Practical writing on enterprise AI, execution, and commercial outcomes — from builders shipping with agents to career notes from the field.
AI & Building
Shipping with agents: memory systems, dev tooling, site builds, and quality gates.
Career
Roles, teams, and lessons from leading programs — including when agents are in the toolchain.
Commerce & Marketing
Ecommerce, CX, agencies, and growth systems — commercial outcomes in practice.
Anthropic's Fable 5 leads CursorBench 3.1 at 72.9%, but at $18 per task and 76 steps. I read the table for score per dollar, tokens, and steps, and where open models land.
Continue reading →
Copilot had the same footer spec but dropped it on long chats. Cursor keeps it with alwaysApply rules, optional hooks, and a v3.1 mode-based Response Footer Contract.
Continue reading →
Most enterprise AI programs struggle before the model fails. Data, governance owners, and change runway get compressed. A pre-flight diagnostic before the next funding gate.
Continue reading →
Five management habits that transfer directly to directing AI agents: show examples, write context down, guide in steps, define outcomes, and close the loop with review.
Continue reading →
A thousand-line profile block in one extension fights merchant menu IA. Split full-page extensions by job and align with how customers navigate account tasks.
Continue reading →
Design capture CLIs that dump outerHTML into SKILL.md files can smuggle instructions. Sanitize at the trust boundary before agents read the DOM.
Continue reading →
I run Cursor on Composer 2.5 only—not to save money alone, but to get predictable rule compliance. A tighter session bootstrap beat chasing frontier models for my workflow.
Continue reading →
Chat is not memory. This series explains a file-based external brain for builders and leaders—four layers, hooks, and why it beats hoping the model remembers.
Continue reading →
The same three-layer memory stack used for shipping code works for strategic work, client engagements, and cross-tool AI—short chat, operational handoffs, evergreen notes, and explicit feedback.
Continue reading →
Chat context is not memory. A three-layer file system—session, operational, evergreen—plus hooks and git automation is how I keep production codebases coherent across hundreds of agent sessions.
Continue reading →
Chat memory is opaque and ephemeral. Deliberate files give audit trails, solo-shipping continuity, team handoffs, and survival when models or tools change.
Continue reading →
The popular STM / LTM / feedback diagram optimizes in-model memory. A file-based external brain optimizes audit, handoff, and tool churn. Here is when each design wins—and why I chose files.
Continue reading →
A complete walkthrough of every Lighthouse bottleneck on a Next.js 16 Vercel site — TBT from 3,020ms to 20ms, LCP from 3.0s to 1.7s — including the config options that don't exist in Next.js 16 and will silently break your build.
Continue reading →
GitHub Copilot's new token-based pricing changes everything. Here's what it actually costs compared to OpenRouter and third-party relays when you code extensively.
Continue reading →
I wanted a clean weekly digest for petralian.com without paying for RSS automations. This is the exact architecture we implemented, the issues we hit, and the code patterns that made it reliable.
Continue reading →
A practical way to move from writing in Obsidian to publishing on a live site without copy-paste, manual uploads, or brittle one-off scripts.
Continue reading →
The why was clean. The how had corners. A ground-level account of building petralian.com — the masonry layout that fought back, a 404 page with a working Asteroids game, the TinaCMS newline problem nobody warns you about, and how AI wrote most of it.
Continue reading →
CSS column-count creates a masonry layout in one line. It also silently breaks left-to-right reading order. Here is what is actually happening in the DOM, and a reliable fix that holds up under variable card heights.
Continue reading →
WordPress was slowing down the actual writing. Here's why I rebuilt petralian.com on Next.js, how Obsidian now sits at the center of my publishing workflow, and why I decided to open source the whole thing.
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) I had a moment…
Continue reading →
Every AI session starts from scratch. Four tools are racing to solve the AI memory problem - OpenClaw, Hermes, Karpathy's LLM wiki, and a plain Obsidian vault. Here's how they differ and which approach actually survives tool churn.
