Recent
The Same Dataset, Now Your AI Can Read It
·
11 mins
The court orders dataset from the explorer, rebuilt as an API and MCP server so AI assistants can query 929 real orders.
From Westlaw to GPT: A Brief History of Legal Technology
Legal tech adoption has always lagged general technology by 10–20 years. That gap is closing fast — and the next wave won't wait for a committee to finish evaluating it.
Ten Things That Will Happen to Legal AI Before 2027
·
17 mins
Ten research-grounded predictions for legal AI through the end of 2026 — from the first disbarment for hallucinated citations to the collapse of point-solution vendors to the pricing collision between AI-enabled firms and their clients.
Can AI Do What a BigLaw Associate Does?
·
16 mins
The APEX benchmark — built by Mercor, with tasks authored by BigLaw-experienced lawyers and advised by Cass Sunstein — is the most rigorous test of whether AI can perform real legal work. The answer is more specific than vendors or skeptics suggest.
You Can Agent the Work, Not the Walls
An Instagram account-takeover wave exploited Meta's AI support bot at the password-reset gate. The lesson for law firms: authentication and ethical walls exist to refuse persuasion — exactly what agents are built to do well.
Lying Spreadsheets
Excel custom number formats let a cell store one value and display another. Every extraction library reads the stored value. Every LLM platform I tested shifted from 'do not pursue' to qualified interest on the same file.
Kirkland's $500 Million Infrastructure Play
Every headline called Kirkland's $500M commitment an AI bet. The signals in the announcement — no named model, full exclusivity, value-based pricing — point to something different: an infrastructure play that happens to run AI.
eDiscovery Economics: What Your Law Firm's AI Pitch Is Actually Selling
·
12 mins
AI processing costs ~3% of an AI-enhanced eDiscovery workflow. The real savings come from restructuring leverage — shifting volume QC from $750/hr associates to $50/hr contract attorneys. Here's the math.
Building a Medicare Fraud Backtest in One Claude Code Session
A walkthrough of building a Medicare fraud backtest overnight in Claude Code — from a plain-English spec to 289 matched providers across 41 states, a predictive model with AUC 0.79, and out-of-sample validation. Including the three times the pipeline failed, the data duplication bug, and the engineering decisions that shaped the final design.
When Documents Are the Attack Surface
The attack surface isn't AI — it's the documents AI processes. Prompt injection in discovery, adversarial inputs delivered through Rule 34 productions, and the cybersecurity gaps firms create by piping untrusted content through LLM pipelines.