Monthly Archives: April 2025

Posted on by

Gen AI usage as superintendent – Reflections from Google – AASA ITC

For emphasis I am sharing a few use cases for Generative AI in this blog post

All content is actually my own and content from speakers (with their consent) via AI tools (glasses, iPad, phone, & other).

I took my “bespoke” notes – that were enhanced, reviewed, proofread and modified by various Gen AI tools and finally, with a prompt to Gemini, Using Canvas and 2.5Pro – see the prompt (unedited)

Is this a good blog post for my post? I’m Mike lubelfeld from mikelubelfeld.edublogs.org, Today, we are at GooglePlex in Mountain View, California. We are greeted by a Google For Education quote that reads, “Elevate education with simple, flexible, and secure tools.” The entire atmosphere is positive, composed, future-oriented, and innovative. I have visited GooglePlex before, and each experience has been as exceptional or more so than the previous one. From the imaginative furniture, billiards, micro and macro kitchens, G-Bikes, and the rich history to the electrifying energy of each learning session, the visit to Google is truly inspiring.

Then Gemini gave insights and feedback and a few suggestions for improvements – I then prompted Gemini to make the suggested edits … here is the Human inspired, Gen AI improved, blog post!

Okay, Mike, here is a revised version of your blog post draft incorporating the suggestions. I’ve focused on improving flow, clarifying the use of AI tools, adding structure with headings (using markdown), and slightly refining phrasing for conciseness and clarity.

Reflections from GooglePlex: AI, Innovation, and the Future of Education

(By Mike Lubelfeld, mikelubelfeld.edublogs.org)

Greetings from GooglePlex in Mountain View, California! Stepping onto the campus, we were immediately met with a powerful Google For Education quote: “Elevate education with simple, flexible, and secure tools.”This set the tone for an experience steeped in a positive, future-oriented, and innovative atmosphere. Having visited GooglePlex before, each visit seems to surpass the last – from the imaginative furniture and G-Bikes to the palpable energy in every learning session, it’s truly inspiring.

Our District’s Journey with Google Tools

Our school district has been leveraging Google’s tools for some time now, starting when Gemini was still known as “Bard.” As a Google For Education Advanced Workspace district, we actively employ a suite of tools including Gemini, Google’s NotebookLM, Vids, Veo, Deep Research, AI Studio, and more. Google is clearly concentrating heavily on generative AI, and the rapid advancements and daily improvements across their tool suite are remarkable.

This post, much like previous reflections, aims to share personal insights, journal entries, and “experience sharing” about the lessons learned and their broader implications.

Session 1: AI in Practice & What it Means for Education

Our day kicked off with an engaging session titled “AI in Practice & What it Means for Education.” We started with a light-hearted LLM exercise involving “sniglets.”

A sniglet is a word that isn’t in the dictionary but perhaps should be – often humorous and describing something nameless. We used Gemini (Gemini.Google.Com) with a prompt asking it to act as a superintendent and compose two humorous, education-related sniglets. (Sharing these creative outputs was a fun icebreaker!)

From there, we dove into the evolution of generative AI, tracing the path from traditional programming to neural networks and today’s large language models. A key moment highlighted was Google’s introduction of the Transformer (the “T” in GPT) back in 2017. Now, in 2024, we’re firmly in the era of multi-modality – integrating text, images, video, and audio. It was fascinating to hear how technology, like Osmo equipping computers with a sense of smell, is attempting to replicate human senses to better support us.

AI Adoption: Students vs. Teachers

We discussed the current landscape of AI adoption. A 2024 Digital Education Council report indicated that 86% of students are using AI tools. However, this usage contrasts sharply with teacher adoption rates. According to Education Week in October 2024, only 36% of teachers nationwide reported using AI tools. This gap highlights a critical area for professional development and support.

We also watched and discussed the impressive video “Airhead Made by Shy Kids,” created using OpenAI’s Sora video generation model, prompting thoughts on creative potential and ethical considerations.

Google’s Approach: AI Principles and Tools

Google emphasized its core AI principles: pursuing bold innovation while ensuring responsible development and deployment, fostering collaborative progress, and maintaining a sense of togetherness.

