Campfire Session — Flint Analytics

Discover how teachers and students use AI to transform Computer Science learning with Flint with tutors, simulations, analytics, and student-created activities.

Lulu Gao, Head of Teacher Experience at Flint | LinkedIn

In this Campfire Session, we explored how teachers are using Flint’s chats, activities, and analytics to create more intentional learning experiences and get clearer visibility into student understanding. We walked through how to design a Flint activity with Sparky, how to manage and duplicate activities across classes, and how to use analytics—from individual sessions to full workspace data—to identify learning gaps, support students, and guide instruction.

Content covered in this session includes:

• How chats and activities work in Flint, and how teachers use Sparky to draft, simulate, and refine activities before assigning them.

• Best practices for activity management, including sharing via link, duplicating for multiple sections, and moving activities across groups while preserving student sessions.

• A tour of Flint’s four analytics layers—session, activity, group, and workspace—and how each one helps teachers spot strengths, find gaps, and flag students who need attention.

• Using analytics in practice for end-of-term reviews, parent meetings, comment writing, supporting multilingual learners, and tracking growth over time.

• How rubrics shape AI feedback, including tips for building clear criteria and using exemplars to improve accuracy.

• Teacher-requested enhancements, such as class-wide learning gap detection, trend data, richer visualizations, student skill tracking, and more robust group analytics.

• Creative ways educators use groups beyond traditional classes, like Model UN, robotics, and long-term projects—to monitor progress and keep everything organized.

Slides from the presentation can be found here.

Got more questions, comments, or feedback for this topic? Feel free to raise them within the Flint Community.

Join our next Campfire Session 🏕️

Subscribe to our events calendar to be notified when upcoming Campfire Sessions and other Flint events get scheduled.

See Events Calendar

Introduction • 00:00

• Lulu introduces the session and agenda.

Ice-breaking news • 01:41

• An ice-breaking news segment discusses AI-powered textbooks in South Korea and their rollout, which was rolled back amid concerns.

• Reaction to the South Korea AI textbook situation is mixed, noting political leadership changes, negative feedback, data privacy concerns, inaccuracies, and increased workload.

Overviewing Flint • 5:11

• Sparky activity builder is demonstrated for an invasive species project and customized classroom prompts are created.

• A live preview and simulation help verify the activity flow, with steps to save and share the activity with students via a link.

• The activity prompts adapt through student feedback to reduce verbosity and tailor questions for sixth graders.

• Lulu explains how to assign activities to a class or group to enable analytics coverage.

• It is demonstrated that moving an activity between groups or classes moves all associated sessions and updates group settings for future interactions.

Activity and group analytics • 14:17

• The analytics overview is introduced, detailing that individual sessions show strengths, areas for improvement, and provide a full transcript for review.

• Analytics access is shown in various locations depending on screen size and is discussed as a key feature to view strengths and improvements.

• Chat analytics are described as informative but buggy due to the volume of data, with a note on the natural limit of information AI can process.

• Follow-up activity recommendations are explained as based on activity settings and the grading rubric, with considerations for targeted vs. group sharing and student-created follow-ups.

• Additional context on how Sparky uses data to provide next steps and how analytics can serve as a data analyst and teaching assistant for teachers and administrators.

Survey and shareout • 26:45

• A poll is proposed and a link is shared for participation, including options for those on laptops.

• Discussion of Flint's LMS integration is clarified as rostering-based, automatically creating groups, assigning teachers, and adding students.

• Emma Bagg requests guidance on rubrics, assessment, and exporting results as a list or Excel file.

• Group analytics ranking is discussed as a priority to understand which analytics areas to focus on.

• Evan Sayles highlights the value of first-pass identified learning gaps for an entire class or assignment, offering quick insights.

• Sparky’s grading uses are discussed, including as a moderator for grades and as a checkpoint against bias.

• Concerns about AI grading accuracy are raised; criteria refinement and rubrics are used to align AI outputs with expectations.

• Interest in enhanced student profiles combining existing data inputs, sparky learnings, and potential input from students, teachers, and parents.

• Agreement on the value of tracking objective progress over time and the usefulness of data in informing instruction and teacher collaboration.

Craig Griebenow on Flint analytics • 46:29

• Craig Griebenow explains how analyzing activities and groups can inform instructional adjustments and benchmarking trends across classes.

• Craig describes using Flint for end-of-term analytics, spacing activities, and providing targeted, personalized feedback to improve student performance across subjects.

• Lulu emphasizes the value of visibility and examples of sharing student conversations with parents to illustrate specific struggles and improvements.

• Craig discusses a new-to-school student in grade 10 with English gaps, leveraging Flint to close gaps and communicate progress to parents, demonstrating impact on confidence and engagement.

Conclusion • 55:33

• Lulu shares QR codes for people to check out the Campfire Calendar, Flint's Instagram (which has a bunch of teacher-facing content), and the Flint Community.