Journal
How to run a consulting practice with AI in it, without the hype or the benchmark recaps.
New here? Start with these
-
The three categories of consulting work — and which ones AI should never touch
Where the line sits between work AI should touch and work it shouldn't.
-
Stop prompting, start briefing: delegating whole deliverables to Claude
The habit change that fixes most bad AI output: brief it, don't prompt it.
-
Stop pasting into chat. Point Claude at a folder.
The setup post — where your files live and how Claude gets to them.
The scope-creep conversation: four scripts for the conversations you've been avoiding
The four scope-creep patterns that come up most, with the response language for each, and how to say it without sounding defensive or apologetic.
How to keep a client's context across Claude sessions (without re-pasting)
The folder structure, the per-engagement Project setup, and the three context files that make Claude operate like it actually remembers your client.
Don't build your practice on one AI model
Your top AI model can change terms, change plans, or leave your picker overnight. Build the consulting practice that barely has to look up.
The case-study harvest: one wrap, three marketing pieces, thirty minutes
A 30-minute procedure that turns a wrapped engagement into one case study and three social posts — before the texture decays. Run it within two weeks.
The context-window mistake most consultants make with Claude
Why your Claude conversations get worse over time, the three failure modes, and the discipline that keeps long consulting workflows sharp through the end.
Stop prompting, start briefing: delegating whole deliverables to Claude
How to hand Claude a whole deliverable: the five-part brief, a worked example, when to steer instead, and the review pass that keeps it client-grade.
The three-touch nudge: late-payment recovery without burning the relationship
A three-touch cadence for recovering late invoices (day 1, day 7, day 14) without the apologetic emails that sour the next engagement.
Claude Projects vs. skills vs. raw prompts — when to use which
The three Claude surfaces solo consultants confuse, and the workflow-by-workflow rule for picking between them. Plus the one combination most people miss.
Fable 5, Opus, or Sonnet: which Claude for client work
A working rule for picking between Fable 5.1, Opus 5.5 and Sonnet on client work, task by task, and what your plan decides for you.
Claude Fable 5 for solo consultants: what actually changes
What Claude Fable 5 changes for solo consultants — longer autonomous runs, briefing instead of prompting, and why setup pays more than it used to.
The five-section Friday update that keeps clients quiet
The weekly update that takes 12 minutes, heads off anxious client check-ins, and reads as confidence instead of a defensive wall of text.
Claude skills for solo consultants: what they are, and the first three to build
What a Claude skill is, why it beats a saved prompt, and the three to build first if you run discovery calls, debrief meetings, or send weekly updates.
Every article, by topic
The complete Journal index. Bookmark this page — new pieces land here on publish.
Setting Up Claude
- Stop pasting into chat. Point Claude at a folder.
- How to keep a client's context across Claude sessions (without re-pasting)
- Claude Projects vs. skills vs. raw prompts — when to use which
- Claude skills for solo consultants: what they are, and the first three to build
- The Claude workflows worth keeping in a solo consulting practice
Working With AI
- When Claude's Second Draft Isn't as Good as the First
- What's left to review when the AI checks its own work
- The effort dial: how much thinking does a task deserve?
- From transcript to deliverable: the AI-assisted research-report workflow
- The one-pager you should write before every AI-assisted task
- The context-window mistake most consultants make with Claude
- Stop prompting, start briefing: delegating whole deliverables to Claude
- Why your AI prompts feel generic — and how solo consultants fix it
Winning Work
- The case-study harvest: one wrap, three marketing pieces, thirty minutes
- An 8-step proposal walkthrough on a real (fake) engagement
- The non-numeric outcome — what stops case studies from reading like marketing fiction
- Why most consulting proposals lose — and the one shape that closes
- The 90-second discovery dossier (when you don't have an SDR)
Running Client Work
- The client update email template (steal this one)
- The scope-creep conversation: four scripts for the conversations you've been avoiding
- The five-section Friday update that keeps clients quiet
- The first hour after a deal closes: what to ship a new client
- The client-meeting workflow that turns transcripts into next actions
Practice Systems
Model Watch
- Which Claude model you actually get now depends on your plan
- Claude Cowork left the desktop. Here's what that buys a consultant.
- Don't build your practice on one AI model
- Fable 5, Opus, or Sonnet: which Claude for client work
- Claude Fable 5 for solo consultants: what actually changes
- Claude vs. ChatGPT for consulting work: why we default to Claude
AI Strategy
- Consultant OS vs. a folder Claude actually works in
- What a paid template kit has to beat
- What "AI-native" actually means for a digital product (and why it's not the prompts)
- Why outcome-specific AI products beat 100-prompt megapacks
- The three categories of consulting work — and which ones AI should never touch