Artificial Intelligence · arXiv:2611.16986 v1 · submitted 12 Nov 2026 · 115 references
Primer: An AI Framework for Instructor-Centered Educational Simulation Creation
The paper says
“Educational simulations are a well-established pedagogical technique that gives learners opportunities to apply knowledge, respond to challenges, and reflect on their performance.”
more of the abstract
High-quality simulations, however, are difficult to build, requiring instructor input, scenario design, character development, scaffolding, technical implementation, and repeated revision. This paper presents Primer, an open-source, LLM-agnostic AI-supported system that helps educators create adaptive educational simulations. Educators contribute their knowledge of the subject, lesson, and students, while generative AI produces responsive variations of practice for students. Primer uses a multi-agent system centered around executing educator's instructional intent through the entire learning experience. We hope that by releasing Primer as an open-source system, including its prompts and GitHub repository, we provide a foundation for development and research on educator-in-the-loop AI authoring, multi-agent educational workflows, and simulation-based pedagogy. Further, by allowing the use of various AI models, including local and open source models, we provide the opportunity for implementation under varied governance regimes. Primer points toward a model of educational AI in which instructors can create locally grounded practice opportunities based on their own materials, goals, examples, and knowledge of students.
from the abstract
Pith says
Machine review · deepseek-v4-flash · 13 Nov 2026 · what was read was not recorded · not checked by a person
It can be wrong. Challenge this review or reply to it.
Holds up, with conditions.
2 major objections · 5 minor
How often objections from reviews like this one are right: not yet measured
Not checked: figures, code, what the 115 references say.
The paper says, at Abstract; Section 'Voice, Pedagogy, and Risks'; Appendix B
The review did not quote this passage.
Pith says: Objection 1 of 2 · major
The paper claims Primer is 'LLM-agnostic' and can use local/open-source models, enabling implementation under varied governance regimes. However, the only model used in testing is OpenAI's gpt-realtime-1.5. The prompts in Appendix B require reliable tool calling (artifact, sessionEvent, delegation, checklist) and the Design Agent must emit a Phases Configuration that 'must parse as JSON by itself' with strict constraints.
more of objection 1
These are exactly the capabilities that vary substantially across models; local open-weight models often struggle with structured tool use and multi-step instruction following. Without cross-model testing, the claim of LLM-agnosticism is unsupported. The authors should either provide evidence that the system functions with at least one alternative model (e.g., a local open-source model) or explicitly qualify the claim to reflect that it has only been tested with OpenAI models.
The paper says, at Section 'Testing and Development with Educators'
The review did not quote this passage.
A classifier read this sentence of the paper as acknowledging the concern (probability 0.67):
“That requires formal research with students and educators under classroom conditions.”
Pith says: Objection 2 of 2 · major
The formative testing provides useful usability feedback, but the evidence that the system 'was capturing their intent' rests on three positive quotes from educators. This is anecdotal. The paper would benefit from a more systematic evaluation of the authoring pipeline's output, such as having independent raters compare design documents to educator intent or assessing the quality of generated simulations against pedagogical criteria.
more of objection 2
The authors acknowledge that effectiveness requires formal research, but the claim that Primer 'helps educators create adaptive educational simulations' would be strengthened by evidence beyond usability. The authors should either provide such evidence or frame the contribution more narrowly as a system design and prototype, with evaluation of output quality left to future work.
5 minor objections
The paper says, at Limitations and Future Work
Pith says: minor objection 1 of 5
Add a sentence explicitly stating that cross-model testing has not been conducted and that the LLM-agnostic claim is currently a design goal rather than an empirically supported property.
The paper says, at Section 'Testing and Development with Educators'
Pith says: minor objection 2 of 5
The section notes that educators played the role of students, but this should be highlighted earlier in the section to avoid any overinterpretation of the results.
show 3 more
The paper says, at Primer Overview
Pith says: minor objection 3 of 5
Consider adding a summary table of the agents and their roles to improve readability and quick reference.
