{"generated":"2026-09-01","schema":"https://null.design/registry-schema","projects":[{"id":"ND-001","title":"Null Operator","slug":"null-operator","classification":{"type":["ACTIVE","PRIVATE INFRASTRUCTURE"],"practice":["agentic systems","automation","research infrastructure"]},"status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"The studio's own operating layer: a lead agent decomposes work into narrow, test-specified jobs, dispatches them to interchangeable worker models (OpenCode/GLM, Codex, a self-hosted agent), gates every result behind tests and a human decision, and records provenance for each run.","topics":["orchestration","dispatch","provenance","human gates","worker fleets"],"research_programs":[],"repositories":[{"url":"https://github.com/nulldesign/null.design","role":"canonical","visibility":"public"}],"agents":["Operator","Builder","Critic","Archivist","Publisher"],"human_gates":["publication approval","repository transfers","deployment and DNS","external commitments"],"commercial":{"commissionable":true,"product_candidate":false,"revenue_model":null},"provenance":{"ownership":"original","original_repository":null,"notes":"Generalised from a dispatch harness first built inside a personal project (2026-09-01) and from earlier fleet runs producing teaching decks. The generalised harness lives in the site repository nulldesign/null.design (agents/dispatch.sh, AGENTS.md, registry/runs), created 2026-09-01. Worker runtimes are third-party; the contract, gates and run records are Null's.","review_required":false,"third_party":["OpenCode","OpenAI Codex CLI","Hermes Agent (Nous Research)","OpenRouter"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":null,"featured":true,"recommendation":"MOVE TO NULL","order":3,"published":"2026-09-01"},"facts":[{"label":"worker backends","value":"3 (OpenCode, Codex, Hermes over SSH)"},{"label":"first recorded run","value":"RUN-2026-0001"}]},{"id":"ND-002","title":"Qlass","slug":"qlass","classification":{"type":["FLAGSHIP","PRODUCT CANDIDATE"],"practice":["learning environments","software","agentic systems"]},"status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"Self-hostable, open-source learning management infrastructure (Next.js, PostgreSQL, Prisma) with a teacher-gated agentic unit builder: plan → author → review, every run logged to an audit table, nothing published without a human. A candidate learning environment for Agentic Education.","topics":["LMS","classroom","BYOK","audit log","human gate","open source"],"research_programs":["ND-R01"],"repositories":[{"url":"https://github.com/willieavendano/qlass-lms","role":"canonical","visibility":"public"},{"url":"https://github.com/nulldesign/qlass-lms","role":"mirror","visibility":"public"}],"agents":["Builder","Critic"],"human_gates":["teacher reviews and publishes every generated unit","provider keys supplied by the instance owner (BYOK)"],"commercial":{"commissionable":true,"product_candidate":true,"revenue_model":"open source; hosted tier and connectors under evaluation (ROADMAP phase 4)"},"provenance":{"ownership":"original","original_repository":"https://github.com/willieavendano/qlass-lms","notes":"34 commits, 2026-06-04 → 2026-07-07; 26 carry Co-Authored-By: Claude trailers. MIT licence. CI runs Prisma validate, typecheck, tests and a production build against Postgres.","review_required":false,"third_party":["Next.js","Prisma","NextAuth","Vercel AI SDK","Railway"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":null,"featured":true,"recommendation":"MIRROR UNDER NULL","order":1,"published":"2026-06-05"},"facts":[{"label":"licence","value":"MIT"},{"label":"data models","value":"28 (Prisma)"},{"label":"test files","value":"8 (Vitest)"},{"label":"agent pipeline","value":"plan → author → review → teacher publish"},{"label":"audit table","value":"AgentRun"}]},{"id":"ND-003","title":"Atlas Curriculum Audit","slug":"atlas-curriculum-audit","classification":{"type":["CLIENT-CAPABLE","TEACHING"],"practice":["agentic systems","automation"]},"status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"An agent skill that reconciles a school's gradebook records against its curriculum-mapping system and a published course guide: build the assignment inventory, classify evidence, correct misplacements, verify every unit — with a human confirming every destructive step. Practical agentic orchestration across educational systems of record.","topics":["curriculum mapping","reconciliation","browser agents","agent skills","PLTW"],"research_programs":[],"repositories":[],"agents":["Researcher","Builder","Critic"],"human_gates":["every deletion or move in the curriculum system is confirmed