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.
If you found this useful, follow me for more practical insights on AI-assisted development and the agent economy. I publish 2-3 times per week. Tags: AI, Programming, Productivity, Open Source, Automation
This is a submission for the Hermes Agent Challenge: Write About Hermes Agent Most tutorials start with a clean Linux machine, a working API key, and someone who already knows what they're doing. This is not that tutorial. This is the story of building a real project with Hermes Agent starting from a Windows PC with virtualisation disabled in the BIOS, zero Linux environment, and a deadline three days away. I built repo-audit-agent — a tool that uses Hermes Agent to perform first-pass technical
Comments
Modern LLM serving is hard to tune because each deployment is a stack of interacting choices: model backend, tensor-parallel shape, prefill/decode split, worker... Modern LLM serving is hard to tune because each deployment is a stack of interacting choices: model backend, tensor-parallel shape, prefill/decode split, worker counts, scheduler settings, routing policy, KV cache behavior, autoscaling thresholds, and topology. Those choices interact across layers, and a local improvement can shift th
Comments
The Pentagon awarded SpaceX a $4.16 billion contract to build missile-tracking satellites linked with President Donald Trump's planned "Golden Dome" defense system, as reported earlier by Bloomberg. In an announcement on Friday, the US Space Force says the sensor-equipped satellites will allow it to detect and track targets from space. The Elon Musk-owned SpaceX - which recently filed for what could be the biggest initial public offering ever - already has contracts with the Space Force to devel
Getting your hands on a capable AI model is the easy part now. Every team can reach the same frontier models through an API, so a strong model is not what sets a product apart. What separates a working product from a demo is everything around the model. You have to measure whether the agent is actually doing its job, then keep grinding on reliability until it stops making expensive mistakes in front of real users. I moderated a panel on exactly that moderated a panel on exactly that at DigitalOc
The US has previously built specialized facilities just for this purpose.
Work with 360Softy
Book a free consultation and we will tell you honestly whether we can help.