The paper says, at References
Pith says: minor objection 4 of 5
The reference for OpenAI is incomplete (OpenAI, n.d.); provide full documentation details or a direct URL.
The paper says, at Discussion: Building Amid a Shifting Frontier
Pith says: minor objection 5 of 5
The paper references 'Appendix D: A Paper That Builds Itself,' but this appendix is not present in the provided text. Ensure the appendix is included or remove the reference.
What would settle it
Run Primer's full authoring pipeline (intake, design, casting, build) with a representative open-weight model (e.g., Llama 3.1 70B or 405B) and with a non-OpenAI commercial model (e.g., Claude or Gemini) on the same scripted educator scenario. Measure: (1) whether the pipeline reaches the handoff phase without human intervention, (2) whether the Phases Configuration artifact is valid JSON with the required keys and no extra top-level keys, (3) whether the resulting experience actually runs with mentor-practice-feedback phases. Compare completion rates and any qualitative failure modes against the OpenAI baseline. If the open-weight model fails on JSON strictness, tool-call sequence, or agent handoff, the LLM-agnosticism claim is unsupported.
from the skeptic's reading
How the review went
3 readings by deepseek-v4-flash · 13 Nov 2026
- Reader holds up, with conditions
- Skeptic partly agrees
- Referee major revision: 2 major objections, 5 minor
Not run on this paper: the editor, the simulated authors' defence.
Pith did not check this review's objections against the paper.
The review in full
The strongest objection
The abstract claims Primer is 'LLM-agnostic' and 'allow[s] the use of various AI models, including local and open source models,' and the paper frames this as enabling implementation under varied governance regimes. Yet the only model used in testing is OpenAI's gpt-realtime-1.5 for voice (Section 'Voice, Pedagogy, and Risks'), and no evidence is presented that the authoring or runtime agents function with any other model. The system's prompts require reliable tool calling (artifact, sessionEvent, delegation, checklist) and the Design Agent must emit a Phases Configuration that 'must parse as JSON by itself' with strict constraints. These are exactly the behaviors where model capability varies substantially; frontier models may comply, local open-weight models often fail at structured tool use or multi-step instruction following. The paper's own reference to Jurenka et al. notes that models produce uneven outputs without scaffolding. Since LLM-agnosticism is a stated value proposition (governance flexibility), it is a load-bearing empirical claim. Without cross-model testing, the claim is unsupported, and the paper's stated benefit of being deployable under varied legal regimes is not established. This is distinct from the acknowledged lack of effectiveness evidence; it is an unacknowledged assumption about model portability.
The reader's verdict was CONDITIONAL, focused on the absence of evidence for pedagogical effectiveness. I agree that is a real limitation, but it is explicitly acknowledged by the authors ('they do not establish its effectiveness as a learning intervention') and future work. The more load-bearing unacknowledged claim is LLM-agnosticism, which underpins the paper's governance flexibility value proposition and is stated without any cross-model testing. If the system only works with frontier models, the claim that it can be used under varied governance regimes (with local models) fails, weakening the contribution. This concern does not overturn the paper's core architectural contribution—the open-source design and prompts are inspectable and adaptable—so the verdict remains CONDITIONAL, with the added condition that model portability be demonstrated. The reader did not identify this specific gap, though they noted the lack of effectiveness evidence; hence partial agreement.
The referee's report
If the system works as described, it could lower the barrier for educators to create practice simulations, enabling more varied and adaptive practice opportunities. The open-source release and detailed prompts allow replication and extension by the research community. However, the current evidence is limited to formative usability testing with educators playing the role of students; effectiveness in terms of student learning outcomes is not established. The main contribution is the systematic architecture and its detailed documentation, not empirical validation. The unsupported claim of LLM-agnosticism weakens the governance-flexibility value proposition, which is a central stated benefit.