by the teacher","vendor AI features used only when explicitly authorised"],"commercial":{"commissionable":true,"product_candidate":true,"revenue_model":"portable kit (ND-KIT-001) — candidate"},"provenance":{"ownership":"original","review_required":true,"third_party":["a curriculum-mapping tool","a student-information system","a vendor course guide"],"ai_coauthored":false},"publication":{"case_study":true,"public_url":null,"featured":true,"recommendation":"FEATURE ONLY","order":5,"published":"2026-06-07"},"facts":[{"label":"form","value":"agent skill (SKILL.md), runner-portable"},{"label":"workflow steps","value":"6"}]},{"id":"ND-004","title":"arXiv Weekly","slug":"arxiv-weekly","classification":{"type":["ACTIVE","RESEARCH"],"practice":["research infrastructure","automation","agentic systems"]},"status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"Autonomous weekly research infrastructure: search 21 arXiv categories, enrich with citation data, filter 100 candidates to 5–10, synthesise a briefing into a knowledge vault, write a script, produce audio, publish an RSS podcast feed. Running unattended every Monday since June 2026.","topics":["arXiv","Semantic Scholar","research digest","podcast","scheduled agents"],"research_programs":[],"repositories":[{"url":"https://github.com/willieavendano/arxiv-weekly-podcast","role":"publish-sink","visibility":"public","note":"Feed and episodes only; the pipeline is a skill in a self-hosted agent."}],"agents":["Scout","Researcher","Analyst","Publisher"],"human_gates":["category list and filter criteria set by a human","no human review per episode today (documented as a gap; see ND-P04)"],"commercial":{"commissionable":true,"product_candidate":true,"revenue_model":"Null Brief (ND-P04) — free digest first"},"provenance":{"ownership":"original","original_repository":"https://github.com/willieavendano/arxiv-weekly-podcast","notes":"All 16 repo commits are made by the agent process itself. Pipeline stages verified in the skill definition on the host; TTS moved from Edge TTS to ElevenLabs after episode 1.","review_required":false,"third_party":["arXiv API","Semantic Scholar API","Hermes Agent (Nous Research)","ElevenLabs","GitHub Pages"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":"https://willieavendano.github.io/arxiv-weekly-podcast/feed.xml","featured":true,"recommendation":"FEATURE ONLY","order":2,"published":"2026-06-09"},"facts":[{"label":"episodes","value":"12 (2026-06-09 → 2026-08-31)"},{"label":"categories","value":"21"},{"label":"candidates per week","value":"100 → 5–10"},{"label":"cadence","value":"weekly"}]},{"id":"ND-005","title":"MDSolids Web","slug":"mdsolids-web","classification":{"type":["FLAGSHIP","PRODUCT CANDIDATE","TEACHING"],"practice":["software","learning environments"]},"status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"An open-source, browser-based, clean-room reimplementation of the classic mechanics-of-materials teaching suite: section properties, axial, torsion, beams, trusses, columns, Mohr's circle, combined loading, pressure vessels. Built by a human directing a fleet of agents against a shared module contract.","topics":["mechanics of materials","engineering education","numerical methods","agent fleet"],"research_programs":["ND-R02"],"repositories":[{"url":"https://github.com/willieavendano/mdsolids","role":"canonical","visibility":"public"},{"url":"https://github.com/nulldesign/mdsolids","role":"mirror","visibility":"public"}],"agents":["Builder","Critic"],"human_gates":["module contract and worked examples defined by the author","integration and review of every generated module"],"commercial":{"commissionable":false,"product_candidate":true,"revenue_model":"open source; departmental licence or support — candidate"},"provenance":{"ownership":"original","original_repository":"https://github.com/willieavendano/mdsolids","notes":"Clean-room reimplementation; not affiliated with or derived from the original MDSolids by T. A. Philpot. 