10 prompts that make Fable act like an owner, not an assistant

Fable 5 left the Claude subscription plans on July 7. After that it moved to usage credits: $10 per million input tokens, $50 per million output. Anthropic says it’ll come back to subscriptions when they have capacity.

So everyone’s been asking the same question: what do I point the smart model at while I have it?

Here’s the wrong answer: more autocomplete. If you spend your window using the smartest model ever shipped to write boilerplate a cheaper model writes fine, you’re using a chief of staff to fetch coffee.

Here’s what I’d do instead.

Stop giving it tasks. Give it a stake.

I confess I did this wrong for a while. My prompts were polite little work orders. “Review this code.” “Summarize this doc.” “Check this for bugs.” The output was fine. Fine is the problem. A reviewer with no skin in the game gives you reviewer answers.

Then I started handing the model an identity with something to lose, and the output changed completely.

There’s a technical reason this works on Fable specifically. Anthropic’s own prompting guidance says to give it goals, not checklists. Fable is built to run long, handle ambiguity, and decide what matters on its own. Step-by-step instructions that helped older models actually drag it down. An ownership stance is the purest goal-shaped prompt there is: here’s who you are, here’s what’s at stake, go.

A consultant gets tasks. An owner gets consequences. Prompt for consequences.

Below are the 10 stances I use. Each one pushes the model into a different corner of ownership, so you get variety instead of ten flavors of “looks good to me.”

The 10 prompts

1. The day-one CTO

That last line matters. Fable is good at self-verification when you ask for it. Making it argue against its own bet is the difference between a hot take and a decision you can act on.

2. The activist investor

Ownership with a deadline attached. Two-year money has no patience for a five-year story.

3. The departing cofounder

This one stings. Run it anyway.

4. The due-diligence lead

Note the framing. Business risk, not “find vulnerabilities.” Fable’s safety margins are wider than any prior model, and security-research phrasing is the fastest way to get a refusal. Due diligence framing gets you the same rigor without tripping the wire.

5. The 10x rebuild

6. The support-ticket detective

The trail requirement keeps it honest. If it can’t show the connection, it doesn’t get to claim the connection.

7. The complexity auditor

8. The org-chart x-ray

Your architecture is a fossil record of your org chart. The model reads fossils fine.

9. The solo operator

The 20-hour constraint is doing the work here. Unlimited-time answers are wish lists. Constrained answers are strategy.

10. The interest rate

Not “what’s the mistake” — every audit above already answers that. This one prices the cost of waiting.

Three practical notes before you run these

Set effort to high. Anthropic recommends high as the default and xhigh for the most capability-sensitive work. Audits like these are exactly that work.

Don’t ask it to show its reasoning. A standing “explain your reasoning” line can trigger a refusal, and in some setups Fable silently hands your task to Opus 4.8 and burns your usage doing it. (If that’s been happening to you: Settings, then Capabilities.) Ask for conclusions and evidence, not the inner monologue.

Mind the meter. Stance audits are token-hungry. They read your whole codebase, your tickets, your docs. That’s precisely the kind of job that gets expensive at $50 per million output tokens. Batch them, and bring your best material.

If most of your life isn’t a codebase, I wrote 15 prompts in the same style for everything else: your statements, your calendar, your inbox, your landing page.

The models got smart enough to be owners. Most people are still prompting them like interns.

I write about running a business with AI agents, the wins and the faceplants. The newsletter is here.