GitHub Spec Kit: How to Get Started with Cursor or Claude Code
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.
20 min read
Archive
Articles, page 12
Older writing on AI applications, software engineering, and developer tools.
How to Build a Good Agentic Code Reviewer
Most AI code review bots fail for a simple reason: they optimize for visible comments instead of reviewer trust. This guide pulls together current benchmarks, practitioner reports, product limitations, and design patterns for building a code review agent that is fast, quieter, less biased, and less hallucination-prone.
23 min read
AI Work Paradoxes: Why Faster Tools Are Making Professional Life Feel Heavier
The emerging AI-era problem is not just automation or job loss. It is possibility overload, expectation creep, verification fatigue, boundary collapse, and work that expands faster than human attention.
12 min read
Spec Kit Legacy Modernization Spec-Driven Development Brownfield Software Architecture Migration Strategy
Before You Copy Legacy Code: A Spec-to-Spec Migration Workflow for Modernizing One Feature
An exploratory, source-backed article on reverse-engineering one feature into current-state specs in the old repo, then using those artifacts to drive a safer implementation in a new repo and a new stack.
18 min read
A Phase-by-Phase Model Strategy for GitHub Spec Kit in 2026
A source-backed follow-up on routing GitHub Spec Kit phases across fast drafting models, deeper planning models, and stronger implementation models without treating all steps as the same kind of work.
19 min read
How to Reverse-Engineer an Existing Feature into GitHub Spec Kit Artifacts
A practical brownfield workflow for reconstructing one existing feature into spec.md, plan.md, tasks.md, and supporting Spec Kit artifacts without pretending you are starting from scratch.
16 min read
Why Concise AI Responses Work Better: Evidence, Biases, and a Better Default for Engineers and PMs
The strongest evidence does not say 'always write less.' It says humans do better with lower cognitive load, clearer cues, and progressive disclosure. Here's how that changes how we should generate AI responses and reports.
11 min read
What `ghcr.io` Is, and How to Use It with Helm and Argo CD for a FastAPI App
A practical, source-backed guide to GitHub Container Registry, OCI Helm charts, Argo CD, and a clean local/dev/prod flow for a simple FastAPI service.
27 min read