We explored SynthID, Google’s tool for watermarking AI-generated content, a crucial aspect of responsible deployment. The discussion centered on AI as a tool – like a hammer or calculator – and how we can create conditions where it effectively enhances learning and solves problems of practice, rather than simply being a novelty.

This led naturally to the importance of metacognition: understanding how we know what we know. In an age where knowledge is ubiquitous, developing the critical skills to discern, interpret, and effectively learn how to learn is paramount for our students.

Deep Dive: Harnessing NotebookLM

One tool we’ve explored extensively over the past few months is NotebookLM.Google.com. Building on insights from a previous post, we explored innovative ways to leverage this powerful resource.

As a practical demonstration, I used one of my own blog posts as a “source” within NotebookLM:

  • Source URL: https://mikelubelfeld.edublogs.org/2025/04/28/learnings-from-the-unfinished-unlearning-leader-112leads/

Using this source, NotebookLM helped generate an audio podcast summarizing the key takeaways.

Beyond NotebookLM, we also touched upon Deep Research and Gemini Canvas, which offer promising approaches for initiating research, coding, and fostering collaborative learning.

Peeking into the Future: Project Astra and AI Glasses

Looking ahead, Project Astra, a Google initiative exploring the future of AI assistants, was captivating. The potential integration with hardware like Google Glass, combined with multi-modality, hints at a revolutionary shift in human-computer interaction.

Real-World AI Application: Transcribing and Summarizing with Multiple Tools

Here’s a practical example of integrating AI tools during the event:

  1. Capture: I wore my Even Realities AI Smart Glasses during a session (with the presenter’s consent). I used the glasses’ Transcribe feature, which displayed the text on the lens in real-time and saved the full transcript via Bluetooth to an app on my phone.
  2. Initial Summary (Gemini): I copied the raw transcript from the Even Realities app and pasted it into Gemini (using the 2.5 Pro Experimental version) with a prompt to “summarize.”
  3. Refined Summary (ChatGPT): I then took Gemini’s summary and input it into OpenAI’s ChatGPT 4o-mini, prompting it to “make a concise summary of this summary of a meeting transcript suitable for inclusion in a blog post.”

Below is the AI-assisted, multi-step generated summary:

The discussion explores how generative AI is reshaping the workforce, drawing comparisons to past technological advancements such as the automobile and the personal computer, which disrupted certain jobs but also created new opportunities. Key points include:

  • AI and Jobs: AI may automate up to 30% of work hours, but like previous technologies, it is expected to create more jobs by shifting the types of roles available, particularly in areas requiring human skills.
  • Future-Ready Skills: Essential skills for future success include critical thinking, communication, creativity, adaptability, and social-emotional intelligence, referred to as “durable skills.” These are vital for navigating AI-driven changes.
  • Teaching Future Skills: Educators emphasize methods like project-based learning (PBL) and self-assessment to foster durable skills. Real-world PBL examples include adaptive technology creation and community collaboration projects.
  • Google’s Educational Initiatives:
    • Grow with Google: Offers career certificates and AI courses.
    • Be Internet Awesome: Teaches digital citizenship and AI literacy to younger students.
    • AI Quests: A gamified program helping middle schoolers build AI models for social good.
  • Partnership Ideas: Suggestions for Google included integrating digital citizenship in Google Classroom, addressing tech access gaps, and offering simulations for practicing durable skills.

This summary underscores the importance of adapting education to future workforce needs, where AI and human-centered skills intersect.

The Future of Education: Policy and Learning Science

Policy is evolving rapidly. As of our meeting (late April 2025), 26 US states have formal AI policies for education, while 24 do not. Google shared insights on creating impactful AI tutors, grounding their work in 5 Learning Science Principles:

  1. Inspire Active Learning
  2. Manage Cognitive Load
  3. Deepen Metacognition
  4. Stimulate Curiosity
  5. Adapt to Learner

Evaluating AI tools against these principles provides a meaningful framework, especially from an education perspective focused on privacy, data security, and responsible use.

We also got a glimpse of Project Mariner, an experimental “agentic” workflow automation tool designed to assist after research is completed. Imagine this workflow: a student submits a quiz, AI provides rubric-based feedback, an email goes to the parent, and an action plan is co-created with the student. This isn’t science fiction; it’s becoming reality.

