizing the topics, activities, and time during the lesson. This makes the teaching process clearer, easier to follow, and more practical for both the teacher and the students.

Prompt engineering for teaching tasks.

 Prompt

Summary: What Is an Effective Prompt?

An effective prompt is a clear and specific instruction that tells an AI tool what task to perform, what information to use, and how the answer should be presented. In other words, a prompt works like a request to a helpful assistant: the more precise and organized the instruction is, the more useful, accurate, and relevant the response will be.

A strong prompt usually includes three main parts: task, context, and format. The task explains what the AI should do, such as summarize, explain, classify, create, rewrite, or analyze. The context gives the AI important background information, such as the audience, educational level, purpose, topic, or data to use. The format describes how the final answer should look, for example as bullet points, a paragraph, a table, steps, JSON, or a concise report.

Effective prompts may also include expectations, examples, and clear sections. Expectations help define the desired tone, level of detail, or quality of the response. Examples guide the AI by showing the type of answer the user wants. Clear organization, such as numbered steps or section labels, reduces ambiguity and helps the AI follow instructions more accurately.

To create better prompts, users should be clear, avoid vague language, provide enough context, define the output format, and review the AI response for accuracy. Prompt writing is an iterative process, so it is normal to adjust and improve the prompt after seeing the first result. A responsible user should also check the information, protect personal data, and remember that AI-generated content may contain errors or bias.

Main Parts of an Effective Prompt

Task: The action you want the AI to complete, such as explain, summarize, create, compare, or analyze.

Context: Background information that helps the AI adapt the response to the situation, audience, topic, or purpose.

Format: The structure or style of the answer, such as a list, paragraph, table, steps, or formal tone.

Expectations: Specific requirements about depth, tone, length, accuracy, or what to include or avoid.

Examples: Sample inputs or outputs that help the AI understand the desired result more clearly.

Simple Example

Effective prompt: Act as a secondary school teacher. Explain photosynthesis in simple language for beginner students. Present the answer as a list of 5 key points and include one practical example at the end.

Best prompt example: You are a secondary school English teacher. Explain the concept of “parts of speech” for a class of ninth-grade students using a clear and simple explanation. Organize the concepts and include one example for each one. Avoid using overly technical terms, and make the explanation engaging and easy to understand for students.

This prompt works because it clearly defines the role, topic, audience, and expected style of the response. It tells the AI to act as an English teacher, explains that the content is for ninth-grade students, and asks for simple language with examples. It also gives clear instructions about how to organize the information and what to avoid, which helps the AI generate a focused, useful, and student-friendly answer.

Reflection

Today, prompts can help teachers optimize many educational tasks by making the use of AI more focused, clear, and productive. A well-written prompt allows teachers to save time when creating lesson plans, summaries, activities, quizzes, explanations, and adapted materials for different student levels. Prompts also help organize ideas and generate resources that can support classroom learning. However, teachers should always review the AI’s responses to make sure the information is accurate, appropriate, and aligned with their educational goals. In this way, prompts become a useful tool to improve teaching efficiency while maintaining human judgment and responsibility.

Using Copilot to summarize academic information.

IA

Summary of Generative AI, LLMs, and Copilot

Summary

Artificial Intelligence is presented in the document as the science of making machines think and act in ways that resemble human behavior. It is described as an “eternal learner”: a system that observes millions of examples until it can imitate patterns, make predictions, or generate new responses. Although AI has existed for decades in tools such as GPS navigation and email spam filters, it has become much more visible with the rise of generative systems that create text, images, music, and other forms of content.

The document explains several types of AI through everyday examples. Generative AI creates new content and is represented by tools such as ChatGPT, Gemini, and Midjourney. Recognition AI identifies objects, faces, and places, as in facial unlocking systems or augmented reality games. Recommendation AI filters information according to a user’s preferences, while predictive AI anticipates results based on past data, such as weather forecasts or bank fraud detection. Together, these examples show that AI is not a single tool, but a broad set of technologies used to observe, classify, predict, and create.

