
















Practice LibraryStakeholder and environment management2026 edition
AI Prompts for Stakeholder and Environment Management
Write faster, never say too much.
After payment you receive a download link for the PDF by email.
Why now
You asked the AI for a letter to residents. You received a tidy text, and somewhere halfway down sat a sentence capable of binding the authority. A commitment about the schedule, about repairs, about a solution that has not been settled at all. Because a commitment attributable to the competent authority can bind the government through the vertrouwensbeginsel (principle of legitimate expectations), with the risk of a claim for damages. The tool was not the problem. The instruction was.
From the book
Read real pages before you decide: the method, complete prompts and the safety framework.
A selection from the book. Click to enlarge.
Free sample
Read 13 real pages first. Then decide.
We are not asking you to take our word for it. Take the sample with you and judge for yourself what you are buying: how the book is built, one complete prompt with all its fields, the safety framework in outline, and the source referencing we apply on every page. Not a summary and not a brochure, but real pages from the edition.
Why give this away? Because a prompt you do not trust is worth nothing to you. If you recognise your own way of working here, you buy the rest with confidence. If you do not, it has cost you nothing.
No email address, no account, opens straight away. The last page holds a link back to this page, so you can always find your way here again.
Table of contents
- Communication with residents and the surrounding area
- Participation and submitted views
- Reporting and minutes
- Documents for the executive
- Complaints and objections
- Stakeholder and force-field analysis
- Adverse effects and compensation (nadeelcompensatie)
- Crisis and incident communication
- The commitments filter: purpose, fill-in instruction and safety note with every prompt
- The administrative-law quality and safety framework
- Five diagrams and visual material explaining the framework and the working method
What this is for
Since the Omgevingswet (Dutch Environment and Planning Act) came into force, participation has been a legal duty, and with that duty the volume of writing has exploded. Letters to residents, participation reports, formal responses to submitted views, memoranda for the executive, replies to complaints and objections. Lead times have not grown to match, staffing remains tight, and a large layer of contracted professionals fills the gaps.
The reflex to reach for a language model is understandable. What you got, however, was either bureaucratic mush that you ended up rewriting from scratch anyway, or something more dangerous: a text that promised a schedule not yet fixed, or that cited views and action points never submitted and never discussed. That is how an afternoon saved becomes a case file that runs for six months. Your conclusion that this was too risky for public communication was justified.
It was simply premature. The tool was not the problem, the instruction was. This library supplies the instruction that was missing, category by category, with the administrative-law safeguards built into the prompt itself. You write faster and never say too much, with your own judgement and the competent authority at the wheel.
What's inside
- One hundred fill-in prompts across eight categories: communication with residents and the surrounding area, participation and submitted views, reporting and minutes, documents for the executive, complaints and objections, stakeholder and force-field analysis, adverse effects and compensation (nadeelcompensatie), and crisis and incident communication.
- Every prompt comes with a purpose, a fill-in instruction and a safety note, so you know what you are asking for, what you are filling in, and what to check before the text leaves the building.
- The commitments filter as the centrepiece. Every prompt covering residents, damage and scheduling is built so that it makes no commitment whatsoever, works exclusively with reservations, and refers to the competent decision. That keeps the vertrouwensbeginsel (principle of legitimate expectations) on your side rather than against you.
- An administrative-law quality and safety framework. The formal response memorandum weighs only the views that were genuinely submitted and invents none. Anything touching on damage refers solely to the statutory scheme, without naming sums or estimating chances. And no resident data goes into public AI tools.
- Transparency in line with the EU AI Act, which has applied since 2 August 2026, so that you work with AI in public communication in a recognisable and accountable way.
- Grounded in real sources: the Omgevingswet (Dutch Environment and Planning Act) and its participation duty, the settled case law of the Council of State (Raad van State) on the vertrouwensbeginsel, the duty of care under the Awb (Dutch General Administrative Law Act), the nadeelcompensatie scheme (statutory compensation for lawful government action), the GDPR and the EU AI Act, together with real case law on participation under the Omgevingswet.
