Who do you work with as an AI automation consultant?

Operations-heavy teams of roughly 10–50 people — agencies, professional services firms, and growing startups. The common thread is a team losing real hours every week to repetitive work that a system could handle.

How long does an automation project take?

A single automation is usually one to two weeks. A connected system across a few tools is more like three to four. Scope is agreed before any work starts.

Do you work hourly or fixed price?

Fixed-scope, fixed-price only. No hourly billing. We agree what's being built and what it costs, then I build it.

What tools do you use to build automations?

Usually n8n for workflow automation, APIs for system integration, and LLM-powered agents (often with RAG) where reasoning is needed. No custom software is built unless off-the-shelf tools can't do the job.

Do we own the automation you build?

Yes. When it's done, it's yours — running in your tools, on your accounts, with documentation so you or another developer can maintain it without me.

Field Notes

Writing on AI, automation, and shipping real things.

When to automate, when not to, and how to think about it.

Tags:

StrategyModel SelectionAI Strategy

5 min readSeptember 23, 2026

Stop Picking AI Models Like You're Chasing a Trophy

The model with the loudest hype is rarely the right hire for every task in your business. Here is how leadership can actually assess AI models: by reliability at your real work, and by honest cost math that could go either way.

Read article

StrategyPart 3AnalyticsStrategyGA4AI AgentsSmol Analytics

9 min readAugust 29, 2026

Side-by-side comparison diagram of Smol Analytics vs Google Analytics 4 for business leadership

Smol Analytics vs. Google Analytics 4: The Practical Guide for Growing Businesses

A candid comparison between Smol Analytics and Google Analytics 4 on performance, implementation costs, privacy, and how AI agents are rendering legacy dashboards obsolete.

Read article

StrategyPart 2OpenFusionAI ToolsProductivity

7 min readAugust 25, 2026

Clean vector editorial illustration in charcoal and blue showing multiple AI models discussing around a central boardroom table on warm cream background.

Giving Your AI Coding Agent a Council of Models: The OpenFusion Product Guide

How to connect OpenFusion to Claude Code, Cursor, Cline, or Codex to cross-examine difficult code, resolve thorny architectural dilemmas, and eliminate blind spots with a dedicated model council.

Read article

StrategyPart 3OpenFusionAI StrategyBusiness Leadership

7 min readAugust 25, 2026

The Multi-Model Advantage: Why Smart Businesses Stop Betting Everything on a Single AI

OpenRouter proved that fusing a panel of budget models outperforms expensive frontier AI at half the cost. Here is how leadership teams can apply multi-model pipelines to cut operational costs, improve reliability, and build an enduring competitive edge.

Read article

StrategyPart 3AI AgentsDeepSeekProduct DesignUX

7 min readAugust 18, 2026

Flat vector illustration of a modern split-pane AI workspace layout with modular interface panels and dynamic canvases in warm cream, charcoal, and blue.

Designing the UI & UX for a Centralized Business AI Hub

A plain chat box is fine for Q&A, but terrible for real business execution. Here is the product and UX blueprint for a dual-pane AI workspace that turns modular agent workflows into an intuitive daily power tool.

Read article

StrategyPart 2AI AgentsDeepSeekSoftware Architecture

10 min readAugust 18, 2026

Flat vector illustration of a central AI switchboard connecting to diverse business apps and isolated data trays in cream, charcoal, and blue.

How to Build a Centralized AI Hub for Your Business (Without the App Sprawl)

Building separate apps for every AI feature leads to subscription chaos and fragmented data. Here is how the DeepSeek Harness blueprint lets you power your company's entire AI stack from one centralized, adaptable platform.

Read article

StrategyZyntopia

4 min readAugust 14, 2026

A checkpoint gate on an automated production line

Why Your Automation Needs a Human Approval Gate

Full automation ships generic work. Full manual never ships. The approval gate is the middle that works: machine does the plumbing, human keeps the judgment.

Read article

Strategy

4 min readAugust 12, 2026

AI Readiness, five questions to ask before automating anything

AI Readiness: 5 Questions to Ask Before Automating Anything

Most automation projects don't fail at the build. They fail before it starts, because no one checked whether the work underneath was ready to be automated. Five questions I run through with every client.

Read article