An anonymised participant case note from a Two Prune work simulation. Some identifying details have been removed.
A senior executive with approximately 20 years of professional experience recently completed a Two Prune AI-fluency assessment.
Her final report demonstrated strong authorship. She did not simply accept an AI-generated answer. The structure, priorities and recommendation reflected her judgment, and she maintained control over the final deliverable.
But the source pack contained a material contradiction. Two pieces of evidence could not both support the conclusion as written. The participant had used AI effectively to synthesise the available information, but not to check the final deliverable systematically against the underlying sources.
The report was coherent, well structured and largely her own work. One important contradiction still survived.
The old workflow: generate, then review
A common model for responsible AI use is:
Use AI to generate or synthesise.
Review the output yourself.
Correct anything that appears wrong.
That is better than accepting AI output without review. But it has a blind spot: the human reviewer is still relying on the same attention and memory used during the initial analysis. If a contradiction was missed the first time, simply rereading the final answer may not expose it.
AI had been used as a synthesis tool, but not as a verification tool.
The workflow change: give verification its own pass
After receiving her assessment report, the participant agreed with the finding and changed her workflow. Instead of using AI only to produce an initial synthesis, she added a separate pass that asks AI to:
compare each material claim with the supplied sources;
identify evidence that supports or conflicts with the claim;
flag contradictions between source documents;
distinguish sourced facts from assumptions or interpretation;
surface claims that cannot be traced to the available evidence.
The participant still owns the conclusion. AI does not determine whether the deliverable is correct. It provides a second, deliberately sceptical pass that directs human attention toward the claims most in need of verification.
