Educational Technology and Change Journal

By Jim Shimabukuro (assisted by Gemini)
Editor

Introduction: I collaborated with Gemini on this report. Our search was for a free AI online science lab for secondary students that doesn’t require a physical lab or classroom and can be accessed in a classroom setting or independently outside of school via laptop or desktop over the internet. The LabXchange and PhET Interactive Simulations combo seems to be a good choice. -js

Gemini: LabXchange and PhET Interactive Simulations have joined forces to offer AI-powered hands-on science labs for secondary students. Both platforms, working together, are highly regarded by educators, students, and parents. They are free to use, accessible on laptops and desktops with an internet connection, and provide a way to track student progress over time.

LabXchange 🔬

LabXchange is a free, AI-powered online platform developed by Harvard University. It provides an extensive library of virtual lab simulations, videos, and assessments. The platform is especially strong in its coverage of biology, chemistry, and other life sciences.

• Key Features: LabXchange uses artificial intelligence to provide real-time feedback to students as they work through simulations. This allows students to make mistakes and learn from them in a safe, consequence-free environment. The simulations are designed to be “lab-accurate” with realistic equipment and procedures.
• Student Progress Tracking: Students can create an account to save their work and track their progress through various learning pathways. Educators can also set up a class and monitor student performance on assignments and labs.
• Reputation: LabXchange is widely used in high schools and universities globally. It’s often cited as a reliable and high-quality resource for remote and blended learning.

PhET Interactive Simulations ⚛️

Developed by the University of Colorado Boulder, PhET provides a large collection of interactive simulations for science and math. While not exclusively AI-powered, the simulations are designed to be highly interactive and inquiry-based, allowing students to explore scientific concepts through a game-like, exploratory environment.

• Key Features: PhET simulations cover a broad range of subjects, including physics, chemistry, biology, and earth science. They are known for their intuitive design and ability to help students visualize abstract scientific concepts. The platform’s interactive nature allows students to manipulate variables and observe the outcomes, promoting a deeper understanding of scientific principles.
• Student Progress Tracking: PhET includes a feature where students can register and save their work. This allows for a cumulative record of their activity and performance. It also includes resources and activities submitted by a community of teachers, which often include assessments and ways to track student learning.
• Reputation: PhET has been a trusted resource for educators for over two decades. It’s renowned for being a research-based project, with simulations grounded in educational research to maximize learning effectiveness. It’s one of the most widely used and respected platforms for science simulations in education.

A Typical Independent Study Lesson: The pH Scale and Acid-Base Chemistry

Let’s imagine a high school sophomore named Alex, who is independently studying chemistry. He’s reached a unit on acids and bases and needs to conduct some “hands-on” experiments. Alex begins his lesson by logging into his LabXchange account.

Part 1: Foundational Knowledge with LabXchange

1. Introduction via a “Pathway”: Alex’s independent learning curriculum has directed him to a specific “Pathway” on LabXchange titled “Introduction to Acids and Bases.” This pathway is a curated sequence of learning resources.
   • He begins with an introductory video from a content partner like the Khan Academy or a Harvard professor, which explains the core concepts of acids, bases, and the pH scale (pH=−log[H+]). The video is followed by a short quiz to check for understanding.
   • Next, he encounters an interactive text document that delves deeper into the role of water in acid-base chemistry, the difference between strong and weak acids, and the concept of chemical equilibrium. The AI in LabXchange might highlight key terms and offer pop-up definitions or related video clips to ensure Alex grasps the concepts.
   • Alex then moves to a virtual lab simulation on LabXchange that focuses on preparing a buffer solution. This is a complex, multi-step process that would be difficult to perform in a physical lab without a teacher’s guidance. The simulation guides him through using a virtual micropipette and a pH meter, providing real-time feedback.¹ If he makes a mistake, like adding too much acid, the AI doesn’t just say “incorrect.” Instead, it might provide a hint, “Consider the molarity of the acid and the desired final volume. How does this affect the calculation?” Alex must correct his approach before moving on. The system tracks his attempts and successful completion.

Part 2: Inquiry-Based Exploration with PhET

2. Connecting to a PhET Simulation: At a key point in the pathway, the LabXchange curriculum seamlessly links to a PhET simulation.² This is where Alex transitions from a structured lab exercise to a more open-ended exploration.
   • The prompt on LabXchange might read, “Now that you understand the theory, use the ‘pH Scale’ PhET simulation to explore the relationship between the concentration of H3​O+ and OH− ions and the pH of a solution. Can you find a solution with a pH of exactly 7? What about 10?”
   • Alex clicks the link and is taken to the PhET “pH Scale” simulation. The interface is intuitive and game-like. He sees a beaker with a substance, a pH meter, and a hydronium-hydroxide ion concentration scale.
   • He begins to experiment freely. He can choose different substances (like coffee, milk, or hand soap) and observe the pH value. He drags the probe into the beaker, and the pH meter instantly changes. He can also see the relative number of H3​O+ and OH− ions.
   • Alex’s AI-assisted experience: While PhET itself doesn’t have an AI assistant, the LabXchange platform can log that he engaged with the simulation. A more advanced LabXchange pathway might even have a post-simulation assessment, where Alex is asked to record his observations and draw conclusions. For instance, he might be asked to predict what would happen to the pH of a strong acid if he adds water and then check his prediction using the PhET simulation’s “dilute with water” feature.