Pith's reading of the paper (a machine's summary, not the authors')
Primer is an open-source, LLM-agnostic AI system that enables educators to create adaptive educational simulations through a structured multi-agent authoring pipeline. The system treats simulation creation as a guided instructional design process: an Intake Agent interviews the educator about goals, student context, and materials; a Design Agent translates that into a structured plan; and after educator review, specialized agents assemble the playable experience. At runtime, students encounter a three-phase structure (mentor preparation, practice application, feedback reflection) with agents that maintain character roles while tracking pedagogical goals. The paper argues for AI-human complementarity: the educator supplies local instructional judgment, and AI provides adaptive variation within that frame. If the approach succeeds, it could make high-quality practice simulations widely accessible to educators without requiring technical expertise.
What carries the argument. The multi-agent authoring pipeline centered on the Intake Agent and the design document as a boundary object. The Intake Agent conducts a structured interview that elicits educator expertise and maintains a planning journal, then delegates to the Design Agent which produces a design document that serves as the shared reference for all downstream agents. The three-phase runtime structure (Mentor, Practice, Feedback) with dual-role agents that simultaneously embody characters and track pedagogical goals is the mechanism that translates educator intent into adaptive practice.
Core claim. Primer is an open-source AI framework that makes simulation authoring accessible to any educator by using a multi-agent pipeline to translate instructional intent into a playable experience. The system's Intake Agent conducts a structured interview to elicit the educator's learning goals, student context, prior knowledge, common misconceptions, and available materials. This conversation is transformed into a design document that functions as a boundary object: the educator reviews it as a lesson plan, while downstream agents (Casting Director, Image Generation Agent, Experience Builder) interpret it as a build specification. At runtime, students interact with three agents (Mentor, Practice, Feedback) that simultaneously embody characters and track learning objectives, adapting challenge based on student performance. The central innovation is the artifact-centered workflow: educator intent travels through the system as inspectable artifacts (transcripts, design documents, journals, checklists) that maintain alignment across the authoring and runtime phases.
The premise it rests on. The paper assumes that the multi-agent orchestration and prompt engineering it describes will reliably produce simulations that are pedagogically sound and aligned with educator intent, without evidence from controlled studies of student learning outcomes or classroom deployment.
If the paper is right (Pith's inferences, not the authors')
Educators without technical or game-design expertise can create adaptive simulations tailored to their specific students, context, and learning objectives.
The open-source release of the full system, including prompts and orchestration code, enables researchers and developers to inspect, modify, and improve the architecture, supporting community-driven development of AI authoring tools.
The artifact-centered workflow provides a design pattern for maintaining alignment with user intent across multi-step generative processes, applicable beyond simulations to other educator-in-the-loop AI systems.
The architecture points toward a scalable model where AI handles adaptive variation while educators focus on instructional judgment, potentially increasing the availability of high-quality practice opportunities across educational settings.
The most significant barrier to adoption may be organizational rather than technical: educators need dedicated time to author simulations, trust the output, and integrate them into existing curricula, and the paper's formative testing with educators playing as students does not address classroom workflow or student learning outcomes.
The system's pedagogical design is grounded in specific learning theories (backward design, scaffolding, retrieval practice, desirable difficulties), but the paper does not test whether these theories hold in AI-mediated practice contexts; the effectiveness of Primer depends on empirical validation that is not yet conducted.
The explicit limitation that practice variation unfolds within a single encounter (not across varied cases) means the system has not yet implemented one of the key mechanisms the authors identify as important for durable learning: varied practice across different contexts.
Check this review
Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.
How often reviews like this one are right
Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.
How often objections from reviews like this one are right: not yet measured
Reviews by people
This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.
