{"id":50454160,"url":"https://github.com/mizcausevic-dev/ai-tutor-card-spec","last_synced_at":"2026-06-01T01:05:42.555Z","repository":{"id":357458020,"uuid":"1236887911","full_name":"mizcausevic-dev/ai-tutor-card-spec","owner":"mizcausevic-dev","description":"AI Tutor Cards v0.1 draft. Disclosure spec for AI agents in an educational role: audience (age, grade, subjects), pedagogy (Socratic / homework_policy / assessment_policy), safety \u0026 privacy (FERPA / COPPA / mandated-reporter). Sixth spec in the Kinetic Gain Protocol Suite.","archived":false,"fork":false,"pushed_at":"2026-05-12T21:38:22.000Z","size":39,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-05-12T22:28:27.226Z","etag":null,"topics":["ai-agents","ai-safety","ai-tutor","coppa","disclosure","edtech","education","ferpa","json-schema","kinetic-gain-protocol-suite","protocol","specification"],"latest_commit_sha":null,"homepage":"https://github.com/mizcausevic-dev/ai-tutor-card-spec","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"agpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/mizcausevic-dev.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-05-12T17:06:37.000Z","updated_at":"2026-05-12T21:38:26.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/mizcausevic-dev/ai-tutor-card-spec","commit_stats":null,"previous_names":["mizcausevic-dev/ai-tutor-card-spec"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/mizcausevic-dev/ai-tutor-card-spec","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizcausevic-dev%2Fai-tutor-card-spec","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizcausevic-dev%2Fai-tutor-card-spec/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizcausevic-dev%2Fai-tutor-card-spec/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizcausevic-dev%2Fai-tutor-card-spec/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mizcausevic-dev","download_url":"https://codeload.github.com/mizcausevic-dev/ai-tutor-card-spec/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mizcausevic-dev%2Fai-tutor-card-spec/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33755379,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-05-31T02:00:06.040Z","response_time":95,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-agents","ai-safety","ai-tutor","coppa","disclosure","edtech","education","ferpa","json-schema","kinetic-gain-protocol-suite","protocol","specification"],"created_at":"2026-06-01T01:05:42.486Z","updated_at":"2026-06-01T01:05:42.540Z","avatar_url":"https://github.com/mizcausevic-dev.png","language":null,"funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI Tutor Cards\n\n[![Validate examples](https://github.com/mizcausevic-dev/ai-tutor-card-spec/actions/workflows/validate.yml/badge.svg)](https://github.com/mizcausevic-dev/ai-tutor-card-spec/actions/workflows/validate.yml)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)\n\nA draft specification for **AI Tutor Cards** — declarative documents that disclose what an AI tutor is for, how it teaches, and what safety and privacy protections it carries.\n\nTutors are a specialized class of AI agent with stakes a general-purpose agent doesn't carry: the audience can be a minor, the buyer is often a school district or parent, and the regulatory surface includes FERPA, COPPA, and state-level student-data laws. A Tutor Card is the document that makes those properties machine-readable for procurement reviewers, accreditation bodies, parents, and the LMS itself.\n\nThis spec is the EdTech-flavored sibling of [Agent Cards](https://github.com/mizcausevic-dev/agent-cards-spec) — it shares the same disclosure philosophy but adds the fields a school board needs and an agent-only context does not.\n\n## The three pillars\n\n| Pillar | What it does |\n|---|---|\n| **Audience** | Declare who the tutor is for: age range, grade range, supported languages, subject scope (topics included AND excluded) |\n| **Pedagogy** | Declare how the tutor teaches: instructional approach, homework policy, assessment policy, scaffolding behavior |\n| **Safety \u0026 Privacy** | Declare protections: content filters, mandated-reporter protocol, FERPA / COPPA / GDPR posture, data-sharing rules, retention |\n\n## Why a separate spec from Agent Cards?