Developing Skills: Google for Education Programs

Google highlighted resources available for educators and students:

  • General Resources: Edu.google.com
  • Professional Development: Training & Certifications
  • Digital Citizenship (Grades 2-6): Be Internet Awesome
  • Leadership Development: AASA & Google ELP Partnership (Ed Leadership Program)

Session 2: Fostering a Culture of Innovation

Konner Brewer, Google Product Manager and Stanford Lecturer, led a fantastic session on Google’s culture of innovation. A key takeaway was Project Aristotle, Google’s internal research which found that psychological safety is the single most important factor for high-performing, innovative teams.

Google’s values underpin this:

  • Respect the User: Understand their deep needs.
  • Respect the Opportunity: Act responsibly with resources.
  • Respect Each Other: Foster psychological safety.

The session drew heavily from the Stanford “d.school” design thinking elements:

  1. Need finding: Empathize (understand the verb – e.g., “I need to hydrate“) and Define (avoid locking into a solution too early – e.g., “I need a glass of water”).
  2. Leveraging: Ideate based on existing strengths and resources.
  3. Failing Fast: Prototype and Test small, learn quickly, and iterate.

Another AI Application: Audio Transcription and Summarization

For another insightful session, I used a different AI workflow:

  1. Capture: Recorded the audio using the Apple iOS Voice Memo app.
  2. Transcription: Used the Apple Intelligence feature within the Notes app to transcribe the audio recording.
  3. Initial Summary (Apple Intelligence): Used Apple Intelligence within Notes to summarize the lengthy transcript.
  4. Refined Summary (Gemini): Finding the Apple summary less concise than desired, I pasted the full transcript into Gemini 2.5 Pro Experimental for a more condensed summary.

Here is the Gemini-generated summary of the 50-minute session on innovation:

  • Psychological Safety is Key for Innovation: Google’s Project Aristotle found psychological safety (feeling safe to take risks/be vulnerable) is the most critical factor for effective teams, more vital than individual high performers. Innovation needs a blameless culture focused on learning from failures.
  • Google’s Innovation Principles: Respect the user (understand deep needs, like the Oreo story example), respect the opportunity (act responsibly), and respect each other (foster psychological safety/diverse voices).
  • Embrace Failure & Quantity: Innovation has a high failure rate (~95%). Google learned from failures (Loon, Glass). Generating many ideas (quantity yields quality) via methods like 20% time (Gmail’s origin), incubators, and external ventures is crucial.
  • Design Thinking Framework:
    • Need Finding: Start with the user need (verb), not a pre-defined solution (noun). Understand real challenges (student engagement, change resistance).
    • Leveraging: Utilize existing resources/skills (like Hermès moving from saddles to bags via leather skills).
    • Failing Fast: Test ideas quickly/small scale, learn, iterate (Google’s “dogfooding”).
  • Real-World School Examples (Glen, NJ Superintendent):
    • Mr. Rogers Project: Paired students needing experience with businesses needing social media help.
    • Swim Lessons/Lifeguarding: Identified unmet needs and built programs incrementally.
    • Farmer’s Market: Leveraged school space/student interest for entrepreneurial opportunities (“Pirate Pickles”).
  • Overall Message: Successful innovation in education requires deep need understanding, safe experimentation environments, leveraging resources, learning from failure, starting small, and community connection.

Wrapping Up: GooglePlex Tour and Reflective Thoughts

The day also included a walking tour of the GooglePlex global headquarters – always a highlight! The serene grounds, history, outdoor art, and intentional building design (even a dinosaur!) offer much to absorb.

This was an action-packed, high-energy, heavy-thinking day with a ton to unpack and process! I’m energized to bring back numerous ideas, affirmations, and opportunities for growth to our organization. A huge thank you to AASA and Google for this incredible experience.

Next up on the journey: our visit to Stanford… stay tuned for more!

Thanks for reading! What are your key takeaways or questions about AI and innovation in education right now? Share your thoughts in the comments below!

Posted on by

Learnings from the Unfinished & Unlearning Leader #112Leads

I’m sometimes thought of as the UNLearning Superintendent, based on my and Nick Polyak’s 2017 book, The Unlearning Leader: Leading for Tomorrow’s Schools Today … but this week I’m writing as the “Learning Leader” as a superintendent on a professional development conference with our national leadership group, the AASA!

