Framework
Deterministic Logic Plus Conversational AI
Most online will builders are wizard-based forms. You fill in fields, answer dropdowns, and a document gets generated. The problem is that approach assumes you already know what you want. That's almost never true. Succession Wills solves this with a split architecture.
How it works
- 1The will itself is generated by a fully deterministic system. Every line of text in the final document was authored by David and his co-founder Nick. No AI is drafting legal language.
- 2The AI layer sits on top as a trained conversational guide. It walks users through the process, answers questions in plain language, and surfaces the right prompts at the right moment.
- 3The result is something closer to having a lawyer in the room than clicking through a form.
Hear it on the podcast
Fix the Thing 70% of Americans Are IgnoringListen to the episodeMore from this episode
Perfect as the Enemy of Good, Applied to Estate PlanningThe biggest threat to completing a will is not complexity. It's emotionally loaded questions, like who gets Dad's guitar, that cause people to stall and never finish. David's framework for getting it done.The LLM-as-Wireframe MethodDavid's practical framework for using AI responsibly in legal contexts without replacing professional counsel entirely.
Get the next framework first
One email a week with the frameworks, tools, and founder stories from the podcast. Free.
More frameworks for AI & Automation
The Unidentified Data PrincipleMost apps say encrypted, in transit, at rest, de-identified. Stephen goes one step further with an architecture where the business model physically cannot pivot into data harvesting.The Round Table of Second OpinionsInstead of marrying one model, poll all of them. Each model has different training data, different personality, different blind spots.AI Disqualification StackUse AI to kill bad deals before they reach human underwriting. Build a hardcoded list of non-negotiables and run every inbound deal through it as a first pass. The goal is not to automate the investment decision - it is to automate the no. Five deals worth real attention each week cannot receive that attention if the team is wading through fifty non-starters. The edge is focus, not volume.The Three Categories of HallucinationDevansh breaks legal AI hallucinations into three categories. The third is the most dangerous, and the hardest to catch with traditional vector search.The Three-Layer StackQuadron's architecture maps onto a deeper principle: institutions need auditability, individuals need ownership, markets need calibration.The Lens vs. The ArtifactAI can generate infinite high-quality artifacts. The scarce resource is the lens — the encoded expertise that produced them.