\n\nAn Agent Card describes capabilities and refusals for any AI agent. A Tutor Card adds the **pedagogical, demographic, and student-data-regulatory** fields that Agent Cards deliberately don't define. The two are complementary: a Tutor Card SHOULD reference its underlying Agent Card (`agent_card_uri`) so a reviewer can chain from \"what this tutor does in classroom terms\" to \"what this agent does in capability terms\" in one click.\n\n## Why not just a vendor brochure?\n\nThree reasons.\n\n1. **Machine-readable procurement.** District procurement teams reviewing AI tutors today read PDFs and run their own pilots. A Tutor Card lets a procurement reviewer diff two tutors side by side mechanically: which one has stricter content filters, which one has a stricter homework policy, which one is FERPA-attested.\n2. **LMS visibility.** A school's LMS (Canvas, Schoology, Google Classroom) can read a Tutor Card on integration day and surface \"what this tutor will and won't do\" to teachers without anyone reading a 40-page vendor whitepaper.\n3. **Parent visibility.** A parent (or a parent-facing portal) can read a Tutor Card without an account at the vendor. Discoverable, signed, auditable.\n\n## Quickstart\n\n1. Pick a `tutor.id` (kebab-case, unique within your org).\n2. Author a Tutor Card conforming to [`tutor-card.schema.json`](tutor-card.schema.json). Start from one of the [examples](examples/).\n3. Validate with any JSON Schema 2020-12 validator (e.g. `ajv`, `jsonschema`).\n4. Serve at `https://\u003cyour-product\u003e/.well-known/tutors/\u003ctutor-id\u003e.json` with `Content-Type: application/json`.\n5. Optionally reference your tutor's [Agent Card](https://github.com/mizcausevic-dev/agent-cards-spec) via the `agent_card_uri` field so reviewers can chain through.\n\n## Files in this repo\n\n- [`SPEC.md`](SPEC.md) — full v0.1 specification\n- [`tutor-card.schema.json`](tutor-card.schema.json) — JSON Schema (draft 2020-12)\n- [`examples/`](examples/) — reference Tutor Cards for a K-12 math tutor, a high-school reading tutor, and a college-level computer-science assistant\n\n## Status\n\n**v0.1 draft.** Issues and pull requests welcome.\n\n## License\n\nMIT-licensed. The specification text, JSON Schema, and example documents in this repository may be freely implemented, extended, redistributed, or incorporated into commercial or non-commercial products with attribution. Reference implementations of this spec (such as [mcp-kinetic-gain](https://github.com/mizcausevic-dev/mcp-kinetic-gain)) are licensed separately under AGPL-3.0.\n\n## Kinetic Gain Protocol Suite\n\nA family of open specifications for the answer-engine and agent era:\n\n| Spec | What it does |\n|---|---|\n| [AEO Protocol](https://github.com/mizcausevic-dev/aeo-protocol-spec) | Entity declaration at `/.well-known/aeo.json` |\n| [Prompt Provenance](https://github.com/mizcausevic-dev/prompt-provenance-spec) | Versioned, lineaged, reviewable LLM prompt records |\n| [Agent Cards](https://github.com/mizcausevic-dev/agent-cards-spec) | Declarative agent capability + refusal disclosure |\n| [AI Evidence Format](https://github.com/mizcausevic-dev/ai-evidence-format-spec) | Structured citations for LLM-generated claims |\n| [MCP Tool Cards](https://github.com/mizcausevic-dev/mcp-tool-card-spec) | Per-tool disclosure for Model Context Protocol servers |\n| **AI Tutor Cards** (this) | EdTech-specialized agent disclosure (vendor-side) |\n| [Student AI Disclosure](https://github.com/mizcausevic-dev/student-ai-disclosure-spec) | Student-side disclosure attached to submitted work |\n| [Classroom AI AUP](https://github.com/mizcausevic-dev/classroom-ai-aup-spec) | District / school / course AI policy (third leg of the EdTech trio) |\n| [AI Incident Card](https://github.com/mizcausevic-dev/ai-incident-card-spec) | Post-incident disclosure — references Tutor Cards via `affected.tutor_card_uris[]` (mandated-reporter failures especially) |\n| [Clinical AI Disclosure](https://github.com/mizcausevic-dev/clinical-ai-disclosure-spec) | **HealthTech sibling** — the healthcare-vertical version of this spec. Same disclosure philosophy, HIPAA/FDA/SaMD-flavored fields. |\n\n---\n\n**Connect:** [LinkedIn](https://www.linkedin.com/in/mirzacausevic/) · [Kinetic Gain](https://kineticgain.com) · [Medium](https://medium.com/@mizcausevic/) · [Skills](https://mizcausevic.com/skills/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmizcausevic-dev%2Fai-tutor-card-spec","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmizcausevic-dev%2Fai-tutor-card-spec","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmizcausevic-dev%2Fai-tutor-card-spec/lists"}