Skip to content
English
Contact us
  • There are no suggestions because the search field is empty.

Reviews and publishing master data 

Extraction produces candidate facts. Review turns them into portfolio data. The gap between the two is where the product earns its trust.

The review queue

Documents → Reviews lists everything waiting for a human decision. The queue is exception-oriented: lowest-confidence extractions first, so attention goes where it is worth spending. An empty queue is a good outcome, not an error state.

What you see per item

  • The extracted fields side by side with the source document.
  • A confidence score per field.
  • Any validation findings raised against it.
  • For amendments: the chain back to the parent contract, so you can see the current effective terms.

Steps

  1. Open the item and compare the extracted fields against the source.
  2. For an amendment, follow the chain and confirm you are looking at the current terms, not the original ones.
  3. Approve: the data is published into the organisation's canonical master data and from that point feeds property profiles, portfolio figures and Sunday's answers. Or reject, and it does not.

Tips & best practices

  • This is the answer to "how do I know the AI didn't make it up?". Nothing becomes official portfolio data without a person approving it, and the decision is recorded. In a regulated institutional environment that is often the deciding factor.
  • Getting the amendment chain wrong by hand is one of the most common and most expensive errors in the industry. Reviewing the chain rather than the base lease is the whole point of the screen.