Model Watch

I picked Claude — here's the one task ChatGPT actually wins

An opinionated take on Claude vs. ChatGPT for consulting work — what Claude does better, the one task that goes the other way, and how to pick.

Winning Work

Why most consulting proposals lose — and the one shape that closes

The structural reason most consulting proposals fail — and the eight-section shape that converts. Specific examples, no template SEO.

Setting Up Claude

The actual Claude workflows of a solo consultant, six months in

Six months in, here are the workflows that compound — and the ones I tried and dropped — for a one-person consulting practice.

Running Client Work

The client-meeting workflow that turns transcripts into next actions

Pre-brief, debrief, follow-up email — the three artifacts to produce around every meaningful client meeting, in 12 minutes total.

Practice Systems

The quarterly retrospective for solo consultants — a 90-minute exercise that compounds

A 90-minute end-of-quarter exercise that tunes your ICP, your pricing, and your pipeline — without team-retro overhead.

Winning Work

The 90-second discovery dossier (when you don't have an SDR)

Three artifacts to produce before any consulting discovery call — company brief, decision-maker brief, fit flag — in three minutes total.

Working With AI

Why your AI prompts feel generic — and how solo consultants fix it

The four reasons Claude and ChatGPT keep producing forgettable output — and the prompt structure that fixes all four for consultants.

AI Strategy

The three categories of consulting work — and which ones AI should never touch

The rule for deciding which consulting tasks to give AI — and which to keep yourself. Specific examples across the three categories.