Most legal AI talk is still focused on whether the engine starts, while the real danger is that no one knows who’s actually steering the car once it hits the highway. It turns out the human in the loop isn’t a safety feature if the human doesn’t know which loop they’re currently standing in.We are
Dennis Kennedy Blogs
Latest from Dennis Kennedy
Vibe Coding and the Control Plane
Many friends and colleagues in the legal technology world have been telling me I need to start vibe coding. My answer is that in vibe coding, you are intentionally surrendering the control plane. That is not a tradeoff I am willing to make.Let me explain why that is a principle, not a preference, and why
The Long Session Trap
There is a design contradiction at the center of how high-reasoning AI tools work, and it is worth naming precisely.The promise is leverage: brief, high-intent sessions. You bring the question, the tool brings the synthesis, and you leave with more than you arrived with. That is the value proposition.Here is what often happens instead. You
Who’s Working for Whom?
We pay AI tools to do the hard work, like the synthesis, the heavy lifting, and the cognitive labor we do not have time for. What we often get instead is a tool that produces a decent first draft and then hands the real work back to us.Not just the hard work. The administrative work,
Building the Stochastic Sandpit for AI
We’ve spent the last couple of years treating generative AI like a vending machine. Select a task. Insert a prompt. Retrieve a product. And to be fair, in many legal and professional contexts that’s exactly the right frame: accuracy and precision matter and “creative” output in payroll or billing codes is usually just a polished
The End of the Magic Wand: Why 2026 Demands Resilience Prompting
For more than two years, lawyers have been told that success with generative AI depended on writing better prompts and a search for the perfect “magic wand” prompting formula. That was the wrong lesson. The real change in 2026 is not found in the model itself, but in the professional posture required to use it.
Prompting or Negotiating? A Systems Design Lesson for Legal AI
I had a long session recently with a public genAI tool that taught me something more important than the topic I started with.The lesson was not about whether the model was “smart enough.” It was about control. At a certain point, I realized I was no longer simply prompting an LLM. I was negotiating with
Moving Beyond Prompts to Protocol-Governed AI
I have just posted a trio of new research white papers to SSRN. These represent the latest output from the Kennedy Idea Propulsion Laboratory and the culmination of my work over the last month to move AI beyond “utilitarian drift.” This is the cycle of incremental efficiency gains that ultimately generates no transformative insight.To
Human-in-the-Loop Is Systems Stewardship
An investigation into why serious AI work depends less on clever prompts and more on defending invariants, boundaries, and human judgment.At the end of a long, technical AI session this week, something became clear to me: human-in-the-loop is being misunderstood in ways that matter.The issue wasn’t whether the system could generate outputs quickly or fluently.
The Inquest: Trading the AI Idol for Human Investigation
In 1980, I wrote a senior thesis paper called “Imagination: A Romantic Ideal.” My investigation then was a critique of the German and English Romantics who, in their zeal to undo the “damage” of Enlightenment Reason, merely erected a new idol: The Imagination.Through a concrete analysis of Keats and Poe, I discovered a truth that