1:"$Sreact.fragment" 2:I[44223,["/_next/static/chunks/02ti70zu7rea_.js","/_next/static/chunks/0d3shmwh5_nmn.js","/_next/static/chunks/06_fwbpl-tgls.js"],"FadeIn"] 9:I[22016,["/_next/static/chunks/02ti70zu7rea_.js","/_next/static/chunks/0d3shmwh5_nmn.js","/_next/static/chunks/06_fwbpl-tgls.js"],""] a:I[97367,["/_next/static/chunks/02ti70zu7rea_.js","/_next/static/chunks/0d3shmwh5_nmn.js"],"OutletBoundary"] b:"$Sreact.suspense" 0:{"rsc":["$","$1","c",{"children":[["$","$L2",null,{"children":["$","section",null,{"className":"relative overflow-hidden depth-section py-12 sm:py-16 section-insights-bg ","children":["$","div",null,{"className":"mx-auto max-w-6xl px-4","children":["$","div",null,{"className":"section-panel section-foreground-gradient","children":[["$","header",null,{"children":[["$","div",null,{"className":"max-w-3xl","children":[["$","p",null,{"className":"text-sm font-semibold tracking-wide theme-text-accent","children":"INSIGHTS"}],["$","h2",null,{"className":"mt-2 text-2xl font-semibold tracking-tight theme-text-primary sm:text-3xl font-[var(--font-heading)]","children":"Cost-Controlled AI: Routing, Caching, and Budget Guardrails"}]]}],["$","p",null,{"className":"mt-3 text-base leading-7 text-pretty theme-text-secondary","children":"Routing, caching, and budgets as first-class design decisions."}]]}],["$","div",null,{"className":"mt-8","children":["$","div",null,{"className":"mt-2 max-w-3xl space-y-10","children":[["$","p",null,{"className":"text-base leading-7 theme-text-secondary","children":"Cost surprises rarely come from a single expensive call—they come from missing routing, unbounded retries, and caches that were never designed. I treat tokens like any other metered resource: budgets, alerts, and fallbacks belong in the architecture diagram."}],[["$","section","0",{"className":"space-y-4","children":[["$","h2",null,{"className":"text-lg font-semibold tracking-tight theme-text-primary font-[var(--font-heading)]","children":"Route before you spend"}],[["$","p","0",{"className":"text-base leading-7 theme-text-secondary","children":"Classify requests by complexity and sensitivity. Simple extraction can use smaller models or rules; only escalate to the largest model when metrics justify it. Routing policy is code—and should be versioned like code."}],["$","p","1",{"className":"text-base leading-7 theme-text-secondary","children":"Instrument routing decisions: how often each path fires, and what quality delta you get from escalation. Without that, you cannot defend a more expensive tier."}]]]}],["$","section","1",{"className":"space-y-4","children":[["$","h2",null,{"className":"text-lg font-semibold tracking-tight theme-text-primary font-[var(--font-heading)]","children":"Cache what repeats"}],[["$","p","0",{"className":"text-base leading-7 theme-text-secondary","children":"Embed caches, retrieval bundles, and summarisation of stable corpora with explicit TTLs and invalidation. Do not cache personalised answers next to shared facts without segmenting keys."}],["$","p","1",{"className":"text-base leading-7 theme-text-secondary","children":"Watch for cache poisoning and stale permissions: invalidate on auth changes and on document updates that affect retrieved content."}]]]}],["$","section","2",{"className":"space-y-4","children":[["$","h2",null,{"className":"text-lg font-semibold tracking-tight theme-text-primary font-[var(--font-heading)]","children":"Budgets and brakes"}],[["$","p","0",{"className":"text-base leading-7 theme-text-secondary","children":"Per-workflow and per-tenant caps, with graceful degradation: shorter context, cheaper model, or human handoff when limits approach. Visibility in Monitor ties spend to business events, not just dashboards for finance."}]]]}],["$","section","3",{"className":"space-y-4","children":[["$","h2",null,{"className":"text-lg font-semibold tracking-tight theme-text-primary font-[var(--font-heading)]","children":"Chargeback and culture"}],[["$","p","0",{"className":"text-base leading-7 theme-text-secondary","children":"Make cost visible to product owners early—weekly burn by feature, not a monthly surprise. When teams see spend next to quality metrics, trade-offs become technical conversations instead of blame cycles."}]]]}]],["$L3"],"$L4","$L5","$L6"]}]}]]}]}]}]}],["$L7"],"$L8"]}],"isPartial":false,"staleTime":300,"varyParams":null,"buildId":"lfEugLFFjbfrSWt8vjHCz"} 3:["$","p","0",{"className":"text-base leading-7 theme-text-secondary","children":"Predictable spend is an engineering outcome. Jomiko helps teams wire cost controls into the same contracts the rest of the system uses."}] 4:["$","p",null,{"className":"text-base leading-7 theme-text-secondary","children":["If you want help applying this to your architecture,"," ",["$","$L9",null,{"href":"/contact","className":"font-semibold underline-slide theme-text-primary","children":"book a strategy call"}]," ","or an architecture review."]}] 5:["$","p",null,{"className":"text-xs theme-text-secondary","children":["Tags:"," ",["$","span",null,{"className":"text-[var(--text-secondary)]","children":"cost · routing · caching · guardrails"}]]}] 6:["$","p",null,{"children":["$","$L9",null,{"href":"/insights","className":"text-sm font-semibold underline-slide theme-text-secondary hover:text-[var(--text-primary)] focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-[var(--accent)] focus-visible:ring-offset-2 theme-ring-offset rounded px-1 py-0.5","children":"← All insights"}]}] 7:["$","script","script-0",{"src":"/_next/static/chunks/06_fwbpl-tgls.js","async":true}] 8:["$","$La",null,{"children":["$","$b",null,{"name":"Next.MetadataOutlet","children":"$@c"}]}] c:null