Field notes
Blog
Local SEO, Google reviews, websites, and marketing for trade shops. Written by people who work with those businesses.
Field notes
Blog
Local SEO, Google reviews, websites, and marketing for trade shops.
Custom Build vs No-Code for a Client Site: How to Decide
A four-input decision framework (traffic, integrations, budget, timeline) for choosing between a custom build and a no-code tool, with real cost numbers.
Jordan Ellis·July 7, 2026·8 min read
What a Web Agency Actually Delivers vs What You Expect
The website is about 30% of a web development engagement. Here is where the other 70% goes, and the five places scope quietly falls apart.
Jordan Ellis·July 2, 2026·7 min read
Why Pylonworks Builds on Next.js for Nearly Every Client Project
Why Pylonworks defaults to Next.js: ISR, edge routing, the Vercel deploy story, TypeScript fit, and the one project type where it is the wrong call.
Jordan Ellis·June 30, 2026·7 min read
The Onboarding Process That Halves Revision Rounds
How a two-page brief, one design checkpoint before any code ships, and a signed spec cut my average revision rounds from 3 to 1.4 per project.
Jordan Ellis·June 25, 2026·7 min read
How I Validate a Web Project Idea Before Writing Code
The waitlist-and-landing-page method I use to test demand for about $60 before committing three months to a build, plus which signals matter and which lie.
Jordan Ellis·June 23, 2026·6 min read
The AI Agent Infrastructure Stack I Run 24/7
The four-piece stack I use to keep Claude agents running around the clock: systemd timers, the Agent SDK, Postgres for state, and OAuth rotation. Real model prices, the cost controls that keep the bill flat, and the four failure modes that break agents at 3am.
Jordan Ellis·June 15, 2026·6 min read
What Autonomous AI Agents Can Actually Do in Production
I break down which autonomous agent tasks hold up in production and which still need a human gate, with current 2026 token costs, rate-limit numbers, and a retry pattern that survives 429s and 529s. The dividing line is whether a test catches the mistake first.
Jordan Ellis·June 11, 2026·6 min read
How I Automated Client Outreach Without Sending One Cold Email
The pipeline that drafts and queues about 20 personalized outreach touches a day for roughly $0.40 in Claude inference, why I never let the model press send, the Haiku scoring pass that cut drafting cost 60%, and the send limits that keep you out of spam.
Jordan Ellis·June 7, 2026·6 min read
How I Decide Whether to Automate a Task With AI
The AI task automation decision comes down to one equation most people skip. I break down the real per-run token cost, the verification trap that kills ROI, and a five-factor rubric for choosing what to automate first.
Jordan Ellis·June 5, 2026·6 min read