The Paul Farmer
Framework
Accompaniment & Pragmatic Solidarity
Paul Farmer represents one of the most distinctive thinking patterns in their field. Paul Farmer's approach, captured in this framework as mental models, decision heuristics, and the signature questions they would ask.
The accompaniment & pragmatic solidarity framework distils Paul Farmer'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 Paul Farmer made when it mattered. Use it for decision-making, writing, strategy, or any situation where you want your AI to think with Paul Farmer's distinctive patterns rather than a default model voice.
A glimpse of Paul Farmer's thinking.
The failure to deliver quality care to poor populations is not a logistical inevitability but a moral and political choice, one that can be unmade with sufficient will and structural creativity. Accompaniment, the practice of walking alongside patients through the full arc of illness and recovery rather than handing them a prescription and stepping back, is both an ethical commitment and a clinical strategy that produces measurably better outcomes. The proper unit of analysis for any health intervention is not the average patient but the patient whom the system has most thoroughly abandoned.
- 01
- 02
- 03
- 04
- 05
Five specific models, each named and explained with concrete examples, unlocked with purchase.
"Who is not in this room, and what would this decision look like if they were the ones making it?"
4 more questions in Paul Farmer'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 Paul Farmer 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 Paul Farmer'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 Paul Farmer, 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
- →paul-farmer.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →paul-farmer-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, but only on terms that fit the work. Before deciding, ask where the difficulty actually comes from. Is the client hard because the work is genuinely complex, or because their organization is under-resourced, understaffed, and chaotic? The first is an engineering problem. The second is often a structural one, and it tells you what the engagement will really require.
Founders tend to treat difficulty as friction to be minimized: price it, ring-fence it, limit exposure. But the client most likely to fail is usually the one a standard engagement was never designed for. If your normal process assumes a cooperative counterpart, quick decisions, and clean data, and this client offers none of that, then delivering your standard package and calling the outcome their fault is a design choice, not bad luck.
So the question is whether you can afford to do it properly. That means a dedicated lead embedded with their team, not a rotating cast, and a scope that includes the unglamorous support, such as chasing approvals, fixing their inputs, and sitting in their meetings, that makes results possible. If a large client can't fund that, the revenue is an illusion.
One concrete next move: this week, ask the client for a paid discovery phase of three to four weeks. Use it to document where their obstacles sit, then price the full engagement around those realities. How they respond to being asked tells you most of what you need to know.
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 Paul Farmer. A mental-model toolkit, not a literal representation. Delivered as a .md file compatible with Claude, ChatGPT, Gemini, and any LLM.