Living in Color August · 03
Living in Color W33: What Is a Harness?
August beginner deep dive: what a coding harness is, why the Bingo Board grades them, and how to pick one without drowning in brand names.
Section
Essays and deep dives, mostly on security, voice and agentic AI engineering, and what it actually looks like to move from twelve years in security operations into building real products. No thought leadership, no hype. Just what I've learned and what I'm still figuring out.
Living in Color August · 03
August beginner deep dive: what a coding harness is, why the Bingo Board grades them, and how to pick one without drowning in brand names.
August Bingo Board · 01
Mid-August Board pulse: Qwen3.8-Max, Muse Spark 1.2 / Muse Code, Grok 4.6, and Gemini 3.7 Flash are on the watchlist ungraded. Routing table did not flip.
Living in Color August · 02
Week of Aug 10: Muse Code as the new harness, SWE-Bench ProMax as the unsaturated refactor yardstick, and Qwen3.8-Max as open-weight Max-class pressure.
Living in Color August · 01
August kickoff for AI in Living Color: Opus still daily, Sol as coding ceiling, Gemini Flash tiers eating computer-use, open-weight pressure rising, and why harness controls matter more than the logo on the model.
GPT-5.6 Sol takes the independent SWE-bench Verified lead. Gemini 3.6 Flash jumps computer-use as a cheap Flash tier. Flash-Lite becomes the latency knife. Here is how the Bingo Board moved in July, and what I am actually running.
The Principal Engineer's Agentic Coding Bible · 06
The closing part of the series. Vibe coding failure case studies with the receipts. Compliance and governance baseline. The Notion workspace template. Feature spec template and launch checklists. The daily, weekly, and monthly loops that turn agentic engineering from a hobby into a discipline you can sustain.
The Principal Engineer's Agentic Coding Bible · 05
A six-part guide for the IT/Cyber/Cloud generalist now orchestrating AI agents. Part 5 is the production architecture playbook. The Vercel + GCP split, Expo + React Native for mobile, Supabase + Postgres + Row-Level Security as the non-negotiable, and the five-stage SDLC runbook from ideation to V1 hardening.
The Principal Engineer's Agentic Coding Bible · 04
A six-part guide for the IT/Cyber/Cloud generalist now orchestrating AI agents. Part 4 is operationalizing the army: six core agent personas, model routing by phase, orchestration framework picks, default tool allowlists, UI standardization rules, and repository + CI/CD discipline.
The Principal Engineer's Agentic Coding Bible · 03
A six-part guide for the IT/Cyber/Cloud generalist now orchestrating AI agents. Part 3 is the security spine. We never fixed SSDLC. Now AI-DLC is showing up alongside it. The puzzle pieces are solved, they're just scattered. A mandate is coming. Supply chain, MCP attack surface, secrets in the agentic era, and the anti-hallucination contract.
The Principal Engineer's Agentic Coding Bible · 02
A six-part guide for the IT/Cyber/Cloud generalist now orchestrating AI agents. Part 2: my actual May 2026 stack, the minimum-viable stack if you're starting fresh, and the tools I downgraded or cut. Plus the platform rules and the promotion ladder from Lovable/Replit to Vercel to GCP.
Everyone says Google lost I/O 2026. They're wrong. While the AI Twitter discourse fixated on per-axis benchmark losses, Google quietly consolidated its disparate AI tooling into a single agentic stack, and shipped the receipts.
The Principal Engineer's Agentic Coding Bible · 01
A six-part guide for the IT/Cyber/Cloud generalist now orchestrating AI agents instead of writing code. Part 1: the moment the mental model broke, why the tool stopped being an IDE, and the discipline that survives. Spec-Driven, Context, and Harness engineering across the new Agentic Development Life Cycle.
A former security operations engineer maps how SOC instincts (threat modeling, least privilege, supply chain paranoia) translate directly into the governance skills that agentic AI development demands.