Struck

Municipality of Amsterdam

Helps to quickly access, search and summarise specific rules in the digital Environment Plan for a specific location.

Last change on 19th of May 2026, at 10:53 (CET) | Publication Standard 1.0

• Publication category: Impactful algorithms
• Impact assessment: Field not filled in.
• Status: In use

General information

Theme

Field not filled in.

Begin date

Field not filled in.

Contact information

[e-mail]

Link to publication website

https://www.struck.eu

Responsible use

Goal and impact

It is time-consuming to manually search complex, layered digital environmental plans in the Digital System for the Environment Act (DSO). Due to the layered legal structure, it is often difficult for non-specialists to quickly and accurately identify which specific rules are in force on a particular parcel of land.

The aim of Struck explore environmental plans is to unlock this information quickly and in understandable language. The system allows users to ask questions in plain language about the use and building possibilities at a specific location. The algorithm analyses the relevant plan rules and summarises them instantly, eliminating the need to search manually through hundreds of legal rules.

As a result, the complex structure of the new Environment Act becomes more accessible to a wider group of employees. This can ensure significantly shorter lead times in preliminary consultations and faster and better information provision at the counter for citizens and businesses.

Considerations

The use of the algorithm is justified because it makes complex legislation significantly more transparent and accessible. The benefit of faster and understandable information outweighs the risk of interpretation errors, as long as a human expert retains final control through the source references provided. The sources are fully accessible and a highlight reference is even made to the section on which the AI bases the answer.

Human intervention

There is a 'Human-in-the-loop'. The AI's interpretation serves as support. The employee checks the accuracy of the unlocked information against the provided source references to the official Environment Plan.

Risk management

The risk management around Struck explore environment plans is aimed at ensuring the accuracy of the information accessed and ensuring expert user control.

● Managing data misinterpretation and accuracy: The risk of misinterpretation due to incomplete source information in the DSO is overcome because the system is designed as a tool for subject professionals. The algorithm unlocks the relevant plan rules with direct source references to the original texts. This enables the professional user to independently assess the completeness and context of the information. The expert user can use the sources presented to identify for himself when information is missing from the source text or when a situation needs further investigation.

● Information security: The algorithm runs within a shielded and secure Microsoft Azure environment (SOC 2-compliant). No exchange with public AI models takes place and the entered project data is not used to train general models.

● Vulnerable groups, exclusion and profiling: These risks are not applicable. The algorithm performs strictly legal disclosure based on objective spatial rules from the environment plan. No personal data are processed that could lead to discrimination based on individual characteristics or backgrounds of applicants.

● Implementation status: The algorithm is currently in use as a decision support tool. Its operation is evaluated periodically when there are changes in the Environment Act and updates in the Digital System for the Environment Act (DSO). Changes within the DSO are immediately processed in Struck so that the correct source is always available. The algorithm is evaluated and improved weekly.

● Through training by Struck and other qualified parties, users are shown how to work with Struck to achieve optimal results. Through prepared prompts and defined workflows (checklists), the output result is standardised between users.

Legal basis

https://wetten.overheid.nl/BWBR0041297

Elaboration on impact assessments

Struck analyses plots and environmental regulations, no profiling of natural persons, no special personal data, and no listing on the AP list. The legal grounds under Article 35 AVG are not met.

Operations

Data

The algorithm uses the following source data and basic registrations to arrive at an accurate assessment:

1. Environment Act & local rules (via the DSO): The current text of the Environment Act, the Building Works Decree for the Living Environment (Bbl) and the rules from the 'Bruidschat'. Via the link with the Digital System for the Environment Act (DSO), the location-specific rules and environmental values are retrieved.

Basic Addresses and Buildings Register (BAG): data on the official boundaries, surface areas and uses of existing properties on the plot in question. This forms the basis for calculating the current building density.

3. Land Registry: Data on plot boundaries and ownership relationships, necessary for accurately determining the rear yard area and its relationship to public space.

4. Project-specific information: User-entered data on the proposed building initiative, such as dimensions, location and intended use of the new structure.

From these sources, the algorithm only processes data on objects and spatial data. No personal data from basic registrations or the DSO are processed.

Technical design

The system uses Retrieval-Augmented Generation (RAG) with a Large Language Model (LLM) via Microsoft Azure. Based on a location and a user query, the system searches the legal texts of the local Environment Plan. The AI analyses the relevant passages and produces a summary that directly answers the query, including references to the source articles.

External provider

Struck.build BV