13 commits with Claude co-author trailers; parallel modules produced by dispatched workers, integrated by a lead agent under human review.","review_required":false,"third_party":["Vite","Vitest"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":"https://willieavendano.github.io/mdsolids/","featured":true,"recommendation":"MIRROR UNDER NULL","order":4,"published":"2026-06-10"},"facts":[{"label":"modules","value":"11"},{"label":"licence","value":"MIT"},{"label":"deployed","value":"GitHub Pages"}]},{"id":"ND-006","title":"Stock Forecast in the Browser","slug":"stock-forecast","classification":{"type":["RESEARCH","TEACHING"],"practice":["data systems","software"]},"status":"complete","visibility":"public","year":{"started":2026,"ended":2026},"summary":"A price forecaster that runs entirely in the browser: a two-layer LSTM, geometric Brownian motion with Monte Carlo confidence bands, a decision-tree regressor over engineered indicators, and a disagreement-widened ensemble. Built as a research exemplar for a secondary-school research course.","topics":["LSTM","Monte Carlo","TensorFlow.js","forecasting","secondary research"],"research_programs":["ND-R02"],"repositories":[{"url":"https://github.com/willieavendano/stock-forecast","role":"canonical","visibility":"public"}],"agents":["Builder"],"human_gates":[],"commercial":{"commissionable":false,"product_candidate":false,"revenue_model":null},"provenance":{"ownership":"original","original_repository":"https://github.com/willieavendano/stock-forecast","notes":"All 13 commits by the author; 11 carry AI co-author trailers (commit log as of 2026-09-01). Attributed as a teacher-built exemplar by human decision (RUN-2026-0001, 2026-09-01). The repository README was updated to that framing by a pull request merged on 2026-09-01, after which the link was released to public pages.","review_required":false,"third_party":["TensorFlow.js","React","Recharts","Alpha Vantage","Yahoo Finance"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":null,"featured":false,"recommendation":"FEATURE ONLY","published":"2026-09-01"},"facts":[{"label":"models","value":"4 (LSTM, GBM-MC, decision tree, ensemble)"}]},{"id":"ND-007","title":"Political Polarity","slug":"political-polarity","classification":{"type":["RESEARCH","TEACHING"],"practice":["data systems","intelligent systems"]},"status":"complete","visibility":"public","year":{"started":2026,"ended":2026},"summary":"An NLP pipeline for measuring political lean in text corpora: a TF-IDF + logistic-regression baseline, a fine-tuned DistilBERT path, synthetic-data generation, and a model card stating out-of-scope uses. A study in what a single researcher can now run that once required a team.","topics":["NLP","transformers","model cards","research ethics","secondary research"],"research_programs":["ND-R02"],"repositories":[{"url":"https://github.com/willieavendano/political-polarity","role":"canonical","visibility":"public"}],"agents":["Builder","Critic"],"human_gates":["model card limits use; no individual profiling"],"commercial":{"commissionable":false,"product_candidate":false,"revenue_model":null},"provenance":{"ownership":"original","original_repository":"https://github.com/willieavendano/political-polarity","notes":"All 3 commits by the author (commit log as of 2026-09-01); no data committed. Attributed as a teacher-built exemplar by human decision (RUN-2026-0001, 2026-09-01). As with ND-006, the repository README was updated to that framing by a pull request merged on 2026-09-01, after which the link was released.","review_required":false,"third_party":["scikit-learn","Hugging Face Transformers","Gradio"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":null,"featured":false,"recommendation":"FEATURE ONLY","published":"2026-09-01"},"facts":[{"label":"models","value":"TF-IDF + LR baseline; DistilBERT"},{"label":"model card","value":"yes"}]},{"id":"ND-008","title":"Six Models, One Lesson","slug":"six-models-one-lesson","classification":{"type":["RESEARCH","EXPERIMENT"],"practice":["intelligent systems","learning environments"]},"status":"complete","visibility":"public","year":{"started":2026,"ended":2026},"summary":"Six model routes given the identical lesson-design brief (an AI-literacy lesson for a statistics course), scored on a fixed rubric, with the route of invocation recorded and a disclosed conflict: the reviewer graded its own submission. The first Agentic Education experiment (AE-001).","topics":["model comparison","rubric","lesson design","self-critique","AI literacy"],"research_programs":["ND-R01"],"repositories":[],"agents":["Analyst","Critic"],"human_gates":["rubric and prompt authored by the teacher","conclusions written by the teacher"],"commercial":{"commissionable":false,"product_candidate":false,"revenue_model":null},"provenance":{"ownership":"original","original_repository":null,"notes":"Local project without a remote at discovery time; to be pushed under Null.","review_required":false,"third_party":["Claude","Codex","Gemini","DeepSeek"],"ai_coauthored":true},"publication":{"case_study":true,"public_url":null,"featured":false,"recommendation":"MOVE TO NULL"},"facts":[{"label":"routes compared","value":"6"},{"label":"rubric dimensions","value":"5"}]},{"id":"ND-009","title":"Course Operations Compiler","slug":"course-operations-compiler","visibility":"internal","status":"active","summary":"Treat