Engineering Manager / Technical Lead
Archive
Older writing on AI applications, software engineering, and developer tools.
AI agents feel like they can touch every system. The practical answer is not more trust in the model, but database roles, row-level policies, semantic layers, tool scopes, approval gates, and audit trails.
The current evidence does not support trusting model size alone for secure code generation. Secure agentic coding needs threat modeling, constrained tools, scanners, evals, and human approval gates.
A practical workflow for engineers who want to digest long, technical articles without drowning in detail. Start with quick-view prompts, then move into grounded notes, multi-pass summaries, and long-context research workflows.
From context and hallucinations to hardening and vibe coding, AI didn't invent all these words, but it definitely gave them a promotion.
There is no truly bulletproof system prompt. But there is a practical engineering standard for making prompts far more robust across Sonnet, Haiku, GPT, and reasoning-style models.
AI makes first-draft code cheaper, but it does not erase ambiguity, integration, verification, coordination, or production risk. That means engineering complexity has to be discussed differently, especially in Scrum planning.
AI agents are the new crawlers. Learn how to signal discoverability, serve machine-readable content, control bot access, and expose capabilities through MCP — with practical code examples.
A simple, source-backed guide for engineers and PMs to start with GitHub Spec Kit, understand the main commands, and use the workflow cleanly in Cursor or Claude Code.
Quick find
Search by topic, title, framework, or pattern.