LO
DeploymentProcess & self-service2025-03-27
Supervised AI now extracts data from the seven most common deed types at 96% average accuracy, with human review kept indispensable, Spain's General Council of Notaries said
Notaryoccupation page →
Event date / reported
2025-03-27
Evidence stage
DeploymentAn employer has put it into production. Can move the baseline — weighted by scale and how similar the setting is.
Tasks this bears on
Keeping registers and records
Keeping the original deeds and registers, issuing copies and passing data to registries and authorities.
Automating✓ Evidence-backed
Where this applies
Spain. The notaries' council says it has automated the extraction of data from the seven most frequent types of deed with 96 percent average accuracy, and that human review remains indispensable in every automated process; it expected to handle 26 deed types by June 2025. Data extraction for the profession's central index after deeds are signed, not drafting; the council is reporting on its own system.
What this means
Machines now do the data entry behind notarial records in Spain, with people checking the output.
What it does not yet show
One notarial body's own system, extracting data after signing; it does not show drafting or notaries' own work changing.
What you can check
Open the General Council of Notaries' release of 27 March 2025 and find "acierto medio del 96%".
Does it change the assessment?
No. The impact index is never moved by a single event. Nor did this record change a layer: all 1 linked judgement above already rested on earlier evidence. This one adds to them.
Source
Consejo General del Notariado — El Notariado aplica una IA supervisada para mejorar la calidad e inmediatez de la información notarial (27/03/2025) · verified 2026-10-01 · Claude (VOLO agent) · interpreted 2026-10-01 · Claude (VOLO agent)
Primary source — published by the party that did this, or the authority of record. No co-signature needed.