The paper
Abstract
Educational simulations are a well-established pedagogical technique that gives learners opportunities to apply knowledge, respond to challenges, and reflect on their performance. High-quality simulations, however, are difficult to build, requiring instructor input, scenario design, character development, scaffolding, technical implementation, and repeated revision. This paper presents Primer, an open-source, LLM-agnostic AI-supported system that helps educators create adaptive educational simulations. Educators contribute their knowledge of the subject, lesson, and students, while generative AI produces responsive variations of practice for students. Primer uses a multi-agent system centered around executing educator's instructional intent through the entire learning experience. We hope that by releasing Primer as an open-source system, including its prompts and GitHub repository, we provide a foundation for development and research on educator-in-the-loop AI authoring, multi-agent educational workflows, and simulation-based pedagogy. Further, by allowing the use of various AI models, including local and open source models, we provide the opportunity for implementation under varied governance regimes. Primer points toward a model of educational AI in which instructors can create locally grounded practice opportunities based on their own materials, goals, examples, and knowledge of students.
The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.
abstract compiled · 2026-11-13
The authors' main claim, as the classifier picked it out 0.87
“Primer points toward a model of educational AI in which instructors can create locally grounded practice opportunities based on their own materials, goals, examples, and knowledge of students.”
How the main claim is stated: hedged possibility 0.91
What the abstract itself states, as probabilities: claims first 0.04 · states limitation 0.24 · human participants 0.38 · controlled comparison 0.02 · randomized assignment 0.01 · states quantitative result 0.03 · compares with prior results 0.06 · mentions code or data availability 0.98
The abstract, sentence by sentence
This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.
| Sentence | Role | The authors' own work | States the main conclusion | Strength |
|---|---|---|---|---|
| Educational simulations are a well-established pedagogical technique that gives learners opportunities to apply knowledge, respond to challenges, and reflect on their performance. | background 1.00 | 0.04 | 0.03 | asserted 1.00 |
| High-quality simulations, however, are difficult to build, requiring instructor input, scenario design, character development, scaffolding, technical implementation, and repeated revision. | background 0.76 | 0.09 | 0.03 | asserted 1.00 |
| This paper presents Primer, an open-source, LLM-agnostic AI-supported system that helps educators create adaptive educational simulations. | contribution 1.00 | 0.83 | 0.25 | asserted 1.00 |
| Educators contribute their knowledge of the subject, lesson, and students, while generative AI produces responsive variations of practice for students. | method 0.92 | 0.35 | 0.11 | asserted 1.00 |
| Primer uses a multi-agent system centered around executing educator's instructional intent through the entire learning experience. | method 0.98 | 0.69 | 0.11 | asserted 1.00 |
| We hope that by releasing Primer as an open-source system, including its prompts and GitHub repository, we provide a foundation for development and research on educator-in-the-loop AI authoring, multi-agent educational workflows, and simulation-based pedagogy. | future work 0.76 | 0.64 | 0.19 | hedged possibility 0.82 |
| Further, by allowing the use of various AI models, including local and open source models, we provide the opportunity for implementation under varied governance regimes. | contribution 0.78 | 0.62 | 0.07 | asserted 0.63 |
| Primer points toward a model of educational AI in which instructors can create locally grounded practice opportunities based on their own materials, goals, examples, and knowledge of students. | interpretation 0.97 | 0.23 | 0.38 | hedged possibility 0.91 |
What kind of paper the classifier reports this is: method or tool 1.00 · evidence from argument 0.97
What was examined, and what was not
Sources read
- arXiv listing abstract v1
Not examined
- full text
- figures and tables
- references and citing sentences
- relations to other papers
Levels run
- P abstract
Not run
- S sections
- T body sentences
- C citations
- R cross-paper relations
How the labels were made
Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-13: 1 request, 6,266 input tokens.
Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON
Figures (4)
Figures are the authors', reproduced from the paper.
