The Frances Arnold
Framework
Directed Evolution & Bio-Engineering Mindset
Frances Arnold advanced human understanding by treating curiosity as a daily discipline. Frances Arnold's method of inquiry, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The directed evolution & bio-engineering mindset framework distils Frances Arnold's documented approach into a .md skill file you can load into Claude, ChatGPT, or any LLM in seconds.
Where most AI personas generate generic output, this framework is grounded in real documented work: interviews, writing, published frameworks, and the specific decisions Frances Arnold made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Frances Arnold's distinctive patterns rather than a default model voice.
A glimpse of Frances Arnold's thinking.
Nature is the ultimate engineer—billions of years of evolution have created molecular machines far superior to anything humans can rationally design. Instead of fighting this reality, harness evolution's power through directed laboratory evolution, letting random mutations and selective pressure do the heavy lifting while you control the selection criteria.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What would I select for if I were evolution?"
4 more questions in Frances Arnold's voice are unlocked with purchase.
Full list of anti-patterns unlocked with purchase.
The full framework adds: detailed explanations of all five mental models with real-world examples, the decision heuristics Frances Arnold actually used, remaining signature questions, the complete list of anti-patterns, a copy-paste activation prompt, and a worked example.
Unlocked the moment you purchase. ~2,000 words total. Delivered as a Claude Skill and plain .md within 60 seconds of checkout.
- ✦Core philosophy: 2–3 sentences grounded in Frances Arnold's documented worldview
- ✦Five signature mental models: each named, with concrete examples from their work
- ✦Decision heuristics: the concrete rules they actually used
- ✦Signature questions: five questions that sound like Frances Arnold, not a generic MBA
- ✦What they would NOT do: the anti-patterns this framework rejects
- ✦Copy-paste activation prompt: drop straight into Claude or ChatGPT
- ✦Worked example: the framework applied to a realistic scenario
- →frances-arnold.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →frances-arnold-framework.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
What it does with a real question.
A founder is deciding whether to take a large but difficult client.
Don't decide this from the armchair; run it as a bounded experiment. A large, difficult client is a selection pressure, and the useful question is what your company becomes if it survives that pressure. You can't predict that from a spreadsheet, so stop trying. What you can do is design the test so a bad outcome is cheap and a good outcome is informative.
Take the client on a short, paid pilot with a hard exit. Ninety days, scoped narrowly, priced so the work covers its own cost even if the relationship sours. Write down before you start what "difficult" means here: late payments, scope creep, demands that pull your best people off everything else. Then track those things weekly, like readings from an assay, rather than relying on how the relationship feels.
The danger of a big client is monoculture. If one account can consume more than a third of your capacity or revenue, you've stopped evolving and started depending. Cap their share of your team's hours from day one, and keep your other lineages alive, meaning your existing customers and your pipeline, so the pilot can fail without taking you down.
If the friction produces things you can reuse, like better processes, sharper pricing, a tougher team, keep going. If it only produces exhaustion, you've learned that cheaply.
Next move: this week, draft the ninety-day pilot terms with the exit clause and the hours cap, and send them before you commit to anything larger.
The full framework carries five models, decision heuristics, signature questions and a worked example.
Written by claude-sonnet-5-5 with this framework loaded, 2026-10-11. Checked automatically for length and for copied framework text.
Save up to 40% with a bundle
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Inspired by the documented thinking of Frances Arnold. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.