Insights
Practical writing on software architecture, SaaS products, AI automation, legacy modernisation, and the business of building reliable systems.
Curated links from external sources — not 360Softy original articles.
Prisma Compute launched with custom domain support. Here's how we made the setup one DNS record while handling TLS certificate provisioning, storage, and routing behind the scenes.
A common objection to agent memory is that you don't need it: context windows are huge now, so just put the whole history in the prompt. We wanted a real answer, not a vibe, so we ran two public long-term-memory benchmarks against a full-context baseline. Here's what we found — including the case where the baseline wins. We compared two configurations on the same questions. The full-context baseline stuffs the entire conversation history into the prompt. Eidentic memory ingests the history into
Today we're releasing Eidentic, an open-source TypeScript SDK for building AI agents with self-improving memory and the production fundamentals built in — not bolted on. It's Apache-2.0, with no enterprise tier, and it runs on Node, Bun, Deno, and the edge. Every serious agent eventually needs the same two things, and most stacks make you assemble both yourself. The first is memory that actually improves. Not a vector store you query and paste into a prompt, but something that remembers across s
Introdução Tipos são uma forma de definir a “forma” ou o contrato dos dados que estamos usando no código. Pensando em Javascript puro, ele é dinâmico: você pode criar uma variável com um número e logo depois colocar um texto nela. O Typescript entra pra colocar ordem na casa. Os tipos dizem ao compilador o que cada variável, função ou objeto pode receber e fazer. Se você tentar fazer algo que quebre essa regra, o TypeScript te avisa antes do código rodar (em tempo de compilação), evitando aque
AgentForge is a control system for AI coding agents. Instead of hoping your agent "writes good code," you give it structured engineering workflows — the same ones senior engineers actually follow. What it is: 28 skills covering the full lifecycle: define, plan, build, verify, review, ship What's different: Anti-rationalization tables: Every skill lists the excuses engineers use to skip best practices ("CI is too slow" → "Optimize the pipeline, don't skip it") Repo: [https://github.com/borhen68/S
Today on Uncanny Valley, we take an early look at the SpaceX IPO and why you might find yourself among the investors without even realizing it.
Comments
A few months ago I built a way to search documents by meaning while keeping the embeddings hidden — even from the server doing the search. I called it ZATRON. The obvious question everyone (including me) kept asking was: does it actually hide anything, or does it just look scrambled? Scrambled-looking isn't the same as secure. So instead of trusting a correlation number, I did the thing that actually scares me: I trained a neural network to break it. This post is the honest write-up — including
Work with 360Softy
Book a free consultation and we will tell you honestly whether we can help.
