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.
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 (MIT)
A short, honest note for anyone reading closely. Parts of this site describe an earlier chapter of the work — the never-launder reasoning engine, the drug-interaction database that shows its proof,
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 practices under
Most drug-interaction alerts arrive as a verdict with no receipt. "Major interaction." Says who? Based on what? A clinician can't tell, so — under time pressure, for
Ask a commercial interaction checker about a three-drug problem and you'll get, at best, three separate two-drug answers. That's not a limitation of the vendor'
Here is the failure mode that should scare anyone who ships clinical decision support: a drug-interaction checker that, when it doesn't know, quietly returns nothing. No alert. No
If you're building AI systems — agents, RAG pipelines, fine-tuned models, anything that learns — you already know that unit tests are necessary and completely insufficient. Tests tell you whether
Our simulation predicted 80% accuracy. Live testing delivered 54%. That's not a rounding error. That's a 26-point gap that calls into question how we validate AI
Every few months, a new paper announces a technique to "reduce hallucinations" in large language models. Retrieval-Augmented Generation. Chain-of-thought prompting. Constitutional AI. Self-consistency checking. These are patches on
Open-world video games face a problem that looks nothing like AI memory — until you squint. The Rendering Problem In a game like Zelda, Breath of the Wild, the world is