evidoria

← Back to browse

Good practice Imported

TKGM's AI Processing Robots — Automating Turkey's Land Registry Transactions

Türkiye · Ankara · See the Türkiye profile · See the Ankara profile

Evidence: Descriptive / self-reported Top 93% 27/100 · Ask Evidence Copilot about this practice

Turkey's land registry agency TKGM piloted AI-assisted 'processing robot' software in Edirne from 2021, then scaled it nationally from 2023 to 96 offices by December 2024, having the robots prepare property-title transactions inside its TAKBİS system before staff sign-off.

96
Land registry offices using the processing robots (as of December 2024)
TKGM's AI Processing Robots — Automating Turkey's Land Registry Transactions

Details

Maturity
Scaling
Promoter
General Directorate of Land Registry and Cadastre (Tapu ve Kadastro Genel Müdürlüğü, TKGM), Ministry of Environment, Urbanization and Climate Change
Period
2021 (Edirne pilot) – present (96 offices as of December 2024)
Keywords
land registry, cadastre, robotic process automation, back-office digitisation

Context

TKGM, Turkey's General Directorate of Land Registry and Cadastre, deployed software 'processing robots' — robotic-process-automation agents with an AI-assisted routing layer — inside TAKBİS, its national land registry and cadastre information system, to prepare property-title transactions submitted through the Web Tapu citizen portal before staff sign-off.

Activities

The system was piloted for three years from 2021 in the Edirne 14th Regional Directorate, then scaled by the General Directorate to Turkey's highest-volume land registry offices from 2023; TKGM has since begun exploring generative-AI extensions such as satellite/LIDAR image processing for boundary determination and drone-based corner-point marking, discussed at a December 2024 workshop tied to a prospective World Bank-financed project.

Results

As of a December 2024 report, 96 land registry offices were using the robots; however, neither the official TKGM page nor the two Anadolu Agency reports documenting the programme disclose a transaction-volume figure, processing-time reduction, error rate, or citizen-satisfaction result.

Conclusions

The only public evidence of effectiveness is the agency's own characterisation of the pilot as workload-reducing; no independent (non-state) Turkish media investigation, academic evaluation, data-protection impact assessment, or citizen appeal mechanism for the robots' output was found, which is a genuine limitation on independent verification.

Implementation
Indicative cost
Medium (€50k–€500k) — No public cost or budget figure disclosed in available sources.
Time to results
Long (> 3 years) — Piloted three years in Edirne from 2021; scaled to highest-volume offices from 2023, reaching 96 offices by December 2024.
Staffing & skills
TKGM land registry office staff (review/sign-off), TKGM in-house technical team

Conditions for success

  • Integration with the TAKBİS national land-registry system and the Web Tapu citizen portal
  • Multi-year regional pilot (Edirne, 2021-2023) before national scale-up
  • Automatic case-allocation pool routing completed files to staff for review and sign-off

Common failure modes

  • No public transaction-volume, processing-time, or error-rate data disclosed, limiting external verification of claimed workload reduction
  • All available sourcing is official-government or state-wire in origin, a genuine limitation on independent scrutiny

Where it fits

Governance type
national government agency (in-house build)
Scale
96 land registry offices nationally (as of December 2024)
Income level
upper-middle-income (Turkey)

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful