Over the past few months I've been building an agentic teacher's assistant that handles a significant amount of my day-to-day tasks.
This tool connects to my school's learning management system and acts as a chatbot loaded with 83 atomic tools and skills: planning and posting lessons, assignments, assessments, rubrics. It can create, read, and update any content on Canvas, Google Docs, or Slides.
It can grade student work and provide feedback that is more helpful and comprehensive than what I can consistently produce by myself.
I have a pedagogical council of AI advisors that help me plan lessons, projects, and assessments. The council is made up of three voices patterned after Seymour Papert, John Dewey, and Maria Montessori. Papert pushes me toward constructionism and learning by making. Dewey keeps me honest about experience and inquiry. Montessori watches for student agency and the prepared environment. I give them a draft lesson, and the council reads it, argues with it, and hands back a revised version.
It knows Franklin's core philosophy and organizes learning around nine Transdisciplinary Competencies: skills that cut across every subject and define what it means to be a Franklin graduate.
The Serendipity Generator skill looks across all my colleagues' curricula and identifies transdisciplinary project opportunities aligned to student interests.
All of this happens in one chat. No copying or pasting. Once I approve a draft, I push it to Canvas. It cannot publish and that's a design choice. I want a final check before anything becomes viewable by students. Student names and identifiers are replaced with anonymous IDs before anything hits the model.
Because I built this as an AI Agent with small tools plus access to our LMS, it can combine them to express emergent capabilities it was not designed for.
When one of our science teachers unexpectedly had to leave mid-year, I generated a transition report for administration and the substitute: where each class was, what had been taught, what hadn't, and how each student was doing.
When the grade level deans needed a daily report on students who got D's or F's, I spun it up with a few prompts and a Slack bot that now automates it.
Department Leads used to spend hours each week checking every Canvas page for compliance with Franklin guidelines. I asked my tool to automate it. Now they get a Google Doc each Friday flagging any issues.
To see how a student is doing on their nine Transdisciplinary Competencies, I can pull every assignment and assessment they've ever done and curate a portfolio that demonstrates those skills.
I love building with AI and for AI Agents. In January, I started with a few small tools that could accomplish specific tasks. I linked them together and learned about Agent Native Architecture. Thanks,
@danshipper and
@every!
I realized that I was growing software rather than building it.
I am planting seeds and wondering: what will this become?