<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>Madgett Law — Practice Lab</title><description>Practice management for lawyers, published free by Madgett Law, LLC. Systems, workflows, and tools for handling more cases in less time — so legal services cost less.</description><link>https://www.madgettlaw.com/</link><language>en-us</language><item><title>Run It Yourself, Then Let the Client Choose</title><link>https://www.madgettlaw.com/practice-lab/run-it-yourself-then-let-the-client-choose/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/run-it-yourself-then-let-the-client-choose/</guid><description>The practical stack for running Qwen on firm hardware — models, runtimes, quantization, what fits in how much memory — and the client-facing tier election it makes possible. If the client picks the tier, the routing has to enforce it.</description><pubDate>Mon, 27 Jul 2026 00:00:00 GMT</pubDate><category>tool</category><author>David J.S. Madgett</author></item><item><title>The Practice of Law in 2035: Predictions, With Failure Conditions</title><link>https://www.madgettlaw.com/practice-lab/the-practice-of-law-in-2035/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/the-practice-of-law-in-2035/</guid><description>Most legal futurism is unfalsifiable, which is why it is always half-right and never useful. Twelve predictions about how AI reshapes legal practice — each with the mechanism driving it and the specific evidence that would prove it wrong.</description><pubDate>Mon, 20 Jul 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>How Do You Know It Works? Evaluating an AI Legal Workflow</title><link>https://www.madgettlaw.com/practice-lab/how-do-you-know-it-works/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/how-do-you-know-it-works/</guid><description>Nobody in law builds evaluation sets, so nobody can tell a workflow that got better from one that quietly got worse. Ground truth, the metrics that actually matter per task type, and why cost-weighted error is the only honest score in a law office.</description><pubDate>Mon, 13 Jul 2026 00:00:00 GMT</pubDate><category>tool</category><author>David J.S. Madgett</author></item><item><title>Legal Aid Turns Away Half the People Who Ask. Here Is a Market That Would Change That.</title><link>https://www.madgettlaw.com/practice-lab/a-currency-for-access/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/a-currency-for-access/</guid><description>Legal aid can&apos;t hire against one-year grants, and volunteer hours consume the supervision they&apos;re supposed to add. A forward, specialty-tagged purchase commitment fixes both — and bundles the one input big firms actually have to give.</description><pubDate>Mon, 06 Jul 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>Retrieval Is the Whole Game</title><link>https://www.madgettlaw.com/practice-lab/retrieval-is-the-whole-game/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/retrieval-is-the-whole-game/</guid><description>Why dumping a matter file into a context window fails, why embedding search underperforms specifically on legal text, and how to build retrieval that recovers the right paragraph with a citation attached.</description><pubDate>Mon, 29 Jun 2026 00:00:00 GMT</pubDate><category>tool</category><author>David J.S. Madgett</author></item><item><title>An Unattributed Entry Is Honest. A Confidently Wrong One Bills the Wrong Client.</title><link>https://www.madgettlaw.com/practice-lab/an-unattributed-entry-is-honest/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/an-unattributed-entry-is-honest/</guid><description>Every system that automatically ties work to a matter faces the same temptation: always produce an answer. In a law office that is the wrong design, and the reason is Rule 1.5.</description><pubDate>Mon, 22 Jun 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>Inbound Is an Attention Problem, Not a Volume Problem</title><link>https://www.madgettlaw.com/practice-lab/inbound-is-an-attention-problem/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/inbound-is-an-attention-problem/</guid><description>Twelve calls, four web inquiries, a portal message and three e-service notices is not a lot of information. It is a lot of interruptions. On classifying inbound automatically, routing it by consequence, and the discipline of suppressing what does not matter.</description><pubDate>Mon, 15 Jun 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>Running Models on Your Own Hardware: When It&apos;s Worth It</title><link>https://www.madgettlaw.com/practice-lab/running-models-on-your-own-hardware/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/running-models-on-your-own-hardware/</guid><description>The strongest confidentiality posture is client data that never leaves the building. Here is what local models actually cost, what they are genuinely good at, where they fall down, and the hybrid architecture that is usually the right answer.</description><pubDate>Mon, 08 Jun 2026 00:00:00 GMT</pubDate><category>tool</category><author>David J.S. Madgett</author></item><item><title>The Work You Did and Never Billed</title><link>https://www.madgettlaw.com/practice-lab/the-work-you-did-and-never-billed/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/the-work-you-did-and-never-billed/</guid><description>Unbilled time is not a discipline problem, it is a capture problem — the work happened somewhere your billing system could not see. On reconstructing it honestly, why rounding decides whether approved equals billed, and the one rule that must never bend.</description><pubDate>Mon, 01 Jun 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>The Failure That Says Nothing</title><link>https://www.madgettlaw.com/practice-lab/the-failure-that-says-nothing/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/the-failure-that-says-nothing/</guid><description>The dangerous bug in a firm&apos;s own software is never the crash. It is the button that does nothing, the file saved to a default location, the integration that stopped syncing in March and told no one.</description><pubDate>Mon, 25 May 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>From the Scanner to the Calendar: A Document Intake Pipeline</title><link>https://www.madgettlaw.com/practice-lab/from-the-scanner-to-the-calendar/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/from-the-scanner-to-the-calendar/</guid><description>The mail arrives as a stack of scanned PDFs and leaves as filed documents, calendared deadlines, and a short list of things somebody has to decide. Six steps, and a clear rule about which ones a human must approve.