References (115)
- [2] Determine whether the skill primarily involves per- formingthroughinterpersonalinteractionordemon- strating understanding by explaining it on Pith
- [4] Specify the template type when delegating. Down- stream agents discover the actual template folder ID. Typical fits include negotiation and customer service for Roleplay, and explaining complex scientific concepts or technical procedures for Teachback. 11 Pedagogical and techn... on Pith
- [5] Intake Agent: gathers teacher intent . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .32 on Pith
- [6] Design Agent: turns intent into approved design. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 on Pith
- [7] Casting Director: turns design into role prompts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .53 on Pith
- [8] Experience Builder: assembles and verifies the playable experience . . . . . . . . . . . . . . . . . . . . . .60 on Pith
- [9] Roleplay runtime prompts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .65 5.1 Roleplay Mentor Agent . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .65 5.2 Roleplay Practic... on Pith
- [10] Teachback runtime prompts . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .74 6.1 Teachback Mentor Agent . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .74 6.2 Teachback Practice... on Pith
- [11] Cross-cutting checklists and journals . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .84 7.1 Checklists . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .84 7.1.1 Teache... on Pith
- [12] Intake Agent: gathers teacher intent The Intake Agent is the teacher-facing entry point to Primer. It gathers the contextual knowledge the model does not have by default: what the teacher is trying to teach, what students already know, where they struggle, what materials defin... on Pith
- [13] Listen to the educator’s learning objectives and teaching challenges on Pith
- [14] Determine whether the skill primarily involves performing through interpersonal interaction or demonstrating understanding by explaining it on Pith
- [15] Select Roleplay for the former or Teachback for the latter, using the objective and context to guide the choice on Pith
- [16] Specify the template type when delegating. Downstream agents discover the actual template folder ID. Typical fits include negotiation and customer service for Roleplay, and explaining complex scientific concepts or technical procedures for Teachback. For Roleplay, students ado... on Pith
- [17] Design Agent: turns intent into approved design Design Agent Progress signaling Tick the public Design Progress checklist exactly once, immediately after both the Design Document and Phases Configuration artifacts have been successfully created. Do not tick it when work begins... on Pith
- [18] Intake Agent→interviews instructor→references the platform-maintained conversation_transcript→delegates to Design Agent (that's you) on Pith
- [19] Design Agent→creates Design Document, Phases Configuration, and Design Process Notes→returns all three artifact IDs to Intake Agent on Pith
- [20] Intake Agent→guides Lesson Plan goals review, then Design Document review→gets approval→educator clicks Build Experience→delegates to Casting Director on Pith
- [21] Casting Director→creates character prompts→returns to Intake Agent on Pith
- [23] Image Generation Agent→creates 3 scene images (one for each scene)→returns to Intake Agent on Pith
show 80 more
- [24] Intake Agent→delegates to Experience Builder with the approved Design Document, matching Phases Configuration, summary, prompts, and images on Pith
- [25] Experience Builder→builds, verifies, and publishes the experience→returns a valid experienceId to Intake Agent on Pith
- [26] Intake Agent→advances to handoff→platform result tile automatically displays the built experience and Play action You are the design agent in this pipeline. Your work returns to the Intake Agent for instructor approval before proceeding. Limitations and Constraints •You are a ... on Pith
- [27] Use artifact with action "get" to retrieve conversation_transcript. Its ID and any uploaded artifact IDs are supplied in artifactIds through delegation. Read the uploaded materials needed for the design on Pith
- [28] Use artifact with action "create" for the educator-facing Design Document. Use the name "Design Document" and state the template type (Roleplay or Teachback) in its Overview. Do not include workflow-phases JSON or other machine-only configuration. Save the returned ID on Pith
- [29] Use artifact with action "create" for the separate machine-only Phases Configuration, using the name "Phases Configuration" and tags: ["phases-configuration"]. Its content must be JSON alone, with no markdown fences or commentary. Save the returned ID on Pith