Continue reading →
A practical breakdown of how Gravio turns repository signals into six-dimension scores, hard quality gates, and actionable remediation plans.
Continue reading →
Unit tests catch code failures. They do not always catch AI quality regressions. Here is how to add quality thresholds as a first-class release gate.
Continue reading →
A practical rollout framework for introducing Gravio across many repos without creating process fatigue, policy confusion, or noisy quality signals.
Continue reading →
Your AI outputs can look great this month and degrade next month without obvious failures. Here is why drift happens and how to detect it before it reaches production.
Continue reading →
A practical, no-fluff walkthrough for getting Gravio running from a clean folder to your first quality score, including the exact command flow and common mistakes.
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) I came across…
Continue reading →
Most AI quality platforms ask you to trust them with your source code. Gravio takes a different path: encrypted scoring designed to keep plaintext out of the server path.
Continue reading →
The Publicis and The Trade Desk dispute has been framed as a transparency scandal, but I think it is more interesting than that. What this dispute actually…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) Having spent…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) The rise of…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) As artificial…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) In almost…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) I recently had…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) Media agencies…
Continue reading →
The recent news that the 133 cardinals have not yet elected a new Pope reminds us that transformative decisions require broad support. In the Vatican’s…
Continue reading →External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) The reported…
Continue reading →
Having led digital transformation initiatives across Asia Pacific for global brands ranging from luxury retail to financial services, I've experienced the…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) In the midst…
Continue reading →
As a digital transformation strategist who has worked with global brands across multiple sectors, I've consistently observed that strong marketing fundamentals…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) AI is…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) The idea that…
Continue reading →
Unlock the potential of AI and SEO integration to elevate your digital campaigns. Discover how combining these innovative strategies can enhance search engine rankings, personalize content, and automate tasks, driving substantial growth for your business.
Continue reading →
Leadership is more than just a title or position-it’s the driving force behind how organizations operate, innovate, and communicate. In the world of marketing…
Continue reading →
The marketing world has recently embraced the infinity loop as an evolution of the marketing funnel, and a revolutionary way to understand and engage with…
Continue reading →
E-commerce has become a cornerstone of global retail, and as we move into 2025, its growth shows no signs of slowing. The ongoing digitalization of modern…
Continue reading →
Having spent over 15 years helping businesses across industries like retail, finance, and e-commerce scale their operations, I’ve seen how access to the right…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) AI and human…
Continue reading →
As someone who has championed digital transformation projects across retail and finance sectors, I’ve had the privilege of seeing firsthand how these…
Continue reading →
The financial industry in the Asia-Pacific (APAC) region faces unique challenges as it seeks to modernize its marketing strategies and better serve a diverse…
Continue reading →
In today’s digital-first world, a strong online presence is the cornerstone of any startup’s success. Your brand is more than just a logo or a tagline. It’s…
Continue reading →
When building a platform designed to empower brands, one of the most important questions we kept coming back to was this: How do we help brands not just…
Continue reading →
As someone who has spent years working at the intersection of eCommerce, digital strategy, customer experience, and analytics, I’ve seen how the dynamics…
Continue reading →
Over the past five months, I had the privilege of working with Silk Commerce as their Vice President of International Markets, focusing on expanding the…
Continue reading →
External Memory Series — File-based memory for AI-assisted work (overview · 1 Implementation · 2 Productivity · 3 vs the diagram · 4 Governance) Recently, I…
Continue reading →
After nearly six incredible years with Merkle Hong Kong, I’ve officially transitioned from my role as Managing Director to explore new opportunities that align…
Continue reading →
Customer experience management (CXM) has emerged as a top priority for companies in today’s digital landscape. It refers to the strategic practice of…
Continue reading →
In an exciting development for Dentsu International Hong Kong, Nathan Petralia has been promoted to managing director of Merkle, the agency's newly launched…
Continue reading →
(Cover photo of this article is copyright WARC, source: https://www.warc.com/reports) I had the opportunity to write an article for WARC. This WARC exclusive…
Continue reading →