Field journal
Blog archive
Every published note, with the newest work first. Use the topic links to stay inside one search intent.
JustPaid ran 7 AI agents 24/7 with OpenClaw, shipped 10 features in a month for $4K/week. Here is the real cost breakdown and what it means for you.
Anthropic accidentally leaked Claude Code's source. I read through it. Here are 6 architecture patterns that are changing how I build agents for clients.
AI agents can be hijacked through the content they read. Here is what prompt injection looks like in production, why your existing security stack will not catch it, and what to build instead.
Model Context Protocol (MCP) is the open standard that lets AI agents talk to your real tools, databases, APIs, files, without custom glue code. Here's what it is, how it works, and whether you actually need it.
88% of AI agent pilots never ship to production. We analyzed why, and built a 5-step playbook used by the 12% of teams that actually make it.
Can a consumer GPU serve an LLM in production? One RTX 5070 Ti runs Llama 3.1 8B Q4_K_M via llama.cpp as a live public endpoint. The stack, what broke, when local pays off, and when it doesn't.
Off-the-shelf AI agents fail when your workflow is the edge. Here's when custom development actually pays off for small business.
One bad loop and an AI agent burned $200 in minutes. AgentGuard is a Python SDK that enforces hard cost limits at runtime, here is how to ship it.
250K GitHub stars doesn't mean OpenClaw fits your business. We ran the same agent on OpenClaw and a custom build: 3x faster to ship, 2x the monthly bill. Verdict + when to switch. (2026)
Gartner saw a 1,445% surge in multi-agent inquiries, yet most businesses don't need one yet. When a single agent hits its ceiling, the 4-step path to 2–3 agents, and why it runs $50–200/mo, not $50K.
A token price alone won't tell you what an AI agent costs. Split one-time build work from recurring run cost (model calls, hosting, review), then the worked math: $0.03/run, $90/mo at 100 runs/day.
Tested all three across 20+ real automations. n8n wins for speed, Make for non-coders, custom scripts when it gets complex. Side-by-side pricing, limits, and the exact use case each one owns.
My framework for identifying, scoping, and building automations without a single meeting. Used on every client engagement.
I let an autonomous agent run 100 ML experiments while I slept. 7 succeeded. Net result: 25% model improvement. Here's the setup.
How AI agents are changing the way we build with Next.js, from agentic development to shipping 10x faster as a solo engineer.