360SOFTY

Insights

Engineering Insights

Practical writing on software architecture, SaaS products, AI automation, legacy modernisation, and the business of building reliable systems.

RSS

Curated links from external sources — not 360Softy original articles.

ExternalSoftware Engineering
DEV Community

Building Production-Grade LLM Evaluation Pipelines: From Vibes to Metrics

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

llmaievaluation
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Gateway Talents in Solon AI: OpenAPI, Tool, and MCP Surfaces That Scale Without Context Blow-Up

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

agentsaiarchitecture
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

I built a site with 150+ browser-only dev tools (Astro + Vue 3 + TypeScript) — here's how it's put together

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

astrovuetypescript
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Optimizing RAG at Scale: Chunking, Retrieval, and the Bayesian Search That Cut Latency 40%

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

llmaievaluation
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Building Production-Grade LLM Evaluation Pipelines: From Vibes to Metrics

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

llmaievaluation
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

Your First Oracle Autonomous Database on OCI Always Free

The single best way to keep your Oracle skills sharp without a license, a server, or a finance OCI Always Free. It gives you a real, fully managed Oracle database — Autonomous 23ai release — that stays free indefinitely. It's the ideal sandbox: a Here's how to stand one up in a few minutes, what's genuinely worth doing with it, and the one catch that personal OCI accoun, never an employer's tenancy. The short version. Sign up at oracle.com/cloud/free, create an Autonomous Database with the Alway

oracledatabasecloud
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

A Stop Hook Is an Event, Not a Dashboard

Claude Code hooks and persistent session monitoring are often compared as if they were two implementations of the same feature. They are not. A hook answers: “Which lifecycle event just happened, and what should run because of it?” A monitor answers: “Across the sessions that exist now, which one is running, waiting, blocked, completed, stalled, or inactive?” The difference becomes obvious after a restart, a missed event, or a second simultaneous session. Claude Code documents session-level, tur

aiclaudeproductivity
DEV CommunityRead original
ExternalSoftware Engineering
DEV Community

The Content Pipeline Nobody Talks About: What Happens After AI Generates the Draft

A lot of AI-content discourse stops at "generate the text." That's actually the easy part now. The interesting engineering problem is everything after it. The gap most teams miss: generation is a solved problem. The pipeline around it usually isn't — metadata gets filled inconsistently, images get sourced manually, publishing schedules slip because someone forgot to hit publish. Where the real time savings live: not in the writing itself, but in closing the loop between draft and published, revi

aiwebdevwordpress
DEV CommunityRead original

Work with 360Softy

Building a SaaS product, AI system, or business platform?

Book a free consultation and we will tell you honestly whether we can help.

Book a consultationView our services →