Essays on AI, agentic systems, enterprise transformation and systems thinking.https://henzard.co.za/https://henzard.co.za/writing/ai-thought-partner/https://henzard.co.za/writing/ai-thought-partner/Geoff Woods' CRIT framework asks the AI to interview you before it does anything. Most people skip that step, and the reason they skip it is exactly why it matters.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/design-taste/https://henzard.co.za/writing/design-taste/Why 'make it look good' fails as an instruction to an AI coding agent, how TasteSkill turns design judgement into explicit constraints, and where rules stop and taste begins.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/esp32/https://henzard.co.za/writing/esp32/What AI development honestly looks like near an ESP32: what fits in 520 KB of RAM, what belongs on a server, and the latency and power trade-offs that decide the split.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/graph-engineering/https://henzard.co.za/writing/graph-engineering/How to tell when nodes and edges are the honest shape of a problem, what traversal really costs, and where graph systems start to break as they grow.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/juniors-and-the-harness/https://henzard.co.za/writing/juniors-and-the-harness/The consensus says AI belongs with the senior engineers who can catch its mistakes. I think juniors gain the most from it, provided someone builds the harness that makes a wrong answer safe.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/mentoring/https://henzard.co.za/writing/mentoring/How to develop a junior engineer's judgement: asking before telling, productive struggle, feedback that lands, and what changes now that plausible answers are instant.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/personal-assistant/https://henzard.co.za/writing/personal-assistant/An AI personal assistant is only as safe as its worst possible action. On capability boundaries, read-only defaults, prompt injection and what should always stay human.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/programmer-ai-world/https://henzard.co.za/writing/programmer-ai-world/An honest accounting of what AI changes about programming and what it does not: where the work moves, where judgment still lives, and what is worth practising now.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/prompting/https://henzard.co.za/writing/prompting/Why prompt tricks age badly, what actually generalises across models, and how specificity, context, constraint and evaluation turn prompting into engineering.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/railway-mcp/https://henzard.co.za/writing/railway-mcp/What changes when you move a Model Context Protocol server from a local stdio process to a hosted service on Railway, and why secrets and blast radius are the real work.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/vibe-coders/https://henzard.co.za/writing/vibe-coders/People without engineering backgrounds are building real software with AI. What they get right, where the danger actually sits, and how engineers can be useful to them.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/voice-ai/https://henzard.co.za/writing/voice-ai/Speech interfaces live or die on latency, turn-taking and honesty about what the system is. On the engineering behind giving an AI a voice with OpenAI and ElevenLabs.Thu, 27 Aug 2026 00:00:00 GMThttps://henzard.co.za/writing/hello-world/https://henzard.co.za/writing/hello-world/A first post, existing so the publishing pipeline has something real to carry end to end.Wed, 26 Aug 2026 00:00:00 GMT