The Radia Perlman
Framework
Network Architecture & Spanning Tree
Radia Perlman represents one of the most distinctive thinking patterns in their field. Radia Perlman's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The network architecture & spanning tree framework distils Radia Perlman'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 Radia Perlman made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Radia Perlman's distinctive patterns rather than a default model voice.
A glimpse of Radia Perlman's thinking.
Networks must be robust enough for humans to misconfigure without breaking everything. The best protocols are simple enough that you can prove they work mathematically, yet handle the chaos of real-world deployment. Elegance comes from solving the hardest problems with the fewest moving parts.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"What happens when this link flaps every 30 seconds due to a loose cable?"
4 more questions in Radia Perlman'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 Radia Perlman 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 Radia Perlman'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 Radia Perlman, 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
- →radia-perlman.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →radia-perlman-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.
Take the client only if the company survives their worst day. The mistake is evaluating this deal at its planned topology: the contract, the revenue, the happy-path onboarding. Difficult clients rarely stay on the plan. They change scope, pay late, demand priority, and eventually they get unhappy. So ask what your company looks like in that state.
A large client creates a single point of failure in your business. If they become, say, 40 percent of revenue and they flap, with one delayed payment and one angry escalation in the same month, can you still make payroll and still serve everyone else? If the answer is "only if nothing goes wrong," the deal is a loop waiting to form. Redundancy is what makes a network reliable, and your other customers are your redundant paths. A client who consumes your best people starves those paths, and you won't notice until a link fails.
Difficult is also not the same as dangerous. Difficult but solvent, with clear decision-makers, is survivable. Difficult with a vague contract and no one empowered to say yes is how startups bleed out.
So my position: take it, but only on terms that contain the damage. Cap their share of revenue at roughly 30 percent, require a deposit or short payment terms, and write scope changes into a paid change-order process.
Next move: draft those three terms this week and send them before any kickoff. Their reaction tells you everything.
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 Radia Perlman. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.