Each of us mostly talks to our own AI agent. The agents stay synchronized through one canonical git repository — kairos/kairos on Robertas's Forgejo server. Every change is dated and attributed, the full history is permanent, and any clone can restore the whole.
A decision that lives in chat scrollback is gone in a week. So the repo has exactly three landing zones: DECISIONS.md — what's settled and why, so nothing gets re-litigated; STATUS.md — who owns what right now; CONTEXT/ — the corrected facts, each carrying its date and confidence label.
n=1, never a trend. A self-report is a claim until corroborated. Killed claims stay visible so they cannot return under new wording. The engagement asks Mysterium for decision discipline — it has to run on the same standard itself.Four words carry the analytical load here, and they are not interchangeable. Fact — computed from named source rows; carries its table, window, and query. Hypothesis — a falsifiable claim written together with its test: what evidence would confirm it, what would refute it, where that evidence lives. No test named — not a hypothesis yet. Assumption — a premise adopted untested so work can proceed; named at the point where the work rests on it. Hunch — pattern-feel without articulated grounds; allowed in conversation, enters the ledger only under that label.
Every gated surface — this War Room included — uses individual identities: an email one-time code per person, no shared passwords, one sign-in for every room behind the door. Rooms are scoped to the identity: curated team rooms for everyone behind the gate; the raw working notes open only to Lee and Šaras — the working-papers rule of section 4, enforced in code.
Everyone keeps private working notes. That is normal professional practice, not secrecy — working papers stay private wherever thinking has to be free to be wrong. The system enforces the flip side: any conclusion that is safe for the whole team must land in the shared repo in the same session it was formed. Hooks check this mechanically — an agent session cannot end with shareable conclusions unpublished.
Humans own judgment and approvals; agents own mechanics. After one-time setup nobody has git duties — ever. Validators reject malformed state before it can commit. Backups run in layers: server-side instance backup on the NAS, plus daily self-verifying full-history bundles held off-NAS on Lee's side.
Because the deliverable is not a report — it is decisions Mysterium can trust. Those require an operation where facts carry confidence, decisions carry dates and owners, access carries names, and nothing depends on anyone's memory. This system is that operation, running in the open where the team can see it.