Skip to main content

How LLTeacher Works: From Assignment Design to Review

LLTeacher is designed to change the way students interact with AI during their coursework. Rather than using an AI to generate a quick answer, the platform creates a structured environment where the AI acts as a tutor. 

The process follows a simple three-step cycle: the instructor creates the homework, the student works through the problem conversationally, and finally the instructor reviews the journey.

Preparing the Lesson

The process begins in the Instructor View, where the educator sets the foundation for the assignment.

Instead of simply providing a question, the instructor uploads a problem statement and a detailed reference solution that serves as the "gold standard." 

Crucially, the instructor also select a set of instructions, or a prompt, that defines the teaching style for that specific task. 

This allows the instructor to direct the AI to:

  1. Act as a nudge for recall, asking students to remember concepts from a previous lecture, or 
  2. Act as a guide for discovery, leading them to find a solution or pattern themselves, or
  3. Act as a critical thinking challenge, providing students with deliberately flawed content for them to identify, analyze, and correct.

The AI uses the reference solution as its boundary, ensuring its guidance stays within the specific scope and terminology of that particular class.

The Student’s Workflow

When a student opens the Student View, they engage with a conversational interface focused entirely on the assignment. 

The student talks through their logic and shares their work with the AI, which is instructed to act as a supportive coach. 

This setup ensures there are no "spoilers"; the AI is programmed not to provide the final solution. 

If a student asks for the answer, the AI redirects them toward the next logical step in the problem-solving process. 

When a student makes a mistake, the AI uses it as a teaching moment by identifying where the logic went off track and providing feedback or follow-up questions. This allows the student to experiment and fail safely before finishing the task.

Reviewing the Learning Process

The cycle ends back in the Instructor View, providing a level of transparency that traditional homework cannot offer. 

While a teacher usually only sees the final result, LLTeacher allows the instructor to read the full conversation history between the student and the AI. 

By reviewing these interaction logs, the instructor can identify friction points where most of the class got stuck or where the AI had to provide the most hints. 

This transparency leads to better feedback, as the instructor can address specific gaps in a student’s thought process during the next lesson, even if the student eventually arrived at the correct answer.

The workflow of the application is also described in LLteacher: A Tool for the Integration of Generative AI into Statistics Assignments 

 

By following this sequence, the homework becomes less about the final output and more about the steps taken to get there.

Video format 


 

Popular posts from this blog

Why We Developed LLteacher

Generative AI is reshaping education, and homework is at the center of this change. Tools like ChatGPT make it very tempting to bypass essential cognitive steps such as recalling concepts, re-elaborating ideas, and applying knowledge. These steps are not just formalities; they are the foundation of learning. When they disappear, so does much of the educational value of assignments. Some institutions have responded by banning AI, but this approach is difficult to enforce and ignores the reality that AI will be part of students’ future professional environments. Instead, we believe the challenge is to integrate AI thoughtfully, in ways that preserve learning objectives, enhance pedagogical tools, and promote equity. LLteacher is our attempt to do this. It is an open-source tool designed for homework assignments in statistics courses. Rather than providing direct answers, LLteacher guides students through problem-solving, encouraging active engagement and critical thinking. Instructors re...
Read more

Preventing AI use is not the answer

When ChatGPT first arrived, it fundamentally changed the landscape of how our students complete their homework. Traditionally, homework was a space where students engaged in their learning process: they had to recall information, re-elaborate concepts, and apply their knowledge independently. Today, that process is at risk.   We’ve seen firsthand how the widespread availability of LLMs has disrupted this cycle. Students can now bypass the entire learning process by asking an AI for direct solutions.  This isn’t just about "cheating", it’s a qualitatively different challenge.  AI is easily accessible, harder to detect, and increasingly socially acceptable among students.  Most critically, when students use AI this way, they miss out on the essential cognitive processes that are central to genuine learning.  While some instructors have moved to ban these tools, we believe that is not the right path for two major reasons:   Enforcement is nearly impo...
Read more