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:

Build LogPart 14Seepient

7 min readOctober 1, 2026

Abstract editorial illustration of a small workshop growing into a building with many separate rooms

From Fussy Tool to Client-Ready: What My AI Assistant Can Do Now

Six weeks of releases turned Seepient from a single-owner terminal tool into something a business can host for its clients. Where it stands against the big agent platforms, what open source adds, and what is still missing.

Read article

IndustrySeepientOpenAIGrokAI Agents

9 min readOctober 1, 2026

Cover image for openai dots grok bot vs seepient

OpenAI Dots and Grok Bot Are Here. Seepient Made a Different Bet.

OpenAI just launched Dots and xAI launched Grok Bot, two takes on the always-on AI worker. I built Seepient, and I think they got the ambition right and the relationship wrong. Here's the honest comparison.

Read article

Build LogSeepientAI Agents

5 min readSeptember 29, 2026

A flat vector building with four pillars marked with a lock, cycle arrows, ledger lines and a plug, standing on a dashed replaceable foundation block

AI Agent Architecture: How I Design Agents a Business Can Depend On

Most AI agents work in demos and fall apart under real load. This is the architecture I use: layers, approval gates, fallback chains, and vendor freedom, so an agent survives the days a business actually needs it.

Read article

Build LogPart 11Seepient

14 min readAugust 27, 2026

Abstract editorial illustration of an AI assistant completing a chain of tasks

How I Turned My AI Assistant Into Something That Actually Does the Work

Over six releases my assistant went from a good talker to something that does the work: it refreshes its own model menu, writes checklists with correct numbers, survives a first-run crash, lets you pick how much to trust it, and recovers when a model or a network goes quiet.

Read article

Build LogPart 8Seepient

8 min readAugust 25, 2026

Flat editorial diagram in charcoal and blue on cream: a control room console screen listing model rows with price tags and connected account checkmarks, with four identical doorway icons feeding one shared core.

Every AI Model, One Screen: How I Built Seepient's Control Room

Most AI tools leave you juggling API keys and dashboards while every model behaves differently. I rebuilt Seepient around one control room where every model is visible with its price, sign-in takes seconds, and every doorway behaves the same.

Read article

Build LogPart 7Seepient

9 min readAugust 21, 2026

Flat editorial diagram in charcoal and blue on cream: a workflow line reroutes over a failed provider node marked with a cross, continuing to healthy provider nodes.

How I Built an AI Assistant That Keeps Working When Its Model Provider Fails

My AI assistant used to depend on a single model provider, so every outage stopped my work. I rebuilt it around a multi-provider engine, and now it keeps working no matter which AI company has a bad day.

Read article

Build LogPart 6SeepientAI StrategyBusiness Automation

7 min readAugust 18, 2026

Strategic business architecture showing one unified AI brain powering multiple company touchpoints

Stop Building Five Different Chatbots: How to Build AI That Actually Runs Your Business

Why most business AI projects turn into expensive maintenance headaches, and how a one-brain approach gives you total control, lower costs, and zero vendor lock-in.

Read article

Build LogPart 5Seepient

7 min readAugust 16, 2026

Cover image for seepient v0 4 3 one screen approvals

Seepient v0.4.3: One-Screen AI Approvals That Survive a Crash

How I rebuilt Seepient's permission UX around a single, complete approval screen, and made every granted permission survive a crash, so your AI assistant's work is never silently undone.

Read article

Build LogPart 2Seepient

4 min readAugust 13, 2026

Automated quality gates and architectural guardrails for AI-generated code

Enforcing Architecture in the Age of AI Code: Taming the Slop

AI development tools speed up development, but unguided code generation introduces hidden operational risks. Here's how I enforce strict governance over AI-built code.

Read article

Build LogPart 3Seepient

5 min readAugust 13, 2026

Seepient four-stage governance pipeline: Policy, Approval, Sandbox, Audit

Inside Seepient's Permission System: Policy, Approval, Execution, Audit

Why simple yes/no approval prompts fail when automating business tasks, and how my 4-stage governance pipeline makes autonomous AI execution safe and fully auditable.

Read article

Build LogPart 1Seepient

5 min readAugust 13, 2026

Six-layer modular architecture diagram for Seepient AI engine

Foundational Architecture: Designing for Evolution, Scale, and Zero Redundancy

How a disciplined, six-layer modular architecture protects Seepient from technical debt, isolates system failures, and guarantees zero vendor lock-in.

Read article

Build LogPart 4Seepient

4 min readAugust 13, 2026

Engineering an AI Person: Seepient persistent digital colleague architecture

Seepient: Engineering an AI Person, Not Another Chatbot

Why single-prompt chatbots fail for busy teams, and how Seepient works as a persistent, secure digital colleague across desktop and cloud environments.

Read article