An AI Reliability Checklist for Law Firms (One Page — Print It)
A printable checklist for legal AI reliability — model portability, data control, human-in-the-loop, and fallbacks. The one-pager an office manager can actually pin up.
grep -l "#ai" ~/blog/* ← all posts
Applied AI, Reliability, and Legal Work
Notes on practical AI, model reliability, industry shifts, privacy, record-grounded legal workflows, and accountable human review.
-
-
Page:Line or It Didn't Happen: Making AI Cite the Record
A dangerous legal-AI failure is confident, uncited fabrication. Here is how to require page:line support in a prompt and review the result.
-
Why Legal AI Should Run on Your Machine, Not Someone Else's Cloud
Sensitive testimony shouldn't be uploaded to a vendor just to be useful. The case for on-device legal AI — privacy, continuity, and cost — and where the line actually is.
-
The frontier comes back online
After the June suspension, Fable 5 is back. What the interruption looked like from the seat of someone who builds on these tools — and what it taught me about wiring a stack to a single model.
-
The Paralegal's Guide to AI Deposition Summaries (What's Safe, What Isn't)
A practical workflow for drafting and reviewing AI deposition summaries with page-line citations, failure checks, and accountable human sign-off.
-
What Happens to Legal AI Tools When the Government Pulls the Plug?
A continuity checklist for legal teams that depend on hosted AI models: portability, human review, data control, and a tested fallback.
-
What Happens When the Person Who Runs the Court Reporting Tech Also Builds the Tools
I run technology at a court reporting firm founded in 1981 and build tools for the same field—what that changes about legal tech, AI, and the record.
-
When the frontier gets recalled
Anthropic said a US directive suspended Fable 5 and Mythos 5. A June 2026 snapshot of what that meant for people building on hosted models.
-
Stop prompting like you're Googling
CasePrompts is in preview: free, copy-ready AI prompts for litigation, built on the CITE method — with citation discipline baked in.