@itsolelehmann: this is how you work *beautifully* with Fable. Thariq's point: when Fable gets something wrong, it's almost always beca…

X AI KOLs Following Tools

Summary

A tweet shares nine practical techniques for working effectively with Fable, emphasizing upfront prompting to avoid mistakes, including blindspot passes, asking for options, and letting the AI ask clarifying questions.

this is how you work *beautifully* with Fable. Thariq's point: when Fable gets something wrong, it's almost always because your prompt was missing information it needed. these 9 moves get that information into the prompt upfront, so the work comes back right the first time: 1. before starting anything you're new at, ask Claude what you don't know. literally say: "do a blindspot pass. what are my unknown unknowns here? teach me enough to prompt you better" 2. before deciding what to build, ask for options. "here's my rough problem. give me 10 ways to solve it, from cheapest to most ambitious. i'll tell you which ones i like" 3. when you can't describe what you want but you'd "know it when you see it", ask for 3-4 rough throwaway versions first. because reacting to drafts beats describing from scratch 4. let Claude ask YOU the questions. "interview me one question at a time about anything that's still unclear. start with the questions where my answer would change the whole plan" 5. show, don't explain. if something already exists that's close to what you want (a doc, a design, a piece of code) just point Claude at it and say "do it like this" 6. before Claude starts the work, have it show you the plan with the big decisions on top. "put the choices i might want to change first. the boring routine stuff goes at the bottom" 7. while Claude works, have it keep notes on every decision it makes without you. "keep a notes file. any time you run into something my instructions didn't cover, write down what you decided. then keep going." you read the list after so nothing slips by silently 8. before you accept the work, test yourself on it. "summarize everything that changed, then quiz me on it. i don't approve until i pass." if you can't pass the quiz, you don't understand what you're shipping 9. if you can't tell good output from bad, have Fable teach you first. Thariq asked for color grading options, realized he couldn't judge them, so he had Claude teach him color grading before picking one every one of these does the same job: it pulls information out of your head before the mistake gets made instead of after another banger article from Thariq.
Original Article
View Cached Full Text

Cached at: 07/07/26, 04:14 AM

this is how you work beautifully with Fable.

Thariq’s point: when Fable gets something wrong, it’s almost always because your prompt was missing information it needed.

these 9 moves get that information into the prompt upfront, so the work comes back right the first time:

  1. before starting anything you’re new at, ask Claude what you don’t know. literally say:

“do a blindspot pass. what are my unknown unknowns here? teach me enough to prompt you better”

  1. before deciding what to build, ask for options.

“here’s my rough problem. give me 10 ways to solve it, from cheapest to most ambitious. i’ll tell you which ones i like”

  1. when you can’t describe what you want but you’d “know it when you see it”, ask for 3-4 rough throwaway versions first. because reacting to drafts beats describing from scratch

  2. let Claude ask YOU the questions.

“interview me one question at a time about anything that’s still unclear. start with the questions where my answer would change the whole plan”

  1. show, don’t explain. if something already exists that’s close to what you want (a doc, a design, a piece of code) just point Claude at it and say “do it like this”

  2. before Claude starts the work, have it show you the plan with the big decisions on top. “put the choices i might want to change first. the boring routine stuff goes at the bottom”

  3. while Claude works, have it keep notes on every decision it makes without you. “keep a notes file. any time you run into something my instructions didn’t cover, write down what you decided. then keep going.” you read the list after so nothing slips by silently

  4. before you accept the work, test yourself on it.

“summarize everything that changed, then quiz me on it. i don’t approve until i pass.”

if you can’t pass the quiz, you don’t understand what you’re shipping

  1. if you can’t tell good output from bad, have Fable teach you first. Thariq asked for color grading options, realized he couldn’t judge them, so he had Claude teach him color grading before picking one

every one of these does the same job: it pulls information out of your head before the mistake gets made instead of after

another banger article from Thariq.

Similar Articles

Fable's judgement

Simon Willison's Blog

A practical tip from Simon Willison: allow Claude Code's Fable model to use its own judgment for testing and delegate coding tasks to subagents running cheaper models, reducing token usage while maintaining quality.