- [30] Immediately after successful Phases Configuration creation, tick Drafting the design document using the required phase:intake tag, as specified under Progress signaling. Do not repeat that call on Pith
- [31] Use artifact with action "create" for "Design Process Notes" and save its returned ID. Only after all three artifacts exist and the required progress and completion calls are finished, return a brief response to the Intake Agent naming all three actual artifact IDs: Design Doc... on Pith
- [32] Reference these materials by their artifactId in your design on Pith
- [33] Extract key elements: - Learning objectives - Assessment criteria - Common misconceptions - Teaching examples 43 Appendix B: Primer Prompts 2. Design Agent: turns intent into approved design on Pith
- [34] Integrate these elements into your design document on Pith
- [35] Note in process notes which materials informed which design decisions Create a detailed design document. Return to Intake Agent: Pass the Design Document, matching Phases Configuration, and Design Process Notes back by their actual artifact IDs. Handling Intake Agent Web Resea... on Pith
- [36] Guide the Lesson Plan goals review, then present the Design Document to the instructor for approval on Pith
- [37] Re-delegate requested modifications and retain the updated Design Document and matching Phases Configuration on Pith
- [38] After approval and the educator’s Build Experience button click, pass the design to the Casting Director and retain both required build inputs for the Experience Builder The Casting Director will then use your design document and context blocks to create prompts for the simula... on Pith
- [39] Casting Director: turns design into role prompts Casting Director Progress signaling Tick the public Build Progress checklist exactly once, immediately after all three character prompt artifacts (mentor, practice, feedback) have been successfully created. Do not tick it when w... on Pith
- [40] CustomizePedagogicalSteps: Given the design document, make each runtime template's teaching, practice, and feedback steps specific to the scenario. Preserve the required educational beats; do not add teacher-intake checklist instructions or checklist tool calls to student-faci... on Pith
- [41] Intake Agent→interviews instructor→references the platform-maintained conversation_transcript→delegates to Design Agent on Pith
- [42] Design Agent→analyzes transcript→creates Design Document with CHARACTER CONTEXT blocks, Phases Configuration, and Design Process Notes→returns all three artifact IDs to Intake Agent on Pith
- [43] Intake Agent→guides Lesson Plan goals review, then Design Document review→gets approval→educator clicks Build Experience→delegates to YOU (Casting Director) 54 Appendix B: Primer Prompts 3. Casting Director: turns design into role prompts 4.YOU→receive approved Design Document... on Pith
- [44] Intake Agent→delegates to Image Generation Agent on Pith
- [45] Image Generation Agent→creates scene images→returns to Intake Agent on Pith
- [46] Intake Agent→delegates to Experience Builder with the approved Design Document, matching Phases Configuration, summary, your prompts, and scene images on Pith
- [47] Experience Builder→builds, verifies, and publishes playable experience→returns valid experienceId to Intake Agent on Pith
- [48] Intake Agent→advances to handoff→platform result tile automatically displays the built experience and Play action Your Inputs and Outputs YOUR INPUTS: •Design document (from Intake Agent) containing CHARACTER CONTEXT blocks •The design document will mention which template stru... on Pith
- [49] Use the`artifact`tool with action`"list"`to see all available artifacts (for debugging/verification) on Pith
- [50] Use the`artifact`tool with action`"get"`and pass the artifact ID from `artifactIds`to retrieve the design document on Pith
- [51] Read the full content of the design document to understand the template type and character contexts YOUR RESPONSIBILITY: Read the design document to determine which template type should be used (Roleplay or Teachback). Then: on Pith
- [53] Find the template whose title matches the type (e.g., if design mentions "Roleplay", find template with title containing "Roleplay") on Pith
- [54] Use that template's folder ID to retrieve agent instructions {{templates}} YOUR OUTPUTS: •Three customized character prompt artifacts (with scenario-specific pedagogical steps) •Process notes •Return all artifact IDs to Intake Agent Templates and Tools Character Prompt Templat... on Pith
- [55] Integrate Character Context Find the`[CASTING DIRECTOR, INSERT APPROPRIATE CHARACTER CONTEXT]`placeholder and replace it with the entire corresponding context block from the design document. Preserve the template's core structure and technical requirements (tool usage, transit... on Pith