The AASA Innovation and Transformation Consortium spring 2025 convening is being held in San Francisco/Bay Area California, featuring Google and Stanford.

The Superintendent’s Association (AASA) has been supporting superintendent leadership growth and development for over a century and a half. As a full-time public school superintendent for the past 15 years, I have benefited from numerous visionary leadership offerings.

This convening appears to be one of the best ever, with thoughtful planning and anticipation of the current needs of leaders across the nation.

Educators and school leaders from various states, including Illinois, West Virginia, Texas, Washington, Pennsylvania, Ohio, Wisconsin, California, New Hampshire, District of Columbia, Virginia, New Jersey, Maryland, and New York, will bring diverse and unique perspectives and approaches.

One of the key questions we will explore, discuss, analyze, and “work through” is how schools should effectively plan, implement, and evaluate innovation to achieve meaningful change. Additionally, the event will cover various topic areas, including AI in Education, Research and Innovation, Policy, Best Practices, and more.

I’m thrilled about the opportunity to learn at Google and Stanford! In this blog post, I’ll share some exciting highlights and insights.

One notable development nationally is the recent Executive Order issued by the President to promote AI literacy in schools. I was curious about how this initiative would be implemented, so I took the text of the Executive Order and used Google’s Notebook LM AI tool to generate a frequently asked questions document. I’ve included the document below.

Frequently Asked Questions on Promoting AI Literacy (generated by artificial intelligence from the actual text of the Order)

Q1: What is the primary goal of this initiative regarding artificial intelligence (AI) education?

The central aim of this initiative is to promote AI literacy and proficiency among Americans of all ages. To achieve this, the initiative aims to integrate AI education into K-12 schooling, provide comprehensive training for educators, and foster early exposure to AI concepts and technologies. Ultimately, the goal is to develop an AI-ready workforce and cultivate the next generation of American AI innovators, ensuring the United States maintains its global leadership in AI.

Q2: How will this initiative integrate AI into the education system, particularly at the K-12 level?

The initiative seeks to integrate AI into K-12 education through several strategies. These include establishing public-private partnerships to develop online resources focused on foundational AI literacy and critical thinking skills for students. Additionally, the initiative will identify existing federal AI resources to support partnerships with state and local educational agencies. Furthermore, the Secretary of Education will issue guidance on using grant funds to improve educational outcomes through AI-based instructional resources, tutoring, and college/career pathway exploration.

Q3: What specific measures will be taken to equip educators to teach and utilize AI?

To enhance AI training for educators, several steps will be taken. The Secretary of Education will prioritize the use of AI in teacher training grant programs, focusing on areas such as reducing administrative tasks, improving teacher training and evaluation, providing professional development to integrate AI fundamentals across subjects, and offering training in foundational computer science and AI. Additionally, the National Science Foundation and the Department of Agriculture will prioritize research and programs to create teacher training opportunities for effectively integrating AI tools and modalities in classrooms.

To foster student achievement and innovation in AI, a Presidential Artificial Intelligence Challenge will be established. This challenge will feature multiple age categories, distinct geographic regions, and diverse topical themes to encourage broad participation and interdisciplinary exploration of AI applications. The challenge aims to highlight student and educator accomplishments in AI and promote collaboration between government, academia, philanthropy, and industry.

Partnerships are crucial for the success of this initiative. Public-private partnerships with AI industry organizations, academic institutions, and non-profit entities will be sought to develop K-12 AI education resources. Collaboration between educators, industry leaders, and employers is also emphasized to create educational programs that equip students with essential AI skills. Furthermore, the initiative encourages collaboration between federal agencies and private sector entities to support the Presidential AI Challenge.

In the context of AI, the initiative will address workforce development and lifelong learning.

The initiative recognizes the significance of workforce development and lifelong learning. The Secretary of Labor will prioritize the development and growth of AI-related Registered Apprenticeships to increase their participation. Funding will be utilized to engage industry and facilitate the creation of these programs. States and grantees will be encouraged to use Workforce Innovation and Opportunity Act (WIOA) funds to develop AI skills and support work-based learning. Efforts will also be made to identify and promote high-quality AI skills education coursework and certifications nationwide, including opportunities for high school students.

