Show HN: ADRs for AI – Deliberation records for human–AI work, versioned in Git

A Show HN project called ADRs4AI proposes recording human–AI collaboration decisions as Architecture Decision Records versioned in Git, so the reasoning behind each choice persists rather than disappearing after a session. The method, demonstrated on the public frontier-model-observatory repository, has an AI stake open questions with options, rationale, confidence and a falsifier, while the human supplies a single ruling — in the cited example, GPT 5.6 Sol recommended a "C — Bitemporal hybrid" temporal policy and Jérémie Lumbroso answered "C — Bitemporal hybrid" from his phone. The workflow starts from a GitHub template repository, commits a record before work begins, and keeps open questions findable with the command grep -rn '^### QST' docs/adr/.

Your thinking stops disappearing. Your decisions start compounding. The most valuable byproduct of the collaboration between a human and an AI is the thinking — and in ordinary practice, all of it evaporates. You can already make good decisions with your AI. Every session produces reasoning you will need again, and lose by default. This keeps the why, so it compounds. This is the method’s product — one question from a live, public project’s own record, exactly as it sits in the repository: QST-HISTORICAL-TRUTH: How should corrections preserve what was previously believed? - Status: answered - Why asking: Conversation attribution needs “what was true or documented as of date X,” while later research may correct earlier records. - Need: Approve or revise the proposed temporal policy. Options : - A — Mutable present truth : Correct records in place; rely on Git history for prior states. - B — Append-only assertions : Never change claims; append corrections and supersession edges. - C — Bitemporal hybrid : Correct descriptive records when needed, while claims/events carry valid-time, observed-time, and explicit supersession; Git remains a third audit layer. Recommendation : by GPT 5.6 Sol at Perplexity Computer C — Bitemporal hybrid. Rationale : Git history records when repository bytes changed, not when a release became valid or when a provider made a statement. Explicit valid-time and observed-time support historical queries, while supersession edges preserve corrections without forcing every typo into an eternal domain event. Confidence : High that Git history alone is insufficient; medium-high that two temporal axes cover the first release. Falsifier : If real attribution cases require additional independent times, such as product-availability time distinct from announced and effective time, the temporal model must expand rather than overload either axis. ANS: by Jérémie "Sonnet 4.5" Lumbroso via ADRs4AI mobile C — Bitemporal hybrid. From frontier-model-observatory https://github.com/jlumbroso/frontier-model-observatory/blob/main/docs/adr/0003-epistemic-records-and-generated-views.md , verbatim. The AI staked the question; the recommendation — options, rationale, confidence, and what would prove it wrong — is GPT 5.6 Sol’s; the one-line ruling came from the founder’s phone. That’s the whole mechanic : The AI carries the reasoning, the human spends one judgment — accept, override, or any answer in any shape https://github.com/jlumbroso/frontier-model-observatory/blob/main/docs/adr/0007-legible-continuous-integration-and-release-artifacts.md — and the record keeps the why, for every mind that comes later. Real commands, the flow the founder actually runs — one seed, one question, one ruling: 1 · Your copy of the template gh repo create my-project --private --clone \ --template ADRs4AI/human-ai-collaboration-template-A cd my-project 2 · Open CLAUDE.md, fill in the top block messy is fine , then stake the record before any work starts: git add -A && git commit -m "chore: the record begins before the building does" 3 · Recruit — open your agent and offer the mission: claude or your agent of choice "Hello — I have a mission for you. Read about it and tell me if you accept, or any pushback." Then dump your thinking into a first seed — dictation is fine; your AI chunks it into ADRs that keep your actual words, the options, the reasoning, the open questions. Answer the first question it stakes. Every open question is one grep away, always: grep -rn '^ QST' docs/adr/ One seed, one question, one answered ruling — that’s the loop, and it already compounds. Running a crew — several seats, wake-on-brief, you stop being the message bus — is the optional next chapter: steps 7–9 of Get started https://adrs.systems/get-started/ . Dump your thinking into a seed — messy is fine, dictation is fine; capture first. Your AI chunks it into ADRs that keep what usually evaporates: your actual words, the options considered, the reasoning, the open questions. Every question is findable by one grep — QST: — or surfaced by the editor extension, the MCP server, the phone in your pocket; and each arrives with the AI’s options, its recommendation, its rationale, its stated confidence, and what would prove it wrong — so answering streamlines to accept or override : Cognitive load down, bandwidth freed for the deliberations that matter. It’s where conversations become decisions that keep their reasons — deliberative programming , in one habit. You don’t need to be an experienced engineer to start. The method was built through daily practice by one human and a growing crew of AI collaborators, and its whole point is that the record does the remembering — as much for the veteran with too many projects, as for the beginner building their very first one. The extension’s Open Questions view, on this project’s own record: A question, its options, an attributed recommendation — and the answer box. Question 16 of 75, that day. Not transcript archival. Not vector-database “memory.” Not an orchestration platform. Not a claim that an AI possesses persistent identity — the record holds, minds change, and the work resumes either way. The most valuable thing that happens between a human and an AI is not the code, the draft, or the answer. It’s the thinking — and in ordinary practice, all of it evaporates. … It does not make an AI persistent, and it does not make anyone remember. It makes the work resumable — and the thinking compound. — from What is ADRs4AI? https://adrs.systems/what-is/ , the founding essay. A stranger can read it cold; its authorship and review record are public, because that is the method.