Developer's Blog

Real experiences from the intersection of software engineering and AI

Sharing lessons learned, practical insights, and honest reflections from building AI-enhanced development tools. No hype, just what works (and what doesn't).

The launch reel’s opening frame: “Ben” in extruded block lettering beside “Live” in mint neon script.

2026-10-14•21 min read

Designing past the AI template, prompt by prompt

How I directed Claude and Codex through benlive.tv’s October upgrade: neon lettering, particle swarms, a code-rendered launch reel and reusable, recast prompts.

The refreshed portfolio gallery, with illuminated lettering, framed photographs, and a timber ceiling.

2026-09-26•18 min read

Rebuilding my WebXR portfolio, one headset test at a time

Bringing my old portfolio gallery up to date with Three.js, readable lighting, natural hand interaction, and an AR view you can hold in your hands.

The blog index, one of the surfaces the site's regression suite covers.

2026-08-28•5 min read

From QA Automation to AI Quality Architecture

A decade of breaking software built the exact instincts AI-assisted development needs. Where the tester's mindset shows up in how I build now, and the false-green runner that proved it.

Problem Solver, where every generation step waits for the person to ask for it.

2026-08-25•4 min read

Human in the Loop: Designing AI Products People Trust

Explicit inference, approval checkpoints, honest model labels, and consent that's real. The design choices behind the AI Lab that make it slower to use and much easier to trust.

Context First, a presentation built around the idea that context beats control.

2026-08-23•4 min read

Context Engineering: The Skill That Makes AI Assistants Useful

The model isn't the problem. What it knows before it starts is. Repo-level rule files, skills, server-side prompt keys, and a memory directory, and how each of them evolves with the codebase.

A working PostHog analytics deck, kept as an ongoing case study after the job it was built for didn't come through.

2026-08-20•6 min read

What a PostHog Application Taught Me

I applied for PostHog's Context Engineer role, didn't get it, and kept the working analytics implementation and the values lesson anyway.

Local Crew operator dashboard showing resources, queue state, and cluster capacity across multiple inference devices.

2026-07-13•7 min read

Building Local Crew: A Local-First Inference Orchestration Framework

How I built a local-first orchestration framework that turns spare computers, desktops, and laptops into one coordinated AI system, with Port as the optional remote companion layer.

The Hire Me page, where the migration work is described.

2026-06-29•5 min read

Cross-Driver Test Architecture: Migrating Enterprise QA with AI Assistance

I'm leading a migration from a VB.NET Selenium test codebase to C# on an adapter that runs Selenium and Playwright under the same test logic. Why the adapter is the whole strategy, and where assistants help without making the decisions.

The AI Lab hub showing the apps covered in this article.

2026-06-15•5 min read

Shipping AI Features End to End as a Solo Engineer

Four AI Lab apps, a serverless backend with model routing and rate limiting, a three-browser Playwright suite, a media pipeline, and a deploy path. What owning the whole delivery surface actually involves, and where assistants change the math.

The chat's tier selector, the only part of the resilience system a visitor sees.

2026-06-01•4 min read

Production Resilience Patterns for AI-Powered Features

The chat on this site looks like three buttons. Behind them is a model chain, a circuit breaker, two different retry policies, a shared rate limiter, and a cost allowlist, each of which exists because something failed.

Agent Agenda, an editor for the personas, rules, skills, and tools that governance documents are made of.

2026-05-18•4 min read

Version-Controlled AI Governance for Engineering Teams

Every team using AI assistants has governance. The question is whether it's a reviewed file in the repo or a habit in someone's head. How I've done it at work and on my own projects, and what it changed.

The About page, where the onboarding and documentation work is listed.

2026-05-04•4 min read

Onboarding Legacy Codebases for People and AI Assistants

The documentation app I built at work to shorten onboarding, and the discovery that the same tool made AI assistants productive on the codebase. The overlap between a good onboarding path and good context is nearly total.

Agent Agenda, an editor for the kind of role and rule documents this article is about.

2026-04-21•5 min read

Meta Programming the Workflow: Context and Agent Orchestration

I spend as much time programming the process that produces software as I do programming the software. Roles for each assistant, context as a finite resource, gates with pass and fail written down, and the tools I built to run it.

The AI Lab hub with all four apps live.

2026-04-09•5 min read

AI Lab Project Building Part 5: Iterative Engineering with AI Assistants

By the time four AI Lab apps were live, the real deliverable was the loop that built them. What the iteration pattern looked like, where it broke, and what the retrospective taught me about docs, tests, and gradient creep.

Agent Agenda's category tabs, domains, and linked components.

2026-03-30•3 min read

AI Lab Project Building Part 4: Agent Agenda

Agent Agenda is a composable editor for agent configuration documents, personas, skills, rules, and tools, with AI assistance only where it removes blank-page friction and never where it removes your decisions.

Problem Solver's step-by-step workbench with scenario, candidates, analysis, solutions, and plan.

2026-03-19•3 min read

AI Lab Project Building Part 3: Problem Solver

Problem Solver was built around one constraint, never spend an inference the user didn't ask for. Four prompt contracts, two sliders that default to one, and a step sequence you can inspect and rewind.

Promptpad's editor with a revision history and enhancement controls.

2026-03-11•4 min read

AI Lab Project Building Part 2: Promptpad

Promptpad started as a standalone Next.js app running against Ollama and became an AI Lab workbench with revisions, diffs, and a model selector that had to match the chat's contract exactly.

Chat About Ben, the AI Lab chat interface with its tier selector and status badge.

2026-03-02•4 min read

AI Lab Project Building Part 1: AI Chat

The chat on this site was the first AI Lab app and it set the rules for everything after it. Server-side prompts, a three-tier model selector with local parity, a fallback chain, and a test suite that grew from real bugs.

Isometric illustration of an automated QA pipeline, with canary tests, batched runners, and AI agents collaborating through a verification workflow.

2026-02-23•14 min read

Automating Quality Assurance for AI-Powered Development

How I use project configuration, plan-then-implement workflows, Claude Code skills, and automated test infrastructure to keep AI-assisted development honest and shippable.

Architectural diagram of a dual-source blog engine processing Markdown and HTML content through a unified pipeline with responsive image optimization.

2026-02-23•9 min read

Building a Dual-Source Blog Engine with Responsive Media

How this blog serves articles from both Markdown and HTML sources through a unified content pipeline, with artist-generated illustrations processed into pixel-perfect responsive variants.

The Hire Me page, where the day-job side of this workflow is described.

2026-02-14•4 min read

Agentic IDE Workflows for Enterprise Teams

How I run AI-assisted work in Visual Studio and VS Code on a team codebase, with Amazon Q Developer's ask and agent modes, version-controlled context packs, and quality gates that apply to every contributor.

The AI Lab hub, built almost entirely through the terminal loop this article describes.

2026-02-03•5 min read

A CLI Agent Harness Playbook

The terminal loop I hold Claude Code and Codex to, the skills that encode it, the repo files that keep two assistants reading one source of truth, and the failure patterns that shaped all of it.

The AI Lab hub, where the model tiers and the harnesses that drive them get exercised.

2026-01-24•5 min read

Models and Harnesses

Why I pick the harness before the model, how I split work between Claude Code, Codex, Copilot, and Amazon Q, and where local models earn a place in the loop.

Isometric workspace with glowing code editor, AI neural pathways, and engineering tools converging into a unified development environment.

2026-01-15•2 min read

Welcome to the Developer's Blog

Notes from the intersection of reliable software engineering and AI-enhanced development.