- [56] Customize the Required Pedagogical Steps Each runtime template supplies the required educational beats. You may reword steps to match the scenario's specifics, combine redundant steps, or reorder them if it serves the flow. Do not remove core pedagogical steps. The Roleplay an... on Pith
- [57] Use`listTemplateExperiences`to discover available templates on Pith
- [58] Find the template whose title matches the template type mentioned in the design and extract its folder ID on Pith
- [59] Use`getTemplateAgentInstructions`to retrieve mentor template instructions (using the discovered folder ID) on Pith
- [60] Use`getTemplateAgentInstructions`to retrieve practice template instructions (using the discovered folder ID) on Pith
- [61] Use`getTemplateAgentInstructions`to retrieve feedback template instructions (using the discovered folder ID) on Pith
- [62] Create the enhanced mentor prompt (integrate character context, preserve the full runtime template, and customize the required pedagogical steps) on Pith
- [63] Create the enhanced practice prompt (integrate character context, preserve the full runtime template, and customize the required pedagogical steps) 58 Appendix B: Primer Prompts 3. Casting Director: turns design into role prompts on Pith
- [64] Create the enhanced feedback prompt (integrate character context, preserve the full runtime template, and customize the required pedagogical steps) Immediately after all three character prompt artifacts exist, tick Creating character prompts using phase:build, as specified und... on Pith
- [65] Experience Builder: assembles and verifies the playable experience The Experience Builder packages the approved design, customized prompts, scene assets, and metadata into a playable simulation and verifies that the mentor-practice-feedback flow remains intact. This is an exce... on Pith
- [66] kind remains "user", as set by copyTemplate,sothe experience is categorized correctly 7.Author fields setwith the educator's name (`author`) and email (`authorEmail`) so the permission system grants them access 8.Experience structure verifiedwith all supplemental files in plac... on Pith
- [67] Approved Phases Configuration applied and verified without changing required template infrastructure 64 Appendix B: Primer Prompts 5. Roleplay runtime prompts 10.deployBuildArtifacts completed with no failed or missing assets, followed by successful publishBuiltExperience publ... on Pith
- [68] experienceIdofthecompleted experience(the exact slug returned by copyTemplate, after successful publication) 2.Summary of template-based build processand components integrated 3.Confirmation that agent prompts replaced template fileswith actual content from Casting Director 4.... on Pith
- [69] Confirmation that the approved Phases Configuration was applied and verified on Pith
- [70] Confirmation that publishBuiltExperience succeeded and populated the Built Experience result artifact 10.Any issues encountered and resolvedduring the build process The final experience MUST resolve all placeholders correctly because the template provides the required suppleme... on Pith
- [71] Roleplay runtime prompts Runtime agents that drive a student through a roleplay experience: the Mentor sets up learning, the Practice agent embodies the in-scenario character the student interacts with, and the Feedback agent debriefs at the end. 5.1 Roleplay Mentor Agent Role... on Pith
- [74] Once they indicate readiness, say: "Good luck, I'll be listening in, and I'll see you after your [experience with next character]!" on Pith
- [75] Advance the workflow to the practice phase 67 Appendix B: Primer Prompts 5. Roleplay runtime prompts Remember to: •Create transcript artifact with the complete conversation using artifact() •Clear any displayed content before transition •Maintain consistent personality while p... on Pith
- [76] List available artifacts to find mentor and practice session transcripts on Pith
- [77] Look for artifacts named "Mentor Session Transcript" and "[Character] Practice Session Transcript" on Pith
- [78] Retrieve both transcripts to understand the full learning journey You were "listening in" on both the mentoring session and practice session, so you can reference specific moments, quotes, and exchanges from the actual conversations that occurred. When reviewing transcripts, y... on Pith
- [79] Self-Assessment: Ask them to reflect on specific moments on Pith
- [80] Strength Recognition: Highlight 1-2 things they did well with examples on Pith
- [81] Growth Areas: Address 1-2 improvement areas with specific instances on Pith
- [82] Planning: Discuss how to apply lessons going forward Conclusion •Synthesize into 2-3 actionable takeaways •Display key points visually with the slide tool (action:'show') •Let student have final reflection •Wrap everything up with a final, friendly sign-off. Make it clear this... on Pith
