Insights
Engineering perspectives on architecture, product development, AI, and the everyday decisions behind useful software.
From the engineering desk
Browse practical articles or follow the latest technology updates.
Subscribe via RSS →Curated links from external sources — not 360Softy original articles.
A cache that has drifted from your database will happily serve wrong prices, expired permissions, or phantom inventory, and it won't feel a shred of guilt about it. Cache consistency is the discipline behind keeping that drift small, so cached values ...
Todo conteúdo sobre “qual linguagem escolher pra Web3” que eu encontro é escrito por quem nunca fez deploy de nada. Compara sintaxe, compara popularidade no GitHub, compara vaga no LinkedIn. Útil até certo ponto, mas é comparação de fora. Eu tive a oportunidade (ou o azar, dependendo do dia) de construir contratos reais nas duas: CryptoMarket, um marketplace de NFTs em Solidity, e Stellar Charge EV, um protocolo de pagamento pra recarga de veículos elétricos em Rust, sobre Soroban (Stellar), fe
Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40% How we moved from "semantic search + hope" to a measured, tunable retrieval pipeline with 95% recall@10 Everyone ships RAG the same way: chunk by 512 tokens, embed with text-embedding-3-small, top-k=5, stuff into context. It works for demos. Then you hit production: Legal contracts: 512 tokens splits clauses mid-sentence API docs: 1000-token chunks drown signal in noise Customer tickets: Conversational c
Building Production-Grade LLM Evaluation Pipelines: From Vibes to Metrics How we replaced "looks good to me" with automated evaluation catching 92% of hallucinations before deployment Three months ago, our team shipped a RAG-based customer support assistant. It worked great in testing — we'd ask it questions, read the answers, and say "yeah, that looks right." Then it hit production. A customer asked about their billing cycle. The assistant confidently cited a policy that didn't exist. Another
When an agent can see 80 tools at once, the model does not get smarter. It gets noisier. Token bills climb, tool choice drifts, and a simple “check order status” prompt suddenly carries half of your company’s OpenAPI surface. Solon AI (v4.0.3) answers that with the Gateway Talent trio in solon-ai-talent-gateway: Talent Source of tools Unit of management OpenApiGatewayTalent OpenAPI / Swagger docs one API source ToolGatewayTalent local / MCP FunctionTools one tool, runtime add/remove
What this is Torinoa Tools is a side project I've been building solo: 152 developer utilities — Base64 conversion, JSON formatting, a regex tester, subnet calculators, AES encrypt/decrypt, and more — all in one site, all running entirely client-side. No server processing — input never leaves the browser Bilingual (Japanese/English) via Astro Content Collections Static site built with Astro + Vue 3 + TypeScript, also distributed as a Docker image Instead of a feature tour, this post is about a
Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40% How we moved from "semantic search + hope" to a measured, tunable retrieval pipeline with 95% recall@10 Everyone ships RAG the same way: chunk by 512 tokens, embed with text-embedding-3-small, top-k=5, stuff into context. It works for demos. Then you hit production: Legal contracts: 512 tokens splits clauses mid-sentence API docs: 1000-token chunks drown signal in noise Customer tickets: Conversational c
Building Production-Grade LLM Evaluation Pipelines: From Vibes to Metrics How we replaced "looks good to me" with automated evaluation catching 92% of hallucinations before deployment Three months ago, our team shipped a RAG-based customer support assistant. It worked great in testing — we'd ask it questions, read the answers, and say "yeah, that looks right." Then it hit production. A customer asked about their billing cycle. The assistant confidently cited a policy that didn't exist. Another
Let’s start with a conversation
An idea, a challenge, or a system that needs to work better. We’ll help you understand the next step.
Prefer email? [email protected]
