R065 · AI's effect on people › Learning, advice and public-good deployment

Primer: teacher-authored AI simulations through a gated multi-agent pipeline

Read the original

educationmulti-agenthuman-oversighteducational-simulations

Sources: Ethan Mollick's LinkedIn post (2026-11-12); the Primer project page from Wharton Generative AI Labs; the wharton-generative-ai-labs/primer README (MIT). Authors named in the post: Lilach Mollick, Ben Przystanski, LJ Ciccarelli, Natalie Bach and Laura Zarrow.

The claim

Simulations are among the best teaching tools, because they make students retrieve what they know, act, and revise based on consequences. They are rarely used because they are expensive to design and build. Primer is an open-source system where an educator describes a lesson in conversation and gets back a playable, AI-run simulation. The pedagogy is written into each agent's instructions, and nothing is built until the educator approves a design document. The release includes the paper, the prompts and the code, plus a final prompt that tells a coding agent to rebuild Primer from the paper: a paper you can run.

Architecture

Two phases, each a pipeline of narrow agents that pass inspectable artifacts rather than sharing one model's memory.

Authoring (educator-facing)

AgentInputOutput
Intake AgentOne-question-at-a-time interview; optional syllabi, lesson plans, rubricsGoals, student level, prior knowledge, misconceptions, teaching approach, assessment criteria
Design AgentInterview recordDesign document: objectives, scenario flow, characters, stakes, adaptation logic
Approval gateDesign documentEducator reads it as a lesson plan, revises, approves. Nothing downstream runs before this.
Casting DirectorApproved designRole prompts for the mentor, practice and feedback characters
Image Generation AgentDesignScene visuals
Experience BuilderPrompts, images, configA playable experience assignable to one student or a class

Runtime (student-facing): three agents in sequence. A mentor activates prior knowledge and surfaces misconceptions. A practice agent plays a counterpart in one of two modes: Roleplay (pursue a goal against a character with its own motives) or Teachback (explain a concept to someone who doesn't get it and revise under questioning). A feedback agent coaches from the transcript, citing specific moments. Each runtime agent has two layers: the in-world character, and an instructional layer that tracks goals, calibrates difficulty and gathers evidence. Educators get per-student and aggregate reports afterwards.

Code: a runtime for config-defined "experiences" (agents with personas and voices, scenes, sound, agent-to-agent flow, tools such as notes, image generation and web search), installable as modules from a registry.

Why the design is right

Failure modes and caveats

Review checklist for adopting it

  1. Read the design document the way you would a colleague's lesson plan: objectives, misconceptions targeted, what counts as evidence.

  2. Red-team the practice agent: try to get the answer handed to you, go off-topic, and push the character to break.

  3. Compare feedback reports with your own grading on a handful of transcripts before trusting the aggregate.

  4. Decide where the student data goes (provider, retention, logs) and get the privacy review done first.

  5. Pin the models per experience, and re-test after any model change.

Bottom line

A careful, open reference design for expert-in-the-loop agent pipelines that happens to be about teaching: interview, readable design document, approval gate, then narrow agents working from artifacts. It is worth studying for the pattern even if you never build a simulation. Treat its learning claims as unproven until there is classroom data.

Connections

See R065 on the knowledge map

Part of the Research notes on nowucca.com. Figures and claims are the source's own unless the summary says otherwise.