I've never been on a podcast before. Probably because podcasts are for experts and entertainers. However, I fooled the good people at Beyond the Backpack into thinking I was one of those things. Check it out! https://www.youtube.com/watch?v=jasPeoPC7LU

I used to dread the post-unit data review. Not because the data wasn't useful — it absolutely is. But because pulling it together meant digging through individual reports, cross-referencing spreadsheets, and trying to hold a mental picture of 30+ students across multiple objectives. By the time I had the full picture, half my planning period was gone. That changed when I used Claude Cowork to turn my Chapter 17 Evidence of Learning reports into a live dashboard. -- What Is Cowork, Exactly? Cowork is Anthropic's desktop AI tool — think of it as Claude with hands. It can read your files, run tasks, and build things on your computer, not just in a chat window. I pointed it at my EOL data and asked it to build me something I could actually use. What came back stopped me cold. -- What the Dashboard Shows The artifact Cowork built surfaces everything I care about in one place: - Class-wide mastery rates by objective - Individual student performance across the unit - Gap patterns — which skills need reteaching vs. which are solid - Trend indicators so I can see where students improved or struggled most No more hunting through individual reports. No more mental math. "No more searching for specific reports — now my custom data is live at my fingertips." -- The Part That Changes Everything: It's Live Here's what makes this different from a one-time export or a static chart: the dashboard updates. Whenever I have new EOL data — a new unit, a re-assessment, a mid-unit check — I tell Cowork to refresh, and the dashboard reflects it. It's not connected to a cloud database. It's connected to me and my workflow. I control when it updates, and it updates completely. That means this isn't a tool I use once. It's infrastructure I build on. -- What This Means for Lesson Design and Assessment I'm still unpacking the implications, but here's what I'm already thinking about: Faster feedback loops. If I can see gap data the same day I run an assessment, I can adjust my next lesson before the window closes. That's a fundamentally different planning rhythm.

Grab the full World Builder activity on TPT What if your students didn't just study geography — they lived it? That was the idea behind World Builder, a four-part simulation activity I ran with my 9th grade World Geography class. The results? One coastal empire built entirely on rare earth wealth, a landlocked nation that immediately ran out of food, and at least one student who proudly announced their country had "become the most powerful region in the nation." -- How It Works World Builder runs across two class periods, structured in four parts. In Part 1, student pairs are randomly assigned a starter terrain — landlocked plateau, tropical island chain, arctic coast, river delta, and more — then spend 10 development points across six resource categories (farmland, coastline, rivers, minerals, freshwater, and forest), each available at three investment tiers. Every choice has a consequence the AI reveals in real time. In Part 2, pairs design their country's identity: flag, hand-drawn map, government type, national motto, currency, and national dish. It's creative, it's personal, and it makes the negotiation hit harder because now they actually care about their country. Part 3 brings two neighboring pairs together for a live negotiation over shared geographic resources — river access, trade routes, mineral deposits — brokered with the help of an AI game master that introduces a crisis after the deal is struck. Part 4 is individual reflection, with questions that escalate from recall to genuine geographic analysis. --The AI as Game Master — Not a Shortcut The real differentiator here is how students use the AI. It isn't answering questions or doing their thinking. It's playing the role of a dungeon master for the real world — responding to student decisions the way geography actually would, with tradeoffs, consequences, and complications they didn't see coming.

I just finished an Evidence of Learning report covering Chapters 15 and 16 of my 9th grade World Geography class — two periods, 40 students, four assessed components. When I shared it with admin, the most common question wasn't about the findings. It was: how on earth did you generate this? The answer is the Classroom Differentiation Machine. And I want to show you what becomes possible when a teacher has that pipeline running. -- What the EOL Report Actually Contains This wasn't a grade printout. The report surfaced patterns I couldn't have seen any other way: - A U-shaped class trajectory across four assessments — strong start on Indochina, a wall on Malay Archipelago, a rebound on China, and a moderate decline on the summative. - A recognition-versus-production gap quantified down to the percentage point — 97% on matching, 61% on essay. Same kids. Same week. - Tier-level effectiveness analysis showing which NWEA tiers are correctly placed and which students (P3-12, P3-06) need to move up or down for Chapter 17. - Seven students flagged for intervention — each with a specific reason, not just a low grade. Test-format mismatch. Handwriting barrier. Volatility suggesting an engagement issue. - Celebration of trajectories — kids like P3-20 (62→64→92→88) who don't show up on a traditional grade report because their growth lives between grades, not in the average. Try generating that from a spreadsheet of final scores. You can't. The data structure doesn't exist. -- Why Only the Differentiation Machine Could Produce This The Machine builds a pipeline. That's the part I think teachers miss when they see AI tools in isolation. Here's what the pipeline looks like for a single unit: 1. Common assessment taken by every student regardless of tier 2. Gap analysis mapping each student's missed questions to specific chapter objectives 3. Individualized remediation activity generated at their NWEA tier — matching for T1, compare-contrast for T3, evaluation for T4 4. Tier-aligned grading rubric that produces data the next step can use