·8 min·build-log
The Architecture Review I'd Give Your Multi-Agent System
Six mistakes every team makes building agent systems, and the architectural patterns that fix them.
Blog
Engineering patterns, build logs, and field notes from the Grid.
Featured
·8 min·build-log
I Mass-Deleted Four Docker Containers, a GPU Instance, and Three AI Services. My Pipeline Got Better.
Vertex AI Pipelines, custom BART models on GPU, three separate AI services per review. I ripped it all out. One Gemini Flash call, Cloud Workflows, and Dataform replaced everything at 98% less cost.
·5 min·get-rezzed
The Only Part of My AI Stack That Needed Coffee Was Also the Bottleneck
The smartest tools in my stack were bottlenecked by the only component that needed coffee and sleep. So I built CacheBash, an open-source MCP server with 34 tools that lets your AI sessions coordinate without you in the middle.
·6 min·build-log
Multi-Agent Orchestration: What We Learned Running 9 AI Programs in Parallel
Five AI agents running in parallel. One git checkout and the whole thing collapses. Real lessons about isolation, session death, and fleet management from running multi-agent AI in production.
·7 min·build-log
What Running an Autonomous AI Fleet Actually Taught Me About Orchestration
Design patterns for bounded, vendor-neutral multi-agent systems in production. Most teams think orchestration equals prompt chaining. That's plumbing. The hard problems are identity, mortality, trust, and economics.
·7 min·get-rezzed
I Built 6 Open-Source Tools for Claude Code. Then I Connected Them.
Each tool is useful. The Heartbeat saves me from checking tmux. The Task Queue saves me from copy-paste handoffs. But when you connect all six, something different happens.
All Posts
·8 min read·build-log
I Mass-Deleted Four Docker Containers, a GPU Instance, and Three AI Services. My Pipeline Got Better.
Vertex AI Pipelines, custom BART models on GPU, three separate AI services per review. I ripped it all out. One Gemini Flash call, Cloud Workflows, and Dataform replaced everything at 98% less cost.
gcpdata-pipelinesgeminidataformterraformbigquery
·7 min read·build-log
What Agents Learn When You Let Them Remember
·8 min read·build-log
The Architecture Review I'd Give Your Multi-Agent System
Six mistakes every team makes building agent systems, and the architectural patterns that fix them.
architecture-reviewsolutions-architectureconsultingdistributed-systems
·8 min read·build-log
I Built an MCP Server. Here's What the Docs Don't Tell You.
The MCP documentation shows you how to build a toy server. Running one in production means solving transport reliability, tool schema design, auth patterns, and failure modes that no tutorial covers.
mcparchitectureproductiondistributed-systems
·10 min read·get-rezzed
Nobody Warned Me About This Place
Seven months deep in Claude's ecosystem. Desktop, CLI, mobile, Projects, MCP servers, multi-agent fleets. What works, what burned me, and why I can't stop ordering.
claude-aiclaude-codemcpmulti-agentbuild-log
·8 min read·build-log
Notes from the Grid: The Telemetry Nobody's Building for Multi-Agent AI
·5 min read·get-rezzed
The Only Part of My AI Stack That Needed Coffee Was Also the Bottleneck
The smartest tools in my stack were bottlenecked by the only component that needed coffee and sleep. So I built CacheBash, an open-source MCP server with 34 tools that lets your AI sessions coordinate without you in the middle.
mcpcachebashmulti-agentopen-sourcedeveloper-tools
·7 min read·get-rezzed
I Built 6 Open-Source Tools for Claude Code. Then I Connected Them.
Each tool is useful. The Heartbeat saves me from checking tmux. The Task Queue saves me from copy-paste handoffs. But when you connect all six, something different happens.
claude-codemcpopen-sourceai-toolscachebash
·6 min read·build-log
Multi-Agent Orchestration: What We Learned Running 9 AI Programs in Parallel
Five AI agents running in parallel. One git checkout and the whole thing collapses. Real lessons about isolation, session death, and fleet management from running multi-agent AI in production.
multi-agentorchestrationclaude-codelessons
·7 min read·build-log
What Running an Autonomous AI Fleet Actually Taught Me About Orchestration
Design patterns for bounded, vendor-neutral multi-agent systems in production. Most teams think orchestration equals prompt chaining. That's plumbing. The hard problems are identity, mortality, trust, and economics.
orchestrationmulti-agentdistributed-systemsarchitectureai-fleet
·6 min read·get-rezzed
From Side Project to SaaS: Shipping CacheBash as a Product
CacheBash started as an internal tool for coordinating AI sessions. Three months later, it's an open-source MCP server with 34 tools, a mobile app, and a roadmap toward commercial infrastructure.
saasopen-sourceproductcachebash
·5 min read·build-log
Building a Fail-Open Compliance Layer for AI Agent Systems
Your AI agent has shell access and API keys. A fail-closed compliance layer stops every ambiguous action. A fail-open one logs everything and lets the work continue. We chose fail-open.
compliancearchitecturemcpagent-patterns
·5 min read·build-log
CacheBash: An MCP Server That Lets Your AI Sessions Talk to Each Other
You open three terminal tabs. Claude Code in one, Cursor in another, a third deploying to staging. None of them know the other two exist. I built CacheBash to fix that.
mcpmulti-agentclaude-codeopen-source
·4 min read·get-rezzed
Your AI Agent's Plan Looks Great. It's Lying to You.
Most planning tools treat specs as a gate — pass/fail. But a 10-step plan where step 7 is 'figure out the database schema' isn't much better than no plan at all. specfirst adds a gradient.
specfirstclaude-codeagent-patternsopen-source