syllabi, block plans, warm-ups, exit tickets and slide decks as compiled artifacts: single-source calendar and course specs, deterministic generators, a tested date library, an agent skill for deck authoring, and programmatic QA for layout overflow. Architecture described publicly; repositories stay private.","classification":{"type":["PRIVATE INFRASTRUCTURE","TEACHING"],"practice":["automation","software"]}},{"id":"ND-010","title":"Approval Gate for Consequential Agent Actions","slug":"approval-gate","visibility":"internal","status":"active","summary":"A small service and two automation flows that let an agent propose actions near money without being trusted: position caps, a falsifiable thesis required for every proposal, a push-notification approval loop, and a 24-hour auto-reject. The pattern is public; the data is not.","classification":{"type":["EXPERIMENT","PRIVATE INFRASTRUCTURE"],"practice":["agentic systems","automation"]}},{"id":"ND-011","title":"Knowledge Base as Agent Memory","slug":"knowledge-base-as-agent-memory","visibility":"internal","status":"active","summary":"A git-synced Markdown vault embedded into pgvector on a schedule and exposed to agents as a single read-only search tool. Long-term memory that humans can read, edit and version — and agents can only query.","classification":{"type":["PRIVATE INFRASTRUCTURE","RESEARCH"],"practice":["research infrastructure","intelligent systems"]}}],"programs":[{"id":"ND-R01","title":"Agentic Education","slug":"agentic-education","status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"Agentic Education investigates how computational agents can increase human agency in learning without outsourcing the cognitive work through which learning occurs.","definition":"Agentic Education investigates how computational agents can increase human agency in learning without outsourcing the cognitive work through which learning occurs.","principle":"The purpose of the agent is to increase the agency of the learner.","workflow":["DEFINE","DECOMPOSE","DELEGATE","OBSERVE","VERIFY","SYNTHESIZE","DEFEND"],"questions":["Which intellectual tasks should learners delegate?","Which tasks should remain human because performing them produces understanding?","How should learners verify computational-agent output?","How should assessment change when agent use is legitimate?","What is agent orchestration literacy?","How can agents expand the complexity of problems learners can investigate?","How should teachers construct environments containing human and computational agents?","How do we distinguish increased learner agency from automated learning?"],"outputs":["research","essays","classroom experiments","software","protocols","curriculum","professional-development material","products"],"experiments":[{"id":"AE-001","title":"Six models, one lesson","status":"complete","project":"ND-008","summary":"Six model routes given one lesson-design brief, scored on a fixed rubric, with a disclosed reviewer conflict."},{"id":"AE-002","title":"Teacher-gated unit builder pilot","status":"planned","project":"ND-002","summary":"A bounded pilot of Qlass's plan → author → review → publish pipeline with one class and one unit; success criteria pre-registered."},{"id":"AE-003","title":"Agentic Research Studio protocol","status":"planned","project":null,"summary":"One cycle of student-directed research with scoped Researcher, Analyst and Critic agents; learners keep definition, decomposition, delegation, verification, synthesis and defence."}],"projects":["ND-002","ND-008","ND-009"],"publication":{"public_url":null,"featured":true,"published":"2026-09-01"}},{"id":"ND-R02","title":"Computational Research in Secondary Education","slug":"computational-research-in-secondary-education","status":"active","visibility":"public","year":{"started":2026,"ended":null},"summary":"How advanced computational methods — neural forecasting, Monte Carlo simulation, transformer classifiers, numerical mechanics — change the scale and nature of inquiry available to secondary-school learners and their teachers.","workflow":[],"questions":["What problems become investigable by a sixteen-year-old when a research-grade pipeline fits in a browser tab?","Which parts of a computational method must a learner build by hand to understand it?","How is authorship attributed when a teacher, students and agents all contribute?","What does a defensible model card look like at secondary level?"],"outputs":["case studies","exemplars","protocols","curriculum"],"experiments":[],"projects":["ND-005","ND-006","ND-007"],"publication":{"public_url":null,"featured":true,"published":"2026-09-01"}}],"products":[{"id":"ND-P01","code":"AE-KIT-001","title":"Agentic