grill-me for AI agent teams: using it as a delegation gate in 2026
grill-me was designed as rubber ducking for solo devs. I use it as a gate that blocks briefs from reaching downstream agents until the vague parts are gone.
Deep Dives
Full technical analysis when the topic earns it. Tested against real hardware, with versions named.
AI SEO Audit Tools: Reliable for Pass/Fail, Not for Counting
We ran Cogny against our site. It said 44 out of 100. We fixed what it flagged. We ran it again. It said 85. Then we ran Lighthouse and SEOptimer in the same 30-minute window. Here is what each tool got right, what it still gets wrong, and what changed.
Local AI in 2026: what's on the box, and why I built it
Local AI on a single RTX 3060: Ollama, SillyTavern, and Stable Diffusion WebUI Forge. What's on the box, why those choices, and what changed in 2026.
We built a telemetry stack to measure our AI agents, then used it to cut prompt costs
A Python parser, Prometheus, and Grafana running locally gives per-agent cache hit rates and cost-per-session data. Here is what we did with it.
@holmdigital/engine: WCAG failures mapped to national law
Axe tells you which WCAG criterion you failed. @holmdigital/engine tells you which law you broke and which authority can fine you.
Stop Calling It an AI Assistant. Build a Team.
Single-agent prompts collapse under their own weight. How to design Claude Code agent teams that hold up: org chart first, profiles second, budget last.
K3s on Proxmox: what actually breaks in production
Running K3s inside Proxmox VMs with real workloads exposed problems that the quick-start guides don't mention. Here's what I found.