When AI Agents Dream: Memory Consolidation for the Obsidian Vault
Teaching AI agents to review their own session transcripts, catch lost decisions, and consolidate memory overnight. Part 3 of the AI memory series.
Thoughts on cloud engineering, architecture decisions, and lessons learned the hard way.
Teaching AI agents to review their own session transcripts, catch lost decisions, and consolidate memory overnight. Part 3 of the AI memory series.
CLAUDE.md instructions are advisory. Hooks are contractual. How I made AI agent memory actually work by adding deterministic enforcement to an Obsidian vault.
Why I'm using plain markdown files for AI agent memory instead of vector databases and semantic search. Sometimes the boring solution is the right one.
How a 500-line bash script evolved into an automated WAF assessment engine - and why deterministic tooling beats giving AI the wheel.
How skills transform AI assistants from context-amnesiacs into genuinely useful collaborators - and why the token savings matter more than you'd think.
How a well-intentioned reseller programme accidentally became the best argument for creative cloud architecture.
Why I started a blog in 2026, how AI is actually helping me write it, and a promise to share the unfiltered versions.
Why most disaster recovery plans are untested fantasies, and how to build resilience that actually works when everything goes wrong.
Why most organisations are flying blind on cloud spend, and how FinOps turns 'bill shock' into strategic investment.
A disclaimer, a warning, and a gentle reminder that you're here entirely at your own risk.