Blog Field notes from the studio · 8 articles · Updated May 2026

Notes from inside a working studio.

Long-form essays, opinionated playbooks and field notes from the team shipping production AI in 30 days. No theory. Written by the same people you'd talk to on a call.

May 2026 · Economics · 12 min read

How much does an AI agent cost in 2026?

A real cost breakdown of building and running an AI agent — by type (chatbot, workflow, autonomous), with per-month token costs, infrastructure, observability, and ROI math from production builds.

Read article May 2026 · Strategy · 10 min read

Build vs buy AI: a 2026 decision framework

When to build your own AI vs use ChatGPT or Claude. The five questions to answer, where each path wins, and the underrated hybrid that beats both for most companies.

Read article May 2026 · Automation · 14 min read

9 AI workflows every small business should automate

From inbox triage to auto-quoting to customer support — the nine workflows that pay back fastest, with tooling, build time and the first step for each.

Read article May 2026 · Explainer · 9 min read

What is RAG? A plain-English guide (2026)

Retrieval-Augmented Generation explained without jargon. Why models hallucinate, when to use RAG vs fine-tuning, common pitfalls, and the production stack we use today.

Read article May 2026 · Lessons · 8 min read

Great AI demo, no traction

Why your AI prototype never shipped. The 5 root causes we see most, and a framework to make sure your next demo actually becomes a production system.

Read article May 2026 · Automation · 8 min read

The 30-day AI implementation playbook

The exact sprint structure we use with every client — day-by-day, week-by-week — written so any in-house team can copy it. No theory. Just the moves that ship.

Read article Apr 2026 · Strategy · 6 min read

Why most AI projects die in PowerPoint

The five reasons enterprise AI never ships — committee phases, vendor grand prix, platform traps — and the studio model that fixes them.

Read article Mar 2026 · Build · 10 min read

Our default 2026 AI stack

The exact tools, models and infrastructure we reach for on day one of every project. Opinionated, with trade-offs. Updated as the landscape moves.

Read article

Eight essays live; more coming. Q3 will cover production eval design, the economics of agent failure modes, and what we'd build differently across our last 10 client engagements. If there's something specific you'd like us to write about, drop us a line.

(End)

Want this in your inbox?

One essay every few weeks. Same voice. No newsletter pop-ups.

Book a strategy call