Part 3: Assessment and Review with LabXchange

3. Synthesizing and Assessing Learning: Alex returns to his LabXchange pathway.
   • He encounters a final virtual lab simulation on LabXchange that requires him to apply what he’s learned from both the introductory material and the PhET exploration. This simulation might involve identifying an unknown solution’s pH and then using a titration technique to neutralize it. This builds on the skills he practiced earlier.
   • He takes a final assessment. This could be a multiple-choice quiz, a short answer section, or a challenge that asks him to design an experiment to test a new hypothesis about acid-base reactions.
   • Alex’s cumulative record: Throughout this process, LabXchange has been recording his every move. His performance record shows:
     • Which videos he watched and for how long.
     • His score on the quizzes and assessments.
     • The time he spent on the virtual labs and how many attempts it took to complete each step successfully.
     • A note that he completed the PhET simulation, with a record of any data he might have been asked to input.

This comprehensive record gives Alex and, if he chooses, a mentor or parent, a detailed picture of his learning journey, not just his final score. He can see which concepts were difficult for him and where he excelled, allowing him to focus his future study more effectively.

Closer Look at AI Features

LabXchange and PhET have distinct approaches to integrating AI and technology to enhance the learning experience. While both are powerful educational tools, their underlying mechanisms and the extent of their AI application differ.

LabXchange: AI-Powered Learning Platform

LabXchange’s AI features are more about personalization and structured, adaptive learning. The platform’s AI acts as a smart tutor and a learning manager.

• Personalized Learning Pathways: The core AI feature of LabXchange is its ability to curate and customize “Pathways” for students. This isn’t just a static list of videos and simulations; the AI can analyze a student’s performance data (e.g., scores on quizzes, time spent on difficult concepts, successful completion of lab steps) and suggest a personalized learning journey. For example, if a student struggles with stoichiometry, the AI might recommend a different sequence of resources, including more foundational videos and practice problems, before moving on to the next lab.
• Real-time Adaptive Feedback: In the virtual labs, LabXchange’s AI acts as a virtual lab assistant.¹ As a student performs a task, such as measuring a chemical or titrating a solution, the AI provides immediate, context-specific feedback. This feedback is designed to be more than just “right” or “wrong.” It can offer hints, ask guiding questions, or explain the scientific principle behind a mistake, allowing the student to correct their own understanding rather than just following a script. This is a form of intelligent tutoring.
• Data-Driven Assessment: The AI in LabXchange continuously collects data on student performance. This cumulative record is not just a list of scores; it provides detailed analytics for both the student and the instructor. It can highlight patterns in a student’s learning, such as a consistent misunderstanding of a particular concept or a skill gap in a certain lab technique. This data-driven approach is crucial for formative and summative assessment in an independent study environment.
• Content Curation: LabXchange’s AI helps to organize its vast library of content from numerous partners (like Harvard and the Amgen Foundation) into logical and effective learning sequences. This saves educators and independent learners significant time by providing a structured curriculum.²

PhET Interactive Simulations: Research-Based, Not AI-Driven

PhET is a different kind of platform. While it’s incredibly interactive and effective for hands-on learning, it is not an AI-driven platform in the same sense as LabXchange. Its power comes from a different kind of intelligence: human-centered design and extensive educational research.

• Research-Based Design: PhET simulations are the result of years of educational research, including extensive student interviews and classroom observations.³ The goal is to design simulations that are intuitive, encourage exploration, and help students build a deep conceptual understanding of scientific principles. The “intelligence” is baked into the design of the simulation itself, not into an external AI that provides feedback.
• Inquiry-Based Learning: PhET’s core philosophy is to let students learn through exploration and discovery.⁴ The simulations are intentionally open-ended and game-like. There’s no AI telling the student, “This is the correct next step.” Instead, the student learns by manipulating variables, observing the results, and forming their own hypotheses. This promotes critical thinking and scientific inquiry.
• Implicit Guidance: While there’s no explicit AI tutor, PhET simulations do provide implicit guidance.⁵ For instance, by visually representing invisible phenomena (like the movement of molecules or electric fields), the simulation itself serves as a mental model that guides a student’s thinking. The controls are also often limited to prevent unproductive exploration, but within those limits, students are free to experiment.
• Community-Driven Resources: The PhET platform’s “AI” is its community. Teachers and educators contribute their own lesson plans, activities, and guides for the simulations.⁶ These resources often include a structured approach to using the simulations, turning an open-ended tool into a more guided lesson, but this guidance comes from a human, not an algorithm.

Conclusion

In the hypothetical scenario, the power of the combination lies in this distinction: LabXchange acts as the “smart curriculum” and “AI tutor,” providing a structured, personalized pathway and real-time feedback. It ensures Alex masters the foundational skills and concepts. PhET, on the other hand, acts as the “virtual lab bench” for free-form, inquiry-based experimentation.⁷ It allows Alex to apply the knowledge from LabXchange and build a deeper conceptual understanding through hands-on, exploratory learning, all without an AI directing his every move.

Filed under: Uncategorized |