- [83] Teachback runtime prompts Runtime agents that drive a student through a teachback experience, in which the student must explain a concept to demonstrate understanding. 6.1 Teachback Mentor Agent Teachback Mentor You are an actor portraying a mentor inside an educational simula... on Pith
- [84] Use artifact() to create a verbatim transcript artifact with the full conversation on Pith
- [85] Clear any currently displayed text on Pith
- [86] Once they indicate readiness, say: "Good luck, I'll be listening in, and I'll see you after your [teaching/advising session]!" on Pith
- [87] Advance the workflow to the practice phase Remember to: •Create transcript artifact with the complete conversation using artifact() •Clear any displayed content before transition •Maintain consistent personality while preparing them for what's next Technical Requirements Essen... on Pith
- [88] List available artifacts to find transcripts and journals on Pith
- [89] Look for artifacts named "Mentor TeachBack Session Transcript" and "[Character] TeachBack Practice Session Transcript" on Pith
- [90] Retrieve all relevant artifacts to understand the full learning journey You were the mentor in the mentoring session and "listening in" on the practice session. You can reference specific moments, quotes, and exchanges from the actual conversations that occurred. When reviewin... on Pith
- [91] Help the student see what they did well and where they can grow (standard feedback) on Pith
- [92] Help them recognize what teaching or advising did for their own understanding (the deeper goal) Students may not know that explaining something makes it clearer in their own head, and that adapting to peer questions pushes them to think harder. You can surface these moments. E... on Pith
- [93] Cross-cutting checklists and journals Checklists and journals are referenced by multiple agents across the pipeline and runtime. Checklists are used onlybythe design-time pipeline (Intake / Design / Casting / Builder). Journals are used byboth the design-time pipeline andthe R... on Pith
- [94] Open an agentic coding environment, or the strongest environment available on Pith
- [95] Provide the complete paper on Pith
- [96] Paste the complete prompt below. The agent will inspect its environment first and explain what it expects to build on Pith
- [97] Expect a long run. This could mean several hours of agent work and paid model usage. Watch progress in BUILD_STATUS.html. When it finishes, try it out, author a lesson of your own through the system it built, and play the result. Note: The agent may build directly from the exi... on Pith
- [98] An educator-facing authoring system on Pith
- [99] A playable learner runtime on Pith
- [100] The artifacts, evidence, approval gates, feedback processes, and testing infrastructure connecting them. Do not substitute any of the following for Primer: •A summary of the paper. •A requirements document or architecture alone. •A static interface mock-up. •A single simulatio... on Pith
- [101] Use the Paper, Repository (if you like), and Environment Correctly Treat the three sources of direction differently: •The paper is the pedagogical constitution. Preserve its commitments even if or when changing the implementation. •The repository is a reference implementation ... on Pith
- [102] Inspect the Environment and Declare the Build Mode Before building, inspect whether you can: •Read and write persistent files. •Run shell commands and application code. •Access or clone the repository. •Install project-scoped dependencies. •Run tests, linters, builds, and loca... on Pith
- [103] Preserve the Primer Contract Create the Primer Contract from the paper in PRIMER_CONTRACT.md or a clearly labeled section of a consolidated record. At minimum, maintain: Educator authority Educator goals, content, examples, misconceptions, criteria, constraints, and classroom ... on Pith
- [104] Preparation that gives the learner enough context and activates relevant prior knowledge on Pith
- [105] Practice that requires meaningful application in a scenario on Pith
- [106] Feedback and reflection grounded in what the learner actually did. Productive friction Use uncertainty, character goals, questions, constraints, consequences, and calibrated difficulty to make the instructional content necessary. Narrative must serve the learning goal rather t... on Pith
The first 100 of 115 references are listed here. All of them are in this paper's citation record.
Challenges and discussion
Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.
Come back by email
A short list of the week's newly reviewed papers. Nothing is sent until you confirm from your inbox, and every email has a link that stops it. No account.
No comments yet.
Sign in to comment