The newly established White House Task Force on Artificial Intelligence Education will be responsible for implementing the policy of promoting AI literacy and proficiency. It will coordinate federal efforts related to AI education, including establishing plans for and overseeing the Presidential AI Challenge, fostering public-private partnerships, and identifying existing federal AI resources to support educational initiatives. The Task Force will be chaired by the Director of the Office of Science and Technology Policy and will include representatives from various federal departments and agencies.

This initiative aims to maintain the United States’ leadership in the AI field by focusing on early and comprehensive AI education. It seeks to equip American youth and the broader workforce with the necessary skills and understanding to use and create future AI technologies. By fostering AI competency, sparking curiosity and creativity, and nurturing the next generation of AI innovators, the initiative aims to propel the nation to new heights of scientific and economic achievement. This will ensure that the United States remains a global leader in the rapidly evolving field of artificial intelligence.

So, with my own professional learning journey as a superintendent, my open mind, and my eagerness to learn, this new directive from the federal government, and a local follow-up to a survey in the fall on Gen AI usage and needs in the district, everything is coming together serendipitously!

The ITC convening from the AASA offers a variety of thought-provoking sessions, workshops, opportunities, and anticipated takeaways.

At the first set of workshops, the theme was “Inspire, Innovate, Transform: Leading the Charge in Educational Excellence.” Over 100 of us gathered to learn, lead, and grow!

Our first speaker was a student at Stanford University! She’s a freshman in college at Stanford, but when she was in high school, she was a student school board member at Leyden High School in Franklin Park, Illinois. Our keynote address was “Innovation Through the Student Lens: From PreK-12 to College and Beyond,” delivered by Joyslyn Maldonado. Thank you to Joyslyn for her powerful and impactful presentation! She shared her experiences as a student board member.

Who do we work for? Students.

Why do we make policy? Student learning.

Why do we learn innovative practices? For students.

Why are we gathered here in Silicon Valley? For students.

It was truly impactful for us to begin our learning journey together with a student from Stanford. Consider incorporating student voice into your board’s decision-making process. Explore various ways to involve students in leadership roles. In our 2018 book, titled “Student Voice: From Invisible to Invaluable,” Nick Polyak, PJ Caposey, and I provide insights into how school leaders can effectively incorporate student voice into their leadership strategies. Joyselyn’s keynote speech exemplifies the real-life impact of student voice and empowerment.

She also discussed the use of AI at Stanford. Each syllabus now includes a notice about AI usage, emphasizing its role as a tool to enhance learning outcomes. AI is encouraged as a supportive resource, a suite of tools, and even a “TA” (teacher assistant) for teaching coursework and curriculum. Tools like Notability are used to summarize and create quizzes.

Following her remarks, we engaged in a question-and-answer session about the use of AI, being a student on a school board, and the overall experience of being a recent K-12 student and a current college student in today’s world. Her speech served as a powerful reminder of the purpose of our learning and the importance of continuous improvement as educational leaders.

Dr. Dave Schuler, the Executive Director of the American Association of School Administrators (AASA), also shared the Public Education Promise, which outlines five key tenets:

1. Student-Centered Education: Learning that prioritizes the needs and interests of students.

2. Learning: Emphasizing the development of real-world skills and knowledge.

3. Teaching: Ensuring that teachers provide effective instruction and support students in their learning journey.

4. Attracting and Retaining Top Educators: Seeking and retaining highly qualified and motivated educators.

5. Family and Community Connections: Fostering strong relationships between schools, families, and communities to support student success.

Isabelle Hau, the Executive Director of Stanford’s Accelerator for Learning, delivered a talk titled “Welcome to the Learning Valley” after our student keynote speaker.

Silicon has been given a new name. Valley = LearningValley

We envision a world where research-driven innovations lead to transformative change, making effective and joyful learning a vibrant reality for all.

Google, founded at Stanford University, continues its legacy of research in education. Our convening is related to Stanford and the Valley becoming the new epicenter for the future of learning. Stanford boasts 122 Unicorn Founders, with contracts, compared to MIT’s 87.

Stanford’s pioneering work in Artificial Intelligence in the 1950s has been a cornerstone of its research. When ChatGPT was launched in November 2022, none of us could have anticipated the profound impact it would have within the next three years. Remarkably, 35% of all queries on ChatGPT are related to homework. However, it’s important to note that the Large Language Model (LLM) was not specifically designed for educational purposes. Despite this, ChatGPT and other large LLMs are increasingly being utilized in and for educational settings.

