Insights
Field notes from production
If it's here, it's because I used it, tested it, or watched it fail and wanted to write down why.
VideoWatch the video5 min watchThe Engineering Headcount Math Just Broke
AI coding agents broke the old headcount-equals-output math. Small senior teams now outship larger orgs, and verification is the new bottleneck.
production-aiai-agentsteam-structure
ArticleRead more9 min readWhat a Fractional CTO Costs in 2026 When Agents Make Senior Judgment Go Further
Fractional CTO pricing in 2026 ranges from about $3K per month at the low end to $15K+ per month for ongoing architecture review, delivery guidance, and production judgment. The important change is that a senior human can use agents to turn decisions into reviewed implementation faster without handing judgment to the model.
fractional-ctoai-agentsai-engineering
VideoWatch the video13 min watchI Added ACP to My Mastra Agent So It Can Work in Repos
ACP is the layer that lets my Mastra agent hand real repo work to Claude Code instead of stopping at advice.
agent-architecturemastraclaude-code
ArticleRead more11 min readAgent Loops vs. Workflows: The Boundary That Makes AI Reliable
Most AI demos hand one agent the whole job. When the output touches reputation, money, or outbound email, use a workflow instead of an agent loop. Here's where the boundary goes, built with Mastra.
ai-agentsagent-architecturemastra
VideoWatch the video17 min watch5 Engineering Loops I'd Actually Run with Codex
Engineering loops are where Codex stops being a scheduler and starts acting like an operational teammate.
codexautomationagent-loops
VideoWatch the video9 min watchStop Giving Your Agent Every Tool
Large tool catalogs break agent context. Tool search fixes that by letting agents discover and load only what they need.
tool-searchtool-usemastra
VideoWatch the video20 min watchTreat Your AI Agent Like a New Engineer
Most AI coding agent failures are not prompt problems. They are onboarding problems.
codebase-readinessagents-mdcodex
ArticleRead more10 min readHarness Engineering: The 4 Levers Behind Almost Every Agent Failure
When an agent fails, harness engineering gives you four levers (Context, Tools, Loop, Governance) to find which one broke in under a minute.
ai-agentsagent-architectureharness-engineering
ArticleRead more10 min readHuman-in-the-Loop Agent Approvals: A Mastra Pattern
Prompt-based approval gates fail because the model decides whether to ask. Mastra's requireApproval primitive removes that decision entirely. Here's how to implement it.
ai-agentsagent-architecturemastra
Nothing matches those filters.