Sketchbook Tags

A way to browse the AI Sketchbook laterally rather than by section. Useful when the pattern you care about is something like writing, fabrication, archives, or source evaluation rather than whether a sketch started in teaching or research.

Below are the tags currently in use across sketchbook post pages. As the sketchbook grows, this should become a more useful way to move across related ideas.

All 3D printing 1 AI literacy 1 agentic AI 2 argument 1 big data 1 fabrication 1 filter bubbles 1 interpretation 1 maps 1 material culture 1 model comparison 1 paleography 1 parameters 1 philosophy 1 prompting 1 remix 1 research skills 2 seminar 1 source evaluation 2 tactile 1 vibe coding 1 writing 1

Showing all sketchbook posts with tags.

Apr 2026 rough activity 20–30 min in class upper-div / grad
Argument Audit

Argument Audit

writingargumentseminar

Key questionHow can AI help sharpen writing skills instead of replace them?

ActivityStudents use AI-generated objections to test whether a thesis is vague, vulnerable, or genuinely persuasive.

What students learn
  • the difference between tone and analytical precision
  • what makes an objection substantive vs. generic
  • how vague writing produces vague critique
Apr 2026 refined activity 30–40 min in class any
Citation Test

Citation Test

source evaluationfabricationresearch skills

Key questionHow can AI output help students learn scholarly integrity?

ActivityStudents verify AI-generated citations one by one and turn fabricated sources into a lesson about evidence and authority.

What students learn
  • why polished prose is not evidence of accuracy
  • how hallucination happens and why it's convincing
  • verification is a scholarly habit, not a library ritual
Apr 2026 tested data work 30–60 min any
Generate 3D Prints from 2D Drawings

Generate 3D Prints from 2D Drawings

3D printingmaterial culturetactile

ExperimentCan AI transform a historical line drawing into a 3D-printable file, adding a tactile dimension to research that images alone can't provide.

Results
  • generating 3D-printable files from 2D historical images
  • reconstructing material culture objects for research
  • incorporating tactile elements into research presentations
Apr 2026 refined activity 45–60 min in class any
Historical Source Evaluation

Historical Source Evaluation

source evaluationfilter bubblesresearch skills

Key questionStudents prompt AI to analyze a short newspaper article from 1892 and compare results across accounts and incognito mode.

What students learn
  • how context shapes historical interpretation
  • what filter bubbles look like in practice
  • the difference between pronouncing and puzzling about sources
Apr 2026 tested processing sources downloaded document images; two hours to set up; automated run of ~12hr/register researcher
Medieval Handwriting Recognition Workflow

Medieval Handwriting Recognition Workflow

big datapaleographyagentic AI

ExperimentTo create an AI agent to work with Gemini and Claude to bulk process 300 images of archival documents and enable full-text search of medieval handwriting.

Results
  • building an agentic pipeline for bulk document processing
  • combining multiple LLMs to improve transcription accuracy
  • enabling full-text search of handwritten archival sources
Apr 2026 tested data work less than 1 hour any
Photos to Map Pins

Photos to Map Pins

vibe codingmapsagentic AI

ExperimentCreate an interactive map with pins for hundreds of photos, using GPS metadata already embedded in your phone's images — in under an hour.

Results
  • extracting GPS metadata from image files
  • building a map visualization with AI-assisted coding
  • presenting geolocated data in a public-facing format
Apr 2026 tested assignment 1–2 hours out of class undergrad / grad
Remixing Plato

Remixing Plato

philosophyremixprompting

Key questionHow can AI help translate ideas into contemporary culture?

ActivityStudents remix a Platonic dialogue into modern garb using AI to investigate how conversations of authority evolve over time.

What students learn
  • what AI can and cannot preserve in philosophical argument
  • how form and genre reshape meaning
  • that prompting requires the same clarity as writing
Mar 2026 rough activity 20–30 min in class any
What Does Cilantro Taste Like?

What Does Cilantro Taste Like?

model comparisonparametersAI literacy

Key questionHow to introduce students to the basics of AI output differences?

What students learn
  • AI is a spectrum of models, not one fixed thing
  • how temperature, token limits, and sampling shape output
  • what training data has to do with what a model knows