Let’s bridge the gap between the need for tutoring, its effective use, and the support provided to tutors. The Stanford University Human-Centered Artificial Intelligence Institute (HAI) is partnering with the Accelerator to develop a special tutor support “bot” informed by tutoring videos, effective practices, research, data, and support for tutors. Existing research indicates that novice tutors can have a significant impact on the students they tutor, and the AI will assist the tutor in delivering effective tutoring sessions. AI Literacy, Tutoring, and Feedback will be key focus areas during our in-person visit to Stanford. At Stanford, AI is not meant to replace educators but rather to empower and augment them.

Other notable projects include:

– Journify (student-led): “Every IEP goal is a journey… wow!”

– Autism Glass Project: Provides emotional regulation support and information.

– Teacher training with ISTE and the Generative AI Education Hub.

– Dr. Hau’s concept of “Educator Centric and Education Centered AI.”

– Cross-sector collaboration: Learning through creation with the GEN AI Seed Grant and AI Tinkery (using AI for creativity).

Magma Math:

– From innovation to impact: How to transform math classrooms into thinking classrooms.

– In D112, we use Magma Math at the middle school level!

– EdTech Space/AI/Learning/Support/Partnership: Move towards conceptual understanding!

 

Stay tuned as I reflect, journal, blog and share my learning and unlearning! Next post will feature Google and Stanford experiences!

Posted on by

Unlearning – A Podcast Interview on The K-12 Change Equation

Recently I had the honor of sitting with Dr. Leila Nuland and Dr. Mort Sherman! Leila is a new friend and Mort is a longtime friend! We discussed my first book, The Unlearning Leader: Leading for Tomorrow’s Schools Today, experiences of the past few years, and a call to action that I share on the podcast, here in the blog, and in my latest book with Nick Polyak, coming out later this year, Leading for Tomorrow’s Schools Today!

If you have some time, listen to the interview and let me know what you think in the comments! I have an AI-generated summary of the podcast as well. I took the YouTube transcript, copied and pasted it into Magic School AI, used the YouTube summarizer app, and asked for a one-page summary. I then put the summary from Magic School AI into Chat GPT for a spelling check!

 

Sharing the audio podcast and a summary of the transcript follows

⸻

In this episode of The K12 Change Equation, Dr. Leila Nuland and Dr. Mort Sherman interview Dr. Mike Lubelfeld, a superintendent and author, focusing on the concept of unlearning as a vital component of effective leadership. The discussion highlights the current challenges faced by public education amidst discussions about its dismantling and the need for state and local control.

Dr. Lubelfeld, co-author of The Unlearning Leader, emphasizes the importance of unlearning outdated practices to adapt to modern educational demands. He recounts a pivotal moment from a 2017 conference where a futurist illustrated how societal perceptions can lag behind factual developments, using the evolution of yield signs and the medical community’s delayed acceptance of the H. pylori bacteria as causes of ulcers as examples.

The interview reveals how Dr. Lubelfeld’s experiences as a superintendent have been shaped by events such as the Uvalde tragedy, which prompted a reassessment of safety protocols in schools. He explains how his district had to shift from complacency to a proactive stance in ensuring student safety following this incident, reinforcing the need for leadership that can adapt and respond effectively to crises.

The conversation also delves into the role of partnerships in enhancing school safety and community support. Dr. Lubelfeld advocates for networking among educational leaders and leveraging local resources to foster a culture of innovation rather than compliance. He emphasizes the importance of building relationships with local authorities and mental health professionals to create a seamless support system for students.

As the discussion progresses, Dr. Lubelfeld addresses the challenges of funding and the impact of federal policies on public education. He expresses concern over the potential loss of federal support and advocates for local solutions that prioritize student well-being and educational equity.

The episode concludes with a call to action for educational leaders to embrace unlearning as a pathway to innovation and adaptability. Dr. Lubelfeld encourages leaders to challenge existing structures and work collaboratively to create an educational environment that meets the evolving needs of students.

Overall, this episode underscores the necessity of unlearning in leadership to drive meaningful change within educational systems, advocating for a future-oriented approach that prioritizes the needs of students and the community.

⸻