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.

Why work with an independent AI automation consultant over an agency?

With an agency, you pitch a senior partner and get handed off to junior contractors learning on your dime. With me, the person who scopes the architecture is the person who writes the code and puts it into production. You get faster turnaround, no communication telephone games, and direct accountability.

What tools and platforms do you use for workflow automation?

I build with Asana for workspace architecture and task rules, Zapier for cross-tool integrations, and custom TypeScript services or LLM frameworks when reasoning is needed. I focus on reliable tools your team already uses, building fail-safes so automations don't break silently when field names or API quotas change.

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 Asana for project tracking, Zapier for workflow automation, direct 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.

Build logs, strategy, and industry breakdowns. Specific over conceptual — written to be useful, not to fill a calendar.

Tags:

StrategyAI AgentsQualityWorkflow

17 min readOctober 4, 2026

A simplified flow of the AI agent workflow in flat vector style: problem, think, brief, build, check, gate, ship, all resting on a bar labeled the library

My complete AI agent workflow, from problem to shipped software

The full workflow I run to ship software with AI agents: think first, build against a frozen copy, let four checkers and a deterministic gate judge the result, then ship with a receipt. Walked through end to end, grounded in a real failure from my Seepient project, and the working summary of my book The One-Person Engineering Team.

Read article