craftedbydaniel.hashnode.devMy Voice Router That Refuses to Think: Pattern‑First Multi‑Agent Orchestration for Sub‑Second LatencyI built my voice assistant orchestration layer around a stubborn rule: Don't spend an LLM call on a problem that a regex can solve. That reads like common sense until you ship a voice-first UX. People tolerate a spinner on a website; they do not tole...2m ago·14 min read
craftedbydaniel.hashnode.devDefensive Multi‑Agent Scoring: How I Made LLM Reviews Clamp, Stream, and Fail LoudlyA few days ago my review stage did the most dangerous thing a multi‑agent system can do: it looked like it worked. The UI showed progress. The pipeline marched forward. And yet one of the agents had effectively returned “nothing,” which meant my fina...1h ago·7 min read
craftedbydaniel.hashnode.devDiversification After Scoring: The Step That Stops My Scene Compiler From Picking Five ParaphrasesA few weeks into running my scene compiler at scale, I hit an embarrassing pattern: I’d ask for five candidates, score them, and the “top five” would be… the same idea, phrased five ways. Not bad ideas—often the highest composite scores—but clustered...1h ago·7 min read
craftedbydaniel.hashnode.devTurning CRM Audit Noise into a Transition Graph: Normalizing Events, Sessionizing Creation Bursts, and Extracting Time‑Weighted State EdgesA deal gets created, a contact gets created, an account gets created… and then the audit trail tells three different stories depending on whether you’re looking at webhooks, API logs, or what the CRM UI eventually shows. When I first tried to audit o...1h ago·9 min read
craftedbydaniel.hashnode.devI got SAM3 video tracking wrong: the session wasn’t the problem—my reprojection wasI assumed the flicker was SAM3 being temperamental. I watched masks snap on and off across consecutive frames, and my first instinct was to reach for the usual bag of excuses: “it’s a hard scene,” “video is noisy,” “the model needs more context.” Wha...1h ago·8 min read