A working collection of AI teaching agent recipes for Pamplin faculty. Each recipe is a starting point for an agent you can build in any major platform — Microsoft Copilot, ChatGPT, Claude, or Gemini. Browse by family, pick a recipe that fits, copy the fields into your platform, and you're running.
In-class activity engines
Agents that drive the dynamic things that happen in class — roleplays, debates, group exercises, structured activities.
The Stakeholder Roleplay Partner
Plays a specific stakeholder — a CFO, customer, regulator, hotel guest, founder — for students to interview, negotiate with, or pitch to in class.
Recipe 1.2The Live Case-Discussion Facilitator
Runs a structured case discussion in class — opens with framing, calls on perspectives, surfaces tensions, debriefs at the end.
Recipe 1.3The Structured Debate Moderator
Runs a two-sided debate in class — assigns positions, prompts each side, plays devil's advocate, synthesizes the strongest arguments.
Recipe 1.4The Small-Group Exercise Generator
Produces a fresh small-group exercise — task, materials, time budget, debrief questions — tailored to the day's topic and class size.
Recipe 1.5The Hands-On Data Activity Builder
Generates a realistic, made-up dataset (CSV-shaped) plus an analysis task and discussion questions, for use in quantitative or analytics courses.
Recipe 1.6The Think-Pair-Share Question Engine
Produces a sequence of think-pair-share prompts at varying cognitive levels for a 50-minute class session, paced to fit the lecture flow.
Student-facing always-on agents
Agents you build once and students use throughout the semester. Higher build effort, much higher leverage per build.
The Course FAQ Answerer
Grounded on a syllabus and course documents; answers student logistics questions and refers back to the human instructor when the answer isn't in the sources.
Recipe 2.2The Concept Tutor (No-Answers, Just Understanding)
Helps students build conceptual intuition — analogies, walkthroughs, "what does this mean" reframings — explicitly without giving away problem solutions or doing graded work.
Recipe 2.3The Adaptive Concept-Practice Partner
Asks students conceptual questions, listens to their answers, adjusts follow-ups based on what the student understood — a Socratic practice partner students use before exams.
Recipe 2.4The Reusable Course Assistant
Grounded on a faculty member's course materials — slides, readings, syllabus, past assignments — that students use throughout the semester for review and asynchronous study support.
Discussion and case-method
Agents that help with case-method teaching and discussion-based formats.
The Discussion Question Generator
Takes a reading and produces a tiered set of discussion questions: opening, probing, application, meta-questions about the reading itself.
Recipe 3.2The Socratic Case-Method Facilitator
Helps faculty rehearse a case-method discussion before class — plays a skeptical student, surfaces where the discussion will go off-track.
Recipe 3.3The Case-Discussion Debrief Synthesizer
Takes notes from a case discussion that just happened and synthesizes a debrief document students can review afterward.
Course architecture and conversion
Agents that help you redesign or restructure a course at the syllabus / module / format level.
The Course Format Converter
Converts a course from one format to another — in-person to async online, semester to compressed, lecture-heavy to flipped — preserving learning outcomes while restructuring delivery.
Recipe 4.2The Syllabus Modernizer
Takes an existing syllabus and produces a revised version — clearer learning objectives, modernized tone, aligned assignments, updated policies — while preserving the faculty member's voice.
Recipe 4.3The Module Architect
Helps faculty design or restructure a course module from scratch — outcomes, sequence, in-class activities, assessments, materials list.
Assessment and feedback
Agents that help with rubrics, formative checks, and feedback voice.
The Rubric Builder
Interviews the faculty member about an assignment and produces a rubric with clear performance levels and criteria.
Recipe 5.2The Formative Check Generator
Produces a short formative-assessment instrument calibrated to a topic and student level, with explanations for why each item tests what it tests.
Recipe 5.3The Feedback Tone Matcher
Helps a faculty member calibrate written feedback on student work — paste your draft and a sample of how you usually write, get suggestions that match your voice.
Examples, cases, and content
Agents that generate teaching content — examples, cases, multi-perspective explanations.
The Discipline-Specific Example Generator
Takes a concept and produces mini-cases or examples tuned to a specific industry, student level, or current relevance.
Recipe 6.2The Current-Events Case Freshener
Takes a recent news event and translates it into a mini-case or in-class discussion vehicle for a specific course.
Recipe 6.3The Concept Explainer With Multiple Framings
Explains a concept through the lens of multiple disciplines — for instance, "explain risk" with framings from Finance, Marketing, Real Estate, and Management — so faculty can pick the framing that fits or use the contrast as the teaching moment.
AI-policy
Agents that help you draft AI-use policy for your course.
New to building agents? Start here.
Each tutorial walks through one platform's agent-creation UI: where to start, what each field maps to, how to share the result. The NotebookLM appendix covers a lightweight grounded-chat alternative.