Current uses of AI are illustrated through cases that show how people often help train these systems without noticing it. In Pokémon GO, for example, players’ camera movements and location-based interactions help artificial intelligence understand real-world spaces, objects, depth, and surfaces. CAPTCHA systems are also described as a kind of classroom where humans teach AI to recognize traffic lights, crosswalks, and road signs. Social media algorithms are another example: they learn from small user signals, such as watching a video until the end, skipping it quickly, or giving it a like. These algorithms build mathematical profiles of user interests and prioritize content that keeps people engaged, even if that content is not necessarily the most truthful or educational.

Large Language Models, or LLMs, are introduced as the technology behind tools such as ChatGPT and similar assistants. Their main task is to predict the next word in a sequence. Although this sounds simple, it allows them to produce coherent sentences, paragraphs, explanations, and complete texts. The document explains that LLMs are first trained with huge amounts of text through pretraining and then improved through feedback from humans or other AI systems, a process called refinement. It also identifies the transformer as the internal structure that allows these models to process language efficiently. The term GPT is explained as Generative Pretrained Transformer.

A central idea in the document is that an LLM should not be confused with a search engine or a source of truth. It does not simply consult a database of verified facts. Instead, it generates probable language by predicting what words are likely to fit together. Because its priority is fluency and coherence, not truth, it may produce answers that sound convincing but are false. These errors are called hallucinations. They can include invented dates, books, laws, authors, or citations that appear real. For that reason, the document emphasizes that AI-generated content must always be checked carefully.

The role of the teacher or professional user is presented as essential. The AI is compared to a copilot that can generate drafts, ideas, and initial text, while the human remains the captain who validates, corrects, and decides what is useful. The document highlights the difference between a novice, who may not detect mistakes, and a trained professional, who can identify historical, pedagogical, or conceptual problems because of their knowledge and experience. This reinforces the idea that information is not the same as knowledge: AI can provide data and text, but human judgment supplies understanding, ethics, and context.

The document also explains basic terms related to how AI works. A data center is the physical infrastructure where AI systems run, described as a building full of powerful computers that give the AI the capacity to respond. A model is the trained digital brain, such as GPT-4 or Gemini. The interface is the screen through which the user communicates with the system, and the text box is where instructions are entered. A prompt is the question or instruction given to the AI, and the quality of the prompt strongly affects the quality of the answer. Tokens are the small pieces of text that AI systems process, similar to building blocks rather than full words or letters.

Another important concept is the context window, which works like the AI’s short-term memory during a conversation. It determines how much previous text the system can remember and use when answering. The document also describes iteration and refinement as the process of improving results by asking the AI to adjust its response. For example, if a generated exam is too difficult, the user can ask the AI to make it simpler. This back-and-forth process helps transform a first draft into a more useful final product.

Finally, the document provides guidance for writing effective prompts. Before asking the AI for help, users should define their objective, explain the context, specify the sources or references needed, and make their expectations clear. They should indicate the desired tone, audience, format, and purpose of the response. Courtesy and clarity are also encouraged, because respectful and specific instructions make it easier for the AI to understand the request. The document closes with guiding questions that help users improve their prompts: what the text should achieve, who the audience is, what tone is appropriate, which data or references should be included, how the response should be organized, and what exact result is expected.

In conclusion, the document presents generative AI and LLMs as powerful tools for learning, writing, organizing information, and supporting teaching, but it also warns that they require critical thinking. AI can accelerate work and provide useful first drafts, but it can also make mistakes, invent information, or reinforce habits shaped by engagement-driven algorithms. The most responsible approach is to use AI as an assistant, not as an unquestionable authority. In this model, Copilot or any similar AI tool supports the work, while the human user provides verification, professional judgment, ethical responsibility, and final decisions.

Explanation of how we use Copilot: For the summary about AI, LLMs, and Copilot, Copilot was used. A prompt was given asking it to create a summary of the document provided and discussed in class. The summary had to be written in English, delivered in a Word document, and presented in prose form.

Reflection: 

In my opinion, Artificial Intelligence can be a very useful support tool for teachers when it is used responsibly. AI can help create teaching materials, organize ideas, prepare summaries, design activities, and save time during lesson planning. If teachers know how to use it well, it can make classes more dynamic, creative, and easier to prepare.

However, AI also has important limitations. It can sometimes provide incorrect or incomplete information, and it does not fully understand the specific needs, context, or learning process of each group of students. For this reason, teachers should not depend on AI for everything. It is important to review and adapt the information, because the teacher is the one who has the professional knowledge, critical thinking, and responsibility for the class.