The Legal Engineer Podcast
door Rob Taylor
The Scoring Problem: How Do You Know If Your AI Is Getting Better?
Over deze podcast
The podcast that explains why most legal AI tools are just a single prompt in a nice interface — and what to build instead. 46 episodes covering legal AI software architecture from the ground up: parallel specialist swarms, prompt builder patterns, streaming, OOXML Track Changes, and the engineering decisions that separate demos from production systems. Hosted by Brian Baker. Sponsored by Taylor Legal Engineering. Where law meets architecture.
Afleveringen
De nieuwste 20 van 46 afleveringen
- The Scoring Problem: How Do You Know If Your AI Is Getting Better? · 27 minYou've built a legal AI pipeline. Your first client says it's great. Your second says it missed something. But HOW MUCH better? By what measure? If you can't quantify quality…
- Promise.allSettled: The One Line of Code That Changes Everything · 27 minOne line of code. The difference between a system that loses ALL results when one thing fails and a system that keeps everything that succeeded. Promise.allSettled instead of…
- The Playbook Problem: Teaching AI Your Firm's Position · 27 minYour best partner has 20 years of pattern recognition. They know uncapped indemnification is a deal-breaker, 99.5% SLA is below market, 30-day cure is standard. That knowledge…
- OOXML: The File Format That Makes Legal AI Work · 27 minThat .docx file on your desktop isn't a document. It's a ZIP archive. Rename it, unzip it, and you'll find XML. Track Changes are w:ins and w:del elements. When AI writes these…
- Temperature, Tokens, and the Physics of Legal AI · 27 minThree misconceptions even experienced AI users get wrong. One: temperature zero makes AI deterministic. It doesn't. Two: max tokens means max words. It doesn't. Three: context…
- Certification Is Coming: What Legal Engineer Will Mean in 5 Years · 28 minEvery discipline that matters eventually gets a certification. CPAs. PMP. CISSP. Legal engineering is next. The first certified legal engineers won't just hold a credential —…
- Legal AI Beyond English: The Multilingual Frontier · 28 minA cross-border M&A deal. Contracts in English, German, Japanese, Portuguese. Traditional: four law firms, four timelines, four invoices. Now imagine: one pipeline, four…
- The In-House Counsel's New Superpower · 28 minIn-house legal has always been a cost center. What if your team could process every contract in the portfolio in an afternoon, surface every auto-renewal proactively, quantify…
- The Boutique Firm Advantage · 26 minBig Law's advantage was always scale. More associates, more offices. But what happens when a 10-person firm delivers the same quality — faster and at a third of the price? Scale…
- Why Legal Tech Startups Keep Failing · 27 minThe legal tech startup graveyard is enormous. Hundreds of companies. Billions in venture funding. Most built the same thing: a nice UI around a single AI prompt, staffed by…
- Why Law Firms Should Build, Not Buy · 27 minTwo ways to get AI into your firm. Buy a platform — someone else's architecture, someone else's idea of your workflow. Or build — your architecture, your specialists, your…
- Data Classification for Legal AI: What Goes In, What Stays Out · 26 minNot every document should touch an AI system. How many firms have written down which documents can and can't? How many have a classification policy? The answer, for most firms…
- Who's Liable When the AI Gets It Wrong? · 26 minYour AI pipeline recommends deleting the limitation of liability clause. The associate accepts without reading. The partner signs off. Six months later, the client loses $2…
- The Supervised Autonomy Model · 27 minThe narrative usually falls into two camps: AI replaces attorneys, or AI is just a fancy search engine. Both are wrong. What's actually happening is supervised autonomy.
- AI and the Duty of Competence · 26 minModel Rule 1.1: competent representation. Comment 8: keep abreast of benefits and risks of relevant technology. In 2026, relevant technology means AI. The question isn't whether…
- The Privilege Architecture Problem: Two Data Paths, One Career · 26 minTwo attorneys analyze the same contract with AI. Attorney A uses direct API — two systems. Attorney B uses SaaS — four systems. Same work. Radically different privilege exposure.
- Your AI Tool Might Be Waiving Privilege Right Now · 26 minEvery time you paste a client's contract into an AI tool, that document travels through the internet, lands on someone else's server, gets processed by someone else's…
- Why AI Contract Analytics Will Kill the Benchmarking Industry · 27 minThere's a multi-billion dollar benchmarking industry that exists solely because extracting data from contracts is expensive. What happens when AI does it in seconds?
- The Research Memo That Writes Itself (Almost) · 27 minA senior partner asks for a research memo on non-compete enforceability for AI-generated inventions. Traditional: 6-10 hours. Legal engineering: 30 minutes with four parallel…
- The Hallucination Problem Is an Architecture Problem · 27 minIn 2023, two attorneys submitted a brief with six fabricated case citations from ChatGPT. Mata v. Avianca. It's not a model problem. It's an architecture problem.








