A neurosymbolic runtime that answers only what it can prove from a governed memory, cites every premise, quarantines what it merely believes — and says so, out loud, when it doesn't know.
No black boxes: every answer is proven, cited, a labeled belief, or a loud abstention — never a guess dressed as a fact.
Every answer wears its mode. Here is one in Proven — open it and check the chain yourself.
Yes — fluconazole inhibits CYP2C9, the enzyme that clears warfarin, so warfarin exposure rises and bleeding risk increases. Every step below cites an FDA label.
An illustration of the Proven mode. When Noesis can't ground a chain, it abstains out loud instead — refusal is a feature, not a failure.
How the Work Actually Flows Most writing about AI agents shows you the last ten minutes: someone types a request, an agent writes code, the code works. That is the
lands on feature-b main's log -> does not contain it A's own git log -> looks correct to A nothing errored, nothing warned With a worktree: A stays on main,
Error: No such option '--board' (create --help: 0 mentions of board) board-add research --preset hdd -> rc 0, installs NO hdd skills; /hypothesis /experiment /idea /literature all absent, all four
arrow-kanban 43s cold, rustc 1.97.1, macOS arm64 init --theme software 0s, .arrow-kanban/ + 7 templates create feature … 0s, "Created FT-1300" board / list render as shown items.parquet 6140 bytes,
When a Tool Earns Its Place You have run the loop a few times now. Each hypothesis is a file, each result is a file next to it, and every
materialize to host language -> compute -> discard) is a general shape this post borrows without the paper's own unmeasured figures. - PAPER-4578 (V18, executable symbolic reasoning over Arrow +
Go and Look: Closing Your First Loop You wrote something down. A claim, a number that would settle it, and a date — committed somewhere you cannot quietly edit it.
60%, commit moved back 26 days, clean. Worse, the fix was already in the page and orphaned: Step 1 created a GitHub account, justified it as "where your timestamp comes
Nobody needs another kanban board, and this post is not about one. We open-sourced arrow-kanban — an Arrow-native work-graph engine with Parquet persistence, typed relationships, and a NATS server mode
The market spent July discovering that agents should think in graphs. It is right. The label is new — roughly three weeks old at meme scale — but the two