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.

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

Tags:

IndustryPart 1AnalyticsAI AgentsOpen SourceSmol Analytics

10 min readAugust 27, 2026

Smol Analytics architecture showing cookieless ingestion and native AI agent integration

The AI-Native Analytics Engine: Introducing Smol Analytics for Modern Businesses

How Smol Analytics replaces legacy tracking bloat and complex database clusters with a single cookieless binary, a universal ingestion API, and 94+ native AI agent tools over MCP.

Read article

Build LogPart 1OpenFusionArchitectureOpen Source

9 min readAugust 25, 2026

Building OpenFusion: How I Built a Local Multi-Model AI Fusion Engine

Why rely on a single AI model when you can synthesize answers across a panel of models? Here is how I built OpenFusion, the architecture behind its two-step judge, and how I solved the MCP client timeout wall.

Read article

IndustryPart 1AI AgentsDeepSeekOpen Source

7 min readAugust 18, 2026

DeepSeek Harness: Why the Future of AI Coding Isn't a Black Box

Most AI coding assistants are closed appliances, with everything hardwired into a single box. DeepSeek Harness treats every capability as an interchangeable plugin on a shared baseplate. Here's why modular architecture matters for growing teams.

Read article

IndustryAI MusicOpen Source

7 min readAugust 16, 2026

Flat vector illustration of a dark chip on a cream background sending circuit traces into a blue audio waveform, with a vinyl record and musical note above.

How I Generate AI Music for Free, Unlimited, on My Own Hardware

Full songs with vocals, for zero dollars and no account. The open music stack (MiniMax Music 3, ACE-Step 1.5, Foundation-1, MuScriptor) now runs on a consumer GPU. Here's the setup, the catches, and when it beats paying for Suno.

Read article

Build LogAnalyticsAI AgentsNext.jsSelf-HostingOpen Source

7 min readAugust 14, 2026

The AI-Native Analytics Stack with Smol Analytics and MCP integration

The AI-Native Analytics Stack: Why We Switched to Smol Analytics (and How to Set It Up)

Why we moved away from bloated analytics trackers to a self-hosted, cookieless single binary that interfaces directly with AI coding assistants over MCP, along with the complete step-by-step setup guide.

Read article