Engineering Manager / Technical Lead
Archive
Older writing on AI applications, software engineering, and developer tools.
LLM-as-a-judge can be one of the most useful patterns in agent evaluation, but only if you understand where it breaks: order bias, self-preference, verbosity bias, weak judges, and evidence-free scoring. This guide explains the pattern, the common traps, and the fixes that make it practical.
Why production agent evaluation is moving beyond output-only checks, how trace-aware grading complements scenario testing, and how LangWatch, LangSmith, and Langfuse compare.
How AI-assisted engineering workflows mature from a simple system prompt into skills, MCP tools, and full plugins — with real engineering examples at every stage.
A source-audited guide to where computer-use agents are already practical, where they still break, and how to deploy them safely for QA, legacy enterprise workflows, and browser automation.
A grounded look at how Cursor's subagents and skills fit with Claude Code's subagents, worktrees, and the new /simplify command for research, implementation, and cleanup.
A practical service-level deployment guide for AI SaaS teams: Docker image design, GitHub Actions builds, Helm packaging, ArgoCD handoff, External Secrets, IRSA, and release hardening.
A source-audited, architecture-first guide to deciding where agent state should live in production, with code examples in Vercel AI SDK, LangChain, and Agno/AgentOS.
A deep dive into why Astro is the best framework for fast, content-rich sites and why Agno is the simplest path to production-grade AI agents — from a Hello World agent to a full multi-agent workflow dashboard.
Quick find
Search by topic, title, framework, or pattern.