Ai

Context: This is the real project plan for dnd-multi, a full-stack AI Dungeon Master platform. It was generated by Claude Opus 4.6 during Phase 0 of the LLM GitHub PR workflow — synthesizing gap analysis from four different models into a structured execution document. Claude Sonnet 4.6 then used this plan overnight to open 24 PRs and ship all seven phases. Personal identifiers have been removed. Technical content is verbatim. Milestone Timeline Milestone Target Date Deliverable M0 — Platform Stable 2026-03-13 All broken deps fixed, migrations applied, Tier 2 lore generating, smoke tests passing M1 — First Playable Session 2026-04-03 Turn structure live, player identity in DM prompt, hot phrase + /dm command working M2 — Full Action Flow 2026-04-24 Action confirmation, non-active player queue, player votes operational M3 — IC/OOC + Personality 2026-05-08 Meta-mode detection, in-character assumption, DM personality tuning deployed M4 — Content & Reporting 2026-05-22 Book/media content generation live, /report + /flag system in admin dashboard M5 — Combat Tracker 2026-06-12 Live HP tracker UI, [COMBAT:] directives wired to death protection M6 — Feature Complete v1.0 2026-06-19 Spell reference Discord command, shareable campaign invitation links Current State Summary The platform has a solid full-stack foundation with all core systems implemented and deployed to the home k3s cluster. The gap is game experience polish — the AI DM has no awareness of whose turn it is, doesn’t distinguish in-character from out-of-character speech, lacks an action confirmation flow, and has no mechanism for players to report misbehavior. These are the features that make the difference between a tech demo and a playable game. ...

Context: This is the live docs/ai-lessons.md from the home k3s cluster repository, referenced extensively across posts on this blog — starting with AI Memory System and GitHub Copilot Setup Guide. Every entry exists because its absence caused a production incident. Personal identifiers and internal domains have been replaced with generic placeholders. Updated: 2026-03-03 Rules discovered through production breakage. Each entry prevents recurrence of a specific failure. Update this file whenever a new non-obvious failure pattern is discovered. ...

TL;DR I added a standardized environment.instructions.md file to every repository in my workspace. It’s a simple Markdown table of tool versions plus a few workflow snippets. AI assistants pick it up automatically, and they’ve stopped suggesting commands for tools or versions I don’t have. The whole thing took less than an hour to write out and propagate. The problem I run GitHub Copilot heavily across several projects — homelab infrastructure, a blog, a few Python services, and some supporting tooling. The AI context setup (those copilot-instructions.md files I wrote about here) covers what each project does and what its conventions are. What it doesn’t cover is what I’m actually running when I type commands in a terminal. ...

TL;DR A $20/month GitHub Copilot subscription gives you Claude Sonnet 4.6, GPT-4o, and Gemini inside VS Code. Out of the box it’s useful. With a proper instruction setup — a copilot-instructions.md file, path-scoped rules, and skill documents — it becomes something you actually rely on. Most of the posts on this blog were built with this toolchain, mostly in the context of my k3s cluster, but the patterns apply anywhere. This is how I have it set up. ...

TL;DR The .github/copilot-instructions.md file started as 10 lines of project description and grew into a 99-line “operating system” for AI assistants. Then it split: failure patterns moved into docs/ai-lessons.md (now 482 lines across 20+ categories), and file-type-specific rules moved into .github/instructions/ with applyTo glob patterns. The same template structure was standardized across 5 repositories. This post traces the three generations of AI instruction architecture and shows how every production incident permanently improves AI reliability. ...

TL;DR I run Wiki.js on k3s as the cluster’s internal knowledge base. It is not a place I write documentation — it is a place the AI writes documentation after completing work. When Claude finishes deploying a service, debugging an incident, or refactoring infrastructure, it commits the results to the wiki with architecture diagrams, decision rationale, and operational notes. I am the primary reader. When I want to understand how something works, or why a specific decision was made three weeks ago, I go to the wiki instead of digging through git history or re-reading code. ...

TL;DR The AI memory system I built three weeks ago started causing the problem it was designed to solve: context window exhaustion. Five generic Claude skills — duplicated identically across all 5 repositories in my workspace — consumed 401KB (~100K tokens) of potential context. The gh-cli skill alone was 40KB per copy, accounting for 42% of all skill content. I ran a full audit, deleted 25 duplicate files, and documented the anti-pattern to prevent recurrence. ...

TL;DR Two weeks of building a production Kubernetes cluster with AI pair programming. Claude Opus 4.6 handles complex multi-step infrastructure work via the CLI. GitHub Copilot provides inline code completion in VS Code. AWS Bedrock (Nova Micro, Claude Sonnet 4.5) powers runtime AI services inside the cluster. The key discovery: AI tools without persistent memory are dangerous. Every session starts from zero. The same bugs get recreated, the same anti-patterns get suggested, the same cluster-specific constraints get forgotten. The solution is the “Memory Protocol” – a set of documentation files the AI reads before every session and updates after every discovery. ...

TL;DR Jellyseerr already knows what I have. Radarr and Sonarr already know how to find things. The missing piece was a front door that understood intent instead of requiring me to search for specific titles. I wired Jellyseerr’s REST API to Claude and gave it a system prompt that knows my taste profile. Now I can say “download 100GB of family-friendly anime I might like” and get a queue of requests back. A Kubernetes CronJob runs the same prompt on a schedule so the library grows without me thinking about it. ...

TL;DR Today I deployed two significant additions to the cluster: an AI-powered Alert Responder that uses AWS Bedrock (Amazon Nova Micro) to analyze Prometheus alerts and post remediation suggestions to Slack, and a multi-user dev workspace with per-user environments. I also hardened the cluster by constraining all workloads to the correct architecture nodes and fixing arm64 scheduling issues. The Alert Responder Running 13+ applications on a homelab cluster means alerts fire regularly. Most are straightforward — high memory, restart loops, certificate expiry warnings — but analyzing each one, determining root cause, and knowing the right remediation command gets tedious, especially at 2 AM. ...