I design for a living https://teapawt.net/t.co/DOLCWaBAHl / Boutique Design Agency https://teapawt.net/t.co/XMFwez7AkE / Framer Agency https://teapawt.net/t.co/hmqhFJsJ82 / AEO SaaS
Dubai
Joined January 2022
- Tweets1.6K
- Following110
- Followers307
- Likes869
Had a lead in March who picked Sanity over Webflow for its “benefits”.
They never went live.
Marketing team is still struggling.
Tech team never got around building the website because their main priority is always the product.
You're burning your AI limits on tasks a cheaper model does just as well.
Most beginners use the biggest model for everything. That's like hiring a senior architect to change a lightbulb.
Here's the simple guide to when to use what 👇
🟢 Small or fast models (Claude Haiku, GPT mini, Gemini Flash):
• Fixing grammar or rewriting a sentence
• Summarizing an email or a doc
• Renaming files, formatting tables, cleaning data
• Quick questions you could Google
• Yes/no checks, tagging, sorting
🟡 Mid models (Claude Sonnet, GPT's standard model, Gemini Pro):
• Writing a first draft
• Everyday coding: small fixes, one file at a time
• Brainstorming ideas
• Turning notes into a plan
🔴 Frontier models (Claude Opus, GPT's top reasoning model, Gemini's Deep Think):
• Big decisions with lots of context
• Planning a whole project or architecture
• Debugging something the smaller models already failed at
• Long, multi-step agent work
• Anything where being wrong costs you real money
Bonus: for pure yes/no decisions inside your apps, tiny decision models like Jev do it in half a second for almost nothing.
The rule I use as a non-techy guy who builds his own tools:
Plan with Opus. Build with Sonnet. Check with Haiku.
Since I started doing this, I hit my limits way less, and nothing got worse.
Bookmark this for the next time you open a new chat on autopilot.
What's your default model right now? ⏬
Clients ask me "Webflow or Framer?" every week.
Wrong question.
The right one: who updates / uses the site after we leave?
Most of my clients have zero tech team. If their marketing lead can't change a headline without calling us, we failed, no matter which tool we picked.
Pick the tool your team can actually run. The rest is preference.
What’s your approach? ⏬
Hot take: most of your AI bill is wasted on questions a cheaper model answers better.
On our agency's internal tool, I don't ask Claude "is this project healthy?" anymore.
A small decision model (Jev) answers yes or no with a confidence score in half a second, for a fraction of a cent. Same for my CRM: does this deal need attention today?
Claude still does the thinking and the writing. But the next AI wave isn't one model that does everything. It's specialists.
I wonder how apt this becomes for human skills.
Generalists vs. Specialists. Which one are you?
Should we make this interesting?
Online design-to-dev race. Same Figma file. Team Webflow/Framer vs team code (Git, Astro, whatever you swear by).
Fastest to a live, client-ready site wins. You judge.
Who's in?
Comment below on which team you want to be in ⬇️
If someone has to ask "so what are you building?", your booth, your homepage and your pitch all have the same bug.
Walked @DubaiAIFest with a designer's eye. The fix:
→ one sentence: who it's for + what it does. no adjectives
→ one visual of the product actually working, not your logo
→ one thing you're better at, not 14 features
→ a palette that isn't blue and orange
Same test applies to ChatGPT now. If it can't say what you do in one line, it won't recommend you either.
Keep generating until you're happy with the product in focus
Use the attached image as the exact reference for the rust-orange leather bomber jacket: its colour, seams, zip and collar, and the dark olive-sage rustic concrete wall. Keep the jacket identical. Remove every other garment and the rest of the rack. The jacket now hangs alone on a single black hanger from one short steel rail against the wall, centred. Studio lighting: a large soft key from the upper left, a gentle neutral fill from the right, a thin rim light along the shoulders, and a soft pool of light on the wall behind with a subtle vignette, so the leather’s grain and sheen read clearly. The wall stays dark and textured. 35mm film still, muted pastel palette, fine grain, soft halation, shallow depth of field. No people, text or logos.
