How I Run Over 20 AI Agents Locally and Deploy One to Production at a TimeThis article was originally published on tebogosacloud.blog. I have over 20 AI agents. Only one is in production. That is not a constraint. It is a strategy. A system with one excellent production ag10 min read·tebza.hashnode.devApr 13
The Missing Test Suite: Why AI Projects Fail Before ProductionMost AI projects never reach production. The missing piece is prompt testing with the same rigour as TDD.18 min read·tebza.hashnode.devApr 2
Building an LLM Judge That Doesn't Lie to YouStructural guardrails, multimodal inputs, and a fixed-weight violation catalogue for trustworthy AI evaluation9 min read·tebza.hashnode.devMar 31
5 Models, 467 Actions, 1 Winner — What We Learned Comparing LLMs on Real Code GenerationTesting Claude, Kimi, DeepSeek on 467 real code generation tasks. The results changed how we think about model selection.10 min read·tebza.hashnode.dev2AAMar 30
Beyond Text: How We Built an Evaluation Framework for Multi-File AI OutputsA 4-layer evaluation framework for scoring AI-generated multi-file artifacts using a violation-deduction model9 min read·tebza.hashnode.devMar 30