Education Field Guide","slug":"agentic-education-field-guide","family":"Null Kits","status":"candidate","visibility":"public","summary":"A practitioner kit for teachers: the framework, a lesson-design protocol, a delegation matrix, a verification protocol, assessment rubrics, classroom agent patterns and an implementation guide.","derived_from":["ND-R01","ND-008","ND-009"],"contents":["framework","lesson-design protocol","delegation matrix","verification protocol","assessment rubrics","classroom agent patterns","teacher implementation guide"],"revenue_model":"one-time digital purchase; institutional licence","maintenance":"versioned releases; low-touch after v1","launch_requires":["at least one documented classroom cycle","human-authored claims only","pricing decision"]},{"id":"ND-P02","code":"AE-KIT-002","title":"Agentic Research Studio","slug":"agentic-research-studio","family":"Null Kits","status":"candidate","visibility":"public","summary":"A reproducible framework for student-directed research with scoped research, analysis and critic agents; learners keep problem definition, decomposition, delegation, verification, synthesis and defence.","derived_from":["ND-R01","ND-R02","ND-001"],"contents":["research protocol","agent scopes","verification checklist","defence rubric","run-record template"],"revenue_model":"one-time digital purchase; institutional licence","maintenance":"versioned releases","launch_requires":["one completed AE-003 cycle","consented examples"]},{"id":"ND-P03","code":"ND-KIT-001","title":"Curriculum Audit Agent","slug":"curriculum-audit-agent","family":"Null Kits","status":"candidate","visibility":"public","summary":"A portable workflow for reconciling a school's system of record against its curriculum map: configurable source/target systems, a placement taxonomy, human confirmation gates and a structured audit log.","derived_from":["ND-003"],"contents":["skill definition","placement taxonomy template","audit-log schema","operator guide"],"revenue_model":"one-time purchase per school; setup commission","maintenance":"vendor UI changes require periodic revision","launch_requires":["sanitised reference implementation","second-school validation"]},{"id":"ND-P04","code":"ND-BRIEF-001","title":"Null Brief — Agentic Education","slug":"null-brief-agentic-education","family":"Null Brief","status":"candidate","visibility":"public","summary":"An agent-assisted research briefing on Agentic Education: search → filter → cluster → read → synthesise → critique → human approval → publish. Free public digest first; paid and institutional editions only after sustained readership.","derived_from":["ND-004","ND-R01"],"contents":["weekly digest","source list with provenance","critique notes"],"revenue_model":"free digest; paid individual edition; institutional licence (later)","maintenance":"~1–2 hours of human review per issue; the approval gate is the cost","launch_requires":["education-specific filters","critique stage","human approval stage","12 free issues before any paid tier"]}],"runs":[{"id":"RUN-2026-0001","date":"2026-09-01","title":"Discovery, architecture and initial build of null.design","status":"running","roles":[{"role":"Operator","agent":"Claude Fable 5 (Claude Code)","scope":"planning, synthesis, integration, review"},{"role":"Scout","agent":"Claude Sonnet 5 ×3 (subagents)","scope":"read-only repository, infrastructure and education inventories"},{"role":"Builder","agent":"GLM 5.3 Flash (OpenCode)","scope":"src/lib/ids.ts, src/lib/rss.ts against tests — gate PASS on first attempt (both)"},{"role":"Builder","agent":"GPT-5.6 Sol (Codex)","scope":"src/lib/registry.ts, scripts/validate-registry.ts against tests — gate PASS on first attempt"},{"role":"Researcher","agent":"Claude Sonnet 5 ×2 (subagents)","scope":"fact-constrained case-study drafts from the discovery report"},{"role":"Critic","agent":"Claude Opus 5 (subagent)","scope":"fabrication, leakage, hype, provenance, consistency and accessibility review of the site, registry and report"},{"role":"Scout","agent":"Claude Sonnet 5 (subagent)","scope":"read-only leakage and provenance scan of the four repositories to be linked or mirrored, before any mirror was created"},{"role":"Builder","agent":"GLM 5.3 Flash (OpenCode)","scope":"src/lib/facts.ts against src/lib/facts.test.ts — gate PASS on first attempt"},{"role":"Builder","agent":"Claude Sonnet 5 (subagent)","scope":"README attribution pull requests on the two exemplar repositories (opened, not merged)"},{"role":"Critic","agent":"Claude Opus 5 (subagent)","scope":"second pass over the changes made after the human decisions