Blog Archive
Page 1 of 3
Your AI Agent Passed Review. It Still Wasn't Ready.
A practical scorecard for AI agent readiness that combines code review quality, ROI signals, governance controls, and production operating metrics.
AI Code Review with Agents: Faster Reviews Without Lowering Standards
How to run AI code review with agents in real engineering teams: review scopes, scoring thresholds, guardrails, and handoff patterns that improve quality.
I Reviewed 1,000 Lines of AI-Generated Code. Here's What I Found.
A systematic audit of what LLM-generated code actually looks like in a production codebase — the patterns, the failure modes, and the one thing that surprised me.
Jira to PR Automation: How AI Agents Ship Faster Without Chaos
A clear Jira-to-PR automation guide using AI agents: ticket intake, branch strategy, code generation, tests, pull requests, and safe human review.
Measuring AI Agent ROI: Metrics That Actually Matter for Engineering
Learn how to measure AI agent ROI with engineering metrics that matter: lead time, review quality, rework rate, and delivery reliability.
The Model Was Confident. The Model Was Wrong. The Model Apologised Beautifully.
On the peculiar problem of AI systems that fail with perfect grammar, excellent formatting, and zero shame.
Your AI Agent Isn't Stupid — You Just Built It Wrong.
The uncomfortable gap between AI demos and production reality, and what to actually do about it.
AI Agent Guardrails and Governance: The Operating Rules That Prevent Incidents
A practical AI agent governance guide covering guardrails, allowlists, risk tiers, kill switches, and audit trails for production engineering systems.
AI is Coming for Your Job — And I Helped Build It.
A completely unbiased reflection from a man who has spent 12 years making machines smarter than people.
Human-in-the-Loop AI Coding: Where Automation Should Stop
Human-in-the-loop AI coding guide for engineering leaders: what to automate, where human checkpoints belong, and how to reduce risk in agentic workflows.