General AI

Reviewing AI results

Reference only. Project progress and credentials come from assessed work.

Review is not a sign that the AI failed. Review is how human judgement remains connected to the work.

Separate three kinds of statement

KindMeaningExample
FactA claim that should be supported by evidence"Revenue fell 8% in Q2"
InferenceA conclusion drawn from one or more facts"The decline is concentrated in one segment"
RecommendationA proposed action based on facts and judgement"Interview ten churned customers"

The further a statement moves from fact to recommendation, the more human judgement it needs.

A three-step review

01
Check shape
Did it follow the task?
02
Check evidence
Do important claims match sources?
03
Check consequence
What happens if we use it?
  1. Check shape. Did the AI answer the actual question and use the requested format?
  2. Check evidence. Do important claims match the cited or supplied source?
  3. Check consequence. What could happen if the output is wrong?

Low-impact drafts need a light review. Customer messages, financial decisions and system changes need a stronger review.

Hallucination in plain language

A hallucination is information the AI presents as if it were supported, even though the available evidence does not support it. It can be a fabricated fact, an incorrect citation or a detail filled into a gap.

Approve, correct or escalate

  • Approve when the output follows the task, important claims are supported and the consequence is acceptable.
  • Correct when the task is sound but the output needs a contained change.
  • Escalate when evidence conflicts, permissions are unclear or the consequence exceeds your authority.

Recap

  • Distinguish facts, inferences and recommendations.
  • Check the output shape, evidence and consequence.
  • Treat unsupported information as a signal to investigate.
  • Escalation is the correct outcome when authority or evidence is unclear.
Reviewing AI results | Mariete Academy