of 2026-09-01"},{"role":"Builder","agent":"GLM 5.3 Flash (OpenCode)","scope":"src/lib/facts.ts factsTableProblems and validator wiring against src/lib/facts.test.ts — gate PASS on first attempt"},{"role":"Builder","agent":"GPT-5.6 Sol (Codex)","scope":"src/lib/publish-plan.ts against src/lib/publish-plan.test.ts — gate PASS on first attempt"},{"role":"Builder","agent":"GLM 5.3 Flash (OpenCode)","scope":"src/lib/checks.ts against src/lib/checks.test.ts — gate FAIL: the worker exhausted its reasoning budget and wrote nothing; job re-dispatched to Codex"},{"role":"Builder","agent":"GPT-5.6 Sol (Codex)","scope":"src/lib/checks.ts (stage-7 leakage and language checks) against src/lib/checks.test.ts — gate PASS on first attempt"},{"role":"Builder","agent":"GPT-5.6 Sol (Codex)","scope":"scripts/publish.ts and scripts/publish.test.ts (pipeline stages 1, 7, 9 and the gate checklist; never merges or deploys) — gate PASS on first attempt"}],"artifacts":["docs/discovery/2026-09-01-discovery-report.md (private; kept out of the publishable tree)","docs/discovery/screenshots/ (private)","registry/schema.ts and 20 records (13 projects, 2 programs, 4 products, 1 run)","registry/_templates/project.yaml","content/work/ (11 case studies) and content/research/ (2 program essays)","content/_templates/ (project, research)","src/ — Next.js App Router site (index, work, research, process, studio, /dev/null, feed.xml, registry.json, sitemap, robots, OG image, icon)","src/lib/ids.ts, src/lib/rss.ts, src/lib/registry.ts, src/lib/content.ts (+ 33 tests)","scripts/validate-registry.ts (frontmatter and facts-table cross-check)","src/lib/facts.ts (+ tests)","LICENSE (MIT)","github.com/nulldesign/null.design (repository; branch run/RUN-2026-0001; pull request","github.com/nulldesign/qlass-lms and github.com/nulldesign/mdsolids (forks; mirrors of the canonical repositories)","Vercel project \"null-design\" (preview deployments only; no production alias)","agents/dispatch.sh, agents/roles.md, .claude/agents/worker-*.md, opencode.json",".github/workflows/check.yml (typecheck, tests, registry validation, lint, build on pull requests; never merges or deploys)","src/app/fonts/IBMPlexSans-Medium.ttf + OFL.txt (bundled for the OG image; deferred critic item resolved)","src/lib/publish-plan.ts (+ tests) — pure planner for the publish pipeline; stops at the human gate","src/lib/checks.ts (+ tests) — stage-7 leakage and banned-language checks as a pure module","scripts/publish.ts (+ tests) — npm run null:publish -- <ID> [--dry-run]: validate, critique-check, build, print the gate checklist; refuses stages 12–13 without a recorded approval","src/lib/facts.ts factsTableProblems (+ tests) — per-row cell-count reporting; deferred critic item resolved","AGENTS.md, README.md","docs/identity/directions.md, docs/identity/moodboard.md, public/identity/*.svg","docs/architecture/publishing-pipeline.md"],"human_decisions":[{"decision":"Renew the studio domain (renewed by the human director; expiry date kept private)","outcome":"approved","date":"2026-09-01"},{"decision":"Agentic Teaching ↔ Agentic Education positioning: complementary and kept distinct; no link to the parked agenticteaching.com","outcome":"approved","date":"2026-09-01"},{"decision":"Attribute ND-006 and ND-007 as teacher-built exemplars (commit record); publish both case studies","outcome":"approved","date":"2026-09-01"},{"decision":"Revive the nulldesign GitHub organisation; create nulldesign/null.design and push the run branch","outcome":"approved","date":"2026-09-01"},{"decision":"Mirror Qlass and MDSolids under nulldesign as forks; canonical repositories unchanged","outcome":"approved","date":"2026-09-01"},{"decision":"Deploy the scaffold to a preview URL only — no production alias, no domain, no DNS change","outcome":"approved","date":"2026-09-01"},{"decision":"Provision studio@null.design mailbox before the contact address goes live (human director will create it; no agent action)","outcome":"deferred","date":"2026-09-01"},{"decision":"Code licence: MIT for the repository (LICENSE applies to everything in it)","outcome":"approved","date":"2026-09-01"},{"decision":"Merge run/RUN-2026-0001 to main","outcome":"approved","date":"2026-09-01"},{"decision":"Attach null.design to a production deployment","outcome":"pending","date":null},{"decision":"Merge the README attribution pull requests on the two exemplar repositories (opened by the Operator as the mechanism for the attribution decision, without a separate approval; closing them reverts the action), then clear review_required on ND-006 and ND-007 so their repository links publish","outcome":"approved","date":"2026-09-01"}]}]}