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
DennisKennedy.Blog: 23rd Blogiversary
DennisKennedy.Blog was born on February 15, 2003.
23 years. The tools change. The mission remains.
Still here. Still at it.
[Originally posted on DennisKennedy.Blog (https://www.denniskennedy.com/blog/)]
DennisKennedy.com is the home of the Kennedy Idea Propulsion Laboratory
Like this post? Buy me a coffee
DennisKennedy.Blog is part of the LexBlog network.
What Disappears When You Stop Carrying It?
I ran an experiment at the beginning of February.
I closed my planning system and didn’t look at any of it for 48 hours. No peeking. No referencing. I just paid attention to what actually pulled at my thinking when nothing was prompting me.
Then, on Monday morning, before I opened anything, I wrote down
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.
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
Submit an Inquest
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
Research
The Kennedy Idea Propulsion Laboratory investigates human-AI interaction challenges when standard playbooks fail. Research focuses on developing frameworks for complex problem diagnosis, investigative methodology, and collaborative intelligence systems.
FEATURED INVESTIGATION
Human-in-the-Loop (HITL) Interaction Design
Investigating how humans and AI systems can work together to amplify insight rather than automate judgment. The research challenges the prevailing