Two South African AI-built apps exposed data in six days. Why a login screen is not authentication, and the boring checklist that separates a demo from a product.
Category: AI & Automation
Ollama vs llama.cpp vs vLLM vs SGLang: Choosing the Right LLM Inference Engine in 2026
Ollama, llama.cpp, vLLM, and SGLang compared — real benchmarks, quantization deep dive, GPU cloud pricing in Rand, migration paths, and a decision framework for production.
Running Local LLMs: A Practical Guide for Production
You can run production-quality large language models on your own hardware. No API keys. No rate limits. No data leaving your network. The cost? A one-time GPU investment that pays for itself in 3-6 months compared to cloud API bills. TL;DR Production-quality LLMs run on your own hardware — no API keys, no rate limits, […]
CodeCritical Beta Release — Know If Your Code Is Ready to Ship
CodeCritical is an AI-powered security analysis platform. Upload your code, get a Nemesis Score, a verdict, and a full report with exactly what to fix, in what order, and how hard it’ll be.
Agent Harness Explained: The Runtime That Makes AI Agents Actually Work
Every agent architecture article talks about LLMs, tools, and skills. Nobody talks about the thing that actually makes them work: the harness. It’s the runtime that takes your prompt, decides what tools to call, manages context, handles errors, and returns a result. Without it, you have components. With it, you have an agent. This is […]
Agent Skills Explained: How AI Agents Learn to Do Real Work
Most AI agents today are still just chatbots with a tool call bolted on. They can chat, but they can’t reliably do specialised work. The ones that ship real value — document editing, brand compliance, data analysis, deployment — have something the others don’t: Skills. Agent Skills are an open standard from Anthropic for packaging […]
MCP Explained: The Open Standard That Makes AI Agents Actually Useful
AI models are powerful, but they’re stuck in a box. They can reason about text, generate code, analyse data — but they can’t click buttons, query databases, or publish content without help. Every team solving this problem was building the same integration over and over: custom glue code, per-model adapters, brittle workflows. Model Context Protocol […]
Bring WordPress Into Your Agent Workflows with the WordPress MCP Server
The WordPress MCP Server lets any MCP-capable assistant draft, publish, and organize WordPress content locally, with an anonymized VS Code profile and direct GitHub link for quick setup.