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.
Your retrieval-augmented generation (RAG) pipeline works well on simple questions. You embedded your documents, built a vector index, and retrieval does its job. Then someone asks something that requires distributed facts, and the whole thing falls ap...
One of the things I keep thinking about with AI-assisted development is that the conversation around AI coding is often backwards. A lot of people talk about AI as if the goal is to hand it a vision and let it materialize the finished thing. Describe the app, describe the feature, describe the experience, and then let the agent build it. But I don’t think that is what most serious builders actually want. If you are designing software, you are not just asking for “an app.” You are deciding how a
*This is a submission for the [Hermes Agent Challenge] When I first heard about agentic AI systems, I imagined something much more capable than a traditional chatbot. A chatbot answers questions. An AI agent plans, reasons, uses tools, and works toward a goal. That idea led me to explore Hermes Agent and build my first autonomous AI project: Hermes Commander. As someone interested in AI, prompt engineering, and autonomous systems, I wanted to understand how modern AI agents actually work. Most t
Most Flutter tutorials show you how to build a todo app. This is not that. Flutter (Dart) — cross-platform mobile Why MercadoPago and not Stripe? Flutter devs building for the Latin American market Get it [email protected]
*This is a submission for the [Hermes Agent Challenge] Hermes Commander is my first AI agent project built using Hermes Agent. The goal of this project was to explore how an AI agent can go beyond simple question-answering and perform structured tasks using tools. Hermes Commander acts as an autonomous research assistant that can understand requests, create research plans, access available tools, and organize workflows. As someone interested in AI, prompt engineering, and research, I wanted to b
I built a self-improving and healing workflow for Antigravity 2.0 where your AI review prompts update themselves based on your actual codebase. No more stale checklists that still reference packages you removed months ago. The core idea: meta-prompts — instructions that tell the AI to scan your package.json, GEMINI.md, skills, and MCP config, then generate hyper-specific review prompts from scratch. Every time. What's in the repo: 🧠 Self-optimizing prompts for code review, spring cleaning, and
How I built a real-time serverless security detection pipeline on AWS using CloudTrail, EventBridge, Lambda, DynamoDB, and SNS — and what broke along the way. All source code for this project is on GitHub: aws-siem-detection-pipeline Most cloud security tutorials show you how to turn on GuardDuty and call it a day. I wanted to better understand what actually happens under the hood. Things like how a detection pipeline routes an event, evaluates it, and fires an alert in real time? So I built one
Most developers using AI coding tools hit the same ceiling eventually. The agent writes code, you accept or reject it, and next time it starts from scratch again. There's no memory of what worked, no accumulated judgment about your codebase, no improvement from one session to the next. You're getting faster, but the tool isn't getting better at helping you specifically. Compound Engineering is a plugin that tries to fix that. Built by Every.to and available for Claude Code, Cursor, Codex, GitHub
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]
