Computer Science

|

9th, 10th, 11th

O(n) review session with real life examples

Have AI conduct a review session with students by providing practical engineering problems where the O(n) time complexity has to be determined.

Student session transcript example next to Flint-generated graph of various O(n) trajectories.
Student session transcript example next to Flint-generated graph of various O(n) trajectories.
Student session transcript example next to Flint-generated graph of various O(n) trajectories.

Teaching goals

Learning time complexity is a critical part of improving students’ algorithmic thinking skills.

Typically, teachers might have students read about comparisons between different time complexities (logarithmic, quadratic, etc.), along with example algorithms for each. Or, teachers may talk through examples with slides or by playing an instructional YouTube video.

With Flint, teachers can take pre-existing static content and turn it into an interactive experience tailored to each student's level. Below, we can see that the teacher has entered a learning objective into Flint, along with a textbook chapter covering examples of time complexity as well as a YouTube video on the topic:

Learning objective:

Students should be able to identify the optimal time complexity (constant, logarithmic, linear, or quadratic) of an algorithm based on a description of a practical engineering problem. After the student gets it right, they should be given the code and should be able to write the time complexity using Big O notation.

YouTube | Big-O notation in 5 minutes

Extra customization

Based on the information provided by the teacher, Flint automatically creates an AI tutor that will give students examples of practical engineering problems and then ask students to identify the optimal time complexity.

Tutor type and initial prompt for this algorithm detective tutor.

Because the uploaded textbook chapter had examples given in Python, the AI tutor will also provide code in Python. However, the teacher can customize this behavior by using the “revise” feature to ask the AI to provide coding snippets in Java (or any other language) instead.

Revise feature request to make the examples in Java instead of Python

Student experience

Once students start a session with this AI tutor, they’ll immediately get practice in identifying time complexity based on real-life examples.

Student session example showing rendered code snippet generated by Flint.

Once students correctly describe the time complexity, the AI will provide them with a code snippet and will ask them to write the time complexity using Big O notation.

If the student needs extra help in understanding time complexity, they can ask additional questions to the AI, which can use graphing when appropriate to better explain the concept.

Student conversation example showing student asking for a visualization of the time complexities and a graph Flint generated to show them.

Extra customization

Based on the information provided by the teacher, Flint automatically creates an AI tutor that will give students examples of practical engineering problems and then ask students to identify the optimal time complexity.

Tutor type and initial prompt for this algorithm detective tutor.

Because the uploaded textbook chapter had examples given in Python, the AI tutor will also provide code in Python. However, the teacher can customize this behavior by using the “revise” feature to ask the AI to provide coding snippets in Java (or any other language) instead.

Revise feature request to make the examples in Java instead of Python

Computer Science

|

9th, 10th, 11th

O(n) review session with real life examples

Student session transcript example next to Flint-generated graph of various O(n) trajectories.

Teaching goals

Learning time complexity is a critical part of improving students’ algorithmic thinking skills.

Typically, teachers might have students read about comparisons between different time complexities (logarithmic, quadratic, etc.), along with example algorithms for each. Or, teachers may talk through examples with slides or by playing an instructional YouTube video.

With Flint, teachers can take pre-existing static content and turn it into an interactive experience tailored to each student's level. Below, we can see that the teacher has entered a learning objective into Flint, along with a textbook chapter covering examples of time complexity as well as a YouTube video on the topic:

Learning objective:

Students should be able to identify the optimal time complexity (constant, logarithmic, linear, or quadratic) of an algorithm based on a description of a practical engineering problem. After the student gets it right, they should be given the code and should be able to write the time complexity using Big O notation.

YouTube | Big-O notation in 5 minutes

Extra customization

Based on the information provided by the teacher, Flint automatically creates an AI tutor that will give students examples of practical engineering problems and then ask students to identify the optimal time complexity.

Tutor type and initial prompt for this algorithm detective tutor.

Because the uploaded textbook chapter had examples given in Python, the AI tutor will also provide code in Python. However, the teacher can customize this behavior by using the “revise” feature to ask the AI to provide coding snippets in Java (or any other language) instead.

Revise feature request to make the examples in Java instead of Python

Student experience

Once students start a session with this AI tutor, they’ll immediately get practice in identifying time complexity based on real-life examples.

Student session example showing rendered code snippet generated by Flint.

Once students correctly describe the time complexity, the AI will provide them with a code snippet and will ask them to write the time complexity using Big O notation.

If the student needs extra help in understanding time complexity, they can ask additional questions to the AI, which can use graphing when appropriate to better explain the concept.

Student conversation example showing student asking for a visualization of the time complexities and a graph Flint generated to show them.

Other Computer Science teacher testimonials:

"I can't emphasize enough how Flint has revolutionized my teaching. Flint has been an invaluable tool for introducing new concepts and assessing student understanding. My students have embraced Flint wholeheartedly. My high flyers love how they can deep-dive into course content with an AI expert. Other students who need more attention can get a one-on-one tutor to help with their specific needs."

Matthew Davis headshot

Matthew Davis

Computer science teacher at Episcopal

"Even as the initial novelty of Flint wore off, engagement has stayed exceptionally high. With any other activity, some top students want to move to more complex material, and others need more time on basics. As a teacher, you are stuck trying to find a middle ground. In Flint's activities, I can rotate as a facilitator and Flint automatically scales the assignments to each student's skill level."

Jake Kazlow headshot

Jake Kazlow

Computer science teacher at Westminster

Spark AI-powered learning at your school.

Sign up to start using Flint, free for up to 80 users.

Watch the video

Spark AI-powered learning at your school.

Sign up to start using Flint, free for up to 80 users.

Watch the video

Spark AI-powered learning at your school.

Sign up to start using Flint, free for up to 80 users.

Watch the video