</description><pubDate>Mon, 18 May 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>The Discovery of Your Prompts</title><link>https://www.madgettlaw.com/practice-lab/the-discovery-of-your-prompts/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/the-discovery-of-your-prompts/</guid><description>Every AI-assisted workflow generates artifacts — prompts, retrieved documents, intermediate drafts, transcripts. Are they work product? Are they privileged? Does a litigation hold reach them? Nobody knows yet, and most firms are retaining them without having decided to.</description><pubDate>Mon, 11 May 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>Connecting Claude to Clio — and Why I Had to Build It Myself</title><link>https://www.madgettlaw.com/practice-lab/connecting-claude-to-clio/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/connecting-claude-to-clio/</guid><description>There is an open standard for exactly this problem. My practice management vendor does not implement it. So the connector is four hundred lines of my own Python, and the interesting part is not the code — it is why every firm is writing it separately.</description><pubDate>Mon, 04 May 2026 00:00:00 GMT</pubDate><category>tool</category><author>David J.S. Madgett</author></item><item><title>Ask for the Matter, Not the Path</title><link>https://www.madgettlaw.com/practice-lab/ask-for-the-matter-not-the-path/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/ask-for-the-matter-not-the-path/</guid><description>The software you build for your own firm will be used by lawyers and legal assistants, not engineers. The single fastest way to make it unusable is to inherit the vocabulary of the tools you built it with.</description><pubDate>Mon, 27 Apr 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>Build a Firm Wiki Your AI Can Query</title><link>https://www.madgettlaw.com/practice-lab/a-firm-wiki-your-ai-can-query/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/a-firm-wiki-your-ai-can-query/</guid><description>The reason AI gives you generic legal work is that it has no idea where it is. A structured Obsidian knowledge base — plain markdown, real schema, provenance on every fact — turns a general assistant into one that already knows your practice.</description><pubDate>Mon, 20 Apr 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>What You Owe the Client You Automated</title><link>https://www.madgettlaw.com/practice-lab/what-you-owe-the-client-you-automated/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/what-you-owe-the-client-you-automated/</guid><description>Do you have to tell a client you used AI on their matter? What happens to the fee when a task takes twenty minutes instead of two hours? The disclosure question is genuinely unsettled — the fee question is not, and it cuts against the lawyer.</description><pubDate>Mon, 13 Apr 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>Never Compute a Deadline From Memory</title><link>https://www.madgettlaw.com/practice-lab/never-compute-a-deadline-from-memory/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/never-compute-a-deadline-from-memory/</guid><description>Minnesota&apos;s three-day mail rule moved in 2020. Rule 6.05 was abrogated; the text now lives in Rule 6.01(e). If you learned it the old way you have been carrying a wrong rule for years — and so has every AI you ask.</description><pubDate>Mon, 06 Apr 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>Verifying Form Is Not Verifying Truth: Building a Citation Gate</title><link>https://www.madgettlaw.com/practice-lab/verifying-form-is-not-verifying-truth/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/verifying-form-is-not-verifying-truth/</guid><description>A fabricated case is the easy failure — it does not exist, so somebody notices. The dangerous one is a real case, correctly cited, standing for something it never said. Here is the four-pass verification gate that catches it.</description><pubDate>Mon, 23 Mar 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>Hire Specialists, Not an Assistant</title><link>https://www.madgettlaw.com/practice-lab/hire-specialists-not-an-assistant/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/hire-specialists-not-an-assistant/</guid><description>One general-purpose AI assistant gives you a capable generalist with no limits and no handoffs. A real office is not organized that way, and neither should this be. On writing agent briefs, and why the limits matter more than the capabilities.</description><pubDate>Mon, 09 Mar 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>Your Templates Are Your Real Knowledge Base</title><link>https://www.madgettlaw.com/practice-lab/your-templates-are-your-knowledge-base/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/your-templates-are-your-knowledge-base/</guid><description>Every firm&apos;s institutional knowledge lives in its form file, and every firm&apos;s form file is quietly wrong in places nobody has checked since 2014. On template hygiene, stale-rule propagation, and why generation should populate a template rather than rebuild one.</description><pubDate>Mon, 02 Mar 2026 00:00:00 GMT</pubDate><category>workflow</category><author>David J.S. Madgett</author></item><item><title>The Perfect Is the Enemy of the Good: How Lawyer Regulation Prices People Out of Justice</title><link>https://www.madgettlaw.com/practice-lab/the-perfect-is-the-enemy-of-the-good/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/the-perfect-is-the-enemy-of-the-good/</guid><description>Nine of every ten ethics complaints in Minnesota close with no discipline at all — and every one of them was answered by a lawyer. A look at what our regulatory apparatus costs the people who never get a lawyer in the first place.</description><pubDate>Mon, 23 Feb 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item><item><title>Six Windows: The Hidden Cost of Practicing Law With AI</title><link>https://www.madgettlaw.com/practice-lab/the-mental-load-of-running-six-conversations/</link><guid isPermaLink="true">https://www.madgettlaw.com/practice-lab/the-mental-load-of-running-six-conversations/</guid><description>AI can draft, research, and summarize. It cannot tell you what you were doing. A working attorney on the mental load of parallel work — and the kanban board built to carry it.</description><pubDate>Mon, 09 Feb 2026 00:00:00 GMT</pubDate><category>essay</category><author>David J.S. Madgett</author></item></channel></rss>