What could be wrong with this?
In 20 minutes, we show why prompts like this create expensive rework.
Academy
Before AI touches your workflows, someone needs to own them.
Tai Miranda - Co-founder, Legalboards
Two failure modes
Both are invisible until something goes wrong.
Unclear ownership
Work lives in the team, so nobody catches what AI invented.
Shallow AI context
Output sounds polished, but the brief behind it was incomplete.
Recognition
You have already seen this happen.
An AI draft moved forward before facts were verified.
A timeline generated by AI was sent to a client as if confirmed.
Junior staff used AI output that sounded right but was not reviewed deeply.
A summary used stale data and the wrong number reached a demand letter.
The framework
The OWNED Framework
Five fields. Every workflow. Every prompt.
One person owns it. Not a role.
Specific, observable, and dated.
Handoff is explicit, or work stalls.
Confirmed inputs, not assumptions.
AI output matches prompt depth.
OWNED · O
Owner named
Not assigned. Owned.
The team will handle it.
Maria owns this. Due Friday.
OWNED · W
What done looks like
Specific, observable, dated.
Draft sent.
Draft reviewed and approved by [name] on [date].
OWNED · N
Next owner
If nobody is named next, work sits. AI amplifies the gap.
Send to whoever picks it up.
Hand to PARALEGAL_2 for filing by 4pm.
OWNED · E
Evidence verified
Confirmed inputs, not assumed.
AI built a demand from an outdated case summary.
Medical expenses [AMOUNT_1] confirmed [DATE_2].
OWNED · D
Depth defined
AI outputs at the level of the person prompting it.
Shallow brief → polished, generic output.
Deep brief → specific, verifiable output.
The common way
What AI invents from a shallow prompt.
- Vague liability stated as fact. "Liability rests entirely with your insured" and "the evidence establishes" - but no evidence was provided. AI wrote it as if it was already proven.
- Medical treatment invented in detail. "Diagnostic testing, physical therapy, pain management" - none of this was in the prompt. AI filled in a treatment history that does not exist yet.
- Damages list expanded without instruction. Lost wages, emotional distress, loss of enjoyment of life - none of these were mentioned. AI added them because they sound right.
- 30-day response deadline set unilaterally. No instruction was given on timeline. AI picked one and put it in the letter as a legal demand.
- $150,000 confirmed as a settlement demand. Was this approved by the supervising attorney? Confirmed against policy limits? Nobody checked.
Structured Prompt
Every field maps to a verified OWNED step.
Three golden rules
If you only remember three things from today.
Use CLIENT_A, OPPOSING_A, INSURER_A.
Extract verified facts and paste text only.
Use enterprise controls where data protection is required.
Questions
