James Cantonwine has long wished teachers working in his district鈥檚 smaller schools of 250 students or less got the kind of personalized instructional coaching available to 糖心动漫vlog at the district鈥檚 larger campuses.
So Cantonwine, the director of research and assessment for the 9,000-student Peninsula school district near Seattle, used artificial intelligence to create the next best thing: LessonLens, which critiques teachers鈥� lessons based on recordings they upload to the tool.
LessonLens was inspired in part by a software demo Cantonwine saw that gave teachers feedback on the number of open-ended questions they asked in classes (which can spur creative thinking) compared with close-answered ones (where a simple 鈥測es,鈥� 鈥渘o,鈥� 鈥渢rue,鈥� or 鈥渇alse鈥� will suffice.)
鈥淎nd I thought, that鈥檚 really cool, but [it] also seemed like it left a lot of value on the table,鈥� Cantonwine said.
He believed AI could offer teachers more detailed feedback to help them reflect on instructional practice鈥攚ithout the feeling of judgment that comes with a human critique, even from a supportive coach.
Teachers can upload videos of their lessons to the tool, then select a set of guidelines against which they want to be measured.
Options include popular blueprints for best practice, such as Charlotte Danielson鈥檚 Framework for Teaching, Doug Lemov鈥檚 , or , as well as the district鈥檚 own instructional guidelines.
A biology teacher, for example, uploaded a video of her lesson on DNA to LessonLens and asked for feedback on how closely she adhered to what the district considers best instructional practice.
LessonLens complimented her for encouraging peer collaboration and providing clear directions but suggested she consider assessing how well individual students understood the lesson, as opposed to asking questions of the whole class.
One teacher pursuing her asked LessonLens to evaluate a lesson she plans to submit to earn the credential.
Use of the tool is 鈥渢otally optional,鈥� and not part of a teachers鈥� performance evaluation, Cantonwine said. District leaders can see how many teachers used it but not who. And they can鈥檛 access the feedback the tool provides, though some teachers have shared it voluntarily to help Cantonwine test and refine the platform.
The lack of visibility for district and school leaders 鈥渨as deliberate,鈥� said Cantonwine, a former middle school science teacher who thought back to his own experiences with coaches in designing the tool.
鈥淥ne of the big challenges for any instructional coach is: How do you make sure that the teacher understands that you鈥檙e not big brother? That you鈥檙e not there to spy on behalf of the principal, but that you鈥檙e there to help a colleague get better?鈥� Cantonwine said. 鈥淎nd so, if we鈥檙e going to have an AI tool help with coaching, it鈥檚 got to be able to do the same thing.鈥�
Vibe coding can be problematic but can pay dividends
Cantonwine developed the tool using Claude Code, a widely available AI coding application. (Competitors include: Codez, Cursor, Replit, and Loveable.)
The approach, known as 鈥渧ibe coding,鈥� allowed the district to create a coaching platform that鈥檚 more customized鈥攁nd cheaper鈥攖han anything available on the open market.
Tools created using vibe coding can be glitchier and more prone to security vulnerabilities than those coded by humans, experts say. But district leaders with significant computer science expertise may be able to alleviate those problems.
Cantonwine doesn鈥檛 have that sort of background, but he鈥檚 collaborated closely with Kris Hagel, the district鈥檚 chief information officer, and other staffers with deeper coding experience.
The district has created a range of other tools using vibe-coding. One is a tool that can comb the internet for scholarships that Peninsula students may be eligible for and add the information to district communications and postsecondary planning kits for kids and families. Another is an app to help parents compare Peninsula鈥檚 academic performance with that of other Washington state districts with similar demographics.
Cantonwine knows LessonLens has a few flaws. For instance, when one teacher submitted an audio file of her lesson, as opposed to a video, the tool told her that she needed to stand closer to students or move about the room more.
The teacher had, in fact, used that 鈥減roximity鈥� strategy, but LessonLens wasn鈥檛 able to pick up on that when it had no visuals to analyze and made the critique without the relevant information.
What鈥檚 more, as far as Cantonwine knows, LessonLens has mostly been used by some of the district鈥檚 instructional high fliers.
He鈥檚 not sure yet how the tool would handle a lesson that truly flops鈥攐r whether a teacher would even want to record and share their failures, no matter how much privacy they鈥檙e guaranteed.
鈥淚 don鈥檛 think there鈥檚 an authentic way for me to grab a sample from a teacher who鈥檚 really struggling in the class in the way I kind of wish I could,鈥� in order to test how the tool would respond, Cantonwine said.
But even if LessonLens needs refining, he鈥檚 excited about the tool鈥檚 ability to provide 鈥渁 very Peninsula-specific version鈥� of PD.
鈥淚t鈥檚 not something we鈥檇 be able to buy off the shelf,鈥� Cantonwine said.