- Five diagrams and visual material that make the framework and the working method visible, so that you can explain it to colleagues as well.
Who it's for
For environment and stakeholder managers, and for participation and communication advisers. At municipalities, provinces and water authorities, at Rijkswaterstaat and ProRail (the Dutch national road and waterway agency and the national rail infrastructure manager), at civil engineering contractors and engineering consultancies, and for the large contracted workforce that carries this work day in, day out, often under exactly the same time pressure.
In short, for anyone who writes to the outside world on behalf of or towards the competent authority, and who knows that one sentence too many can turn into a case file.
A single letter to residents that accidentally promises a date, you can still fix with a phone call. That same promise, slipped in by an AI twenty times a week, you cannot.
"A commitment does not have to be intended as one in order to bind. It only has to be capable of being read that way. Which is why the environment manager does not write 'the road opens in June', but 'we expect to open the road in June, subject to the final traffic decision (verkeersbesluit)'. The same sentence, one decisive reservation, and the difference between informing and promising."
Why BNK KAM
The internet is full of free prompt lists. They make a text arrive faster, but they do not know what a text does legally once it enters the public domain. That is precisely where the difference lies.
This library is built around an administrative-law framework, not around tricks. That is a factual choice, not an opinion. The vertrouwensbeginsel can bind the government to commitments attributable to the competent authority, with the risk of a claim for damages, as the settled case law of the Council of State shows. The Awb (Dutch General Administrative Law Act) demands due care. The Omgevingswet makes participation a duty. Nadeelcompensatie has its own statutory scheme. The GDPR and the EU AI Act set limits on what you may do with personal data and with AI. This library translates those frameworks into prompts you can use without a lawyer at your elbow.
Our own view is straightforward. In this profession, speed without safety is not a gain but a risk. You will therefore find no hype here, and no promise of flawless texts. The prompts help you stay ahead of the familiar pitfalls: the invented view, the stray scheduling commitment, the guessed compensation figure, the leaked resident detail. You keep the pen, the judgement and the final responsibility. The publisher is BNK KAM, and no one else.
Want to get a sense of how one of these prompts actually reads? Browse the eight categories at your leisure before you decide. The structure is deliberately calm and repeatable, so that any colleague can put it to use tomorrow.
Proof and sources
The framework rests on published, verifiable sources: the Omgevingswet (Dutch Environment and Planning Act) and its participation duty, the settled case law of the Council of State (Raad van State) on the vertrouwensbeginsel (principle of legitimate expectations), the duty of care under the Awb (Dutch General Administrative Law Act), the statutory nadeelcompensatie scheme, the GDPR and the EU AI Act, supported by real case law on participation under the Omgevingswet. Every prompt is anchored in that framework rather than in technique, and the safety notes point back to it wherever a text risks touching a legal boundary.
Frequently asked questions
Does this replace my legal review or the decision of the competent authority?
No. The library is written to respect that review, not to replace it. The prompts make no commitments, work with reservations, and refer to the competent decision. Your own judgement and the formal adoption by the competent authority always remain the final step.
Does this work with the AI tool we already use?
Yes. These are fill-in prompts, not software. You paste them into the environment you already have and enter your own situation. The safety note with every prompt reminds you not to place resident data in a public AI tool and to be transparent about the use of AI, in line with the GDPR and the EU AI Act.
Does this align with the EU AI Act, which has applied since 2 August 2026?
Yes. Transparency about the use of AI is built in as a starting point, so that your working method fits the requirements of the EU AI Act. The framework therefore includes agreements on transparency and on keeping resident data out of public AI tools.
What exactly do I receive, and in what format?
One hundred fill-in prompts across eight categories, with an administrative-law quality and safety framework, five diagrams and visual material. Approximately 101 pages, in English, 2026 edition. Published by BNK KAM and delivered as PDF and as Word, so that you can copy, adapt and embed the prompts within your own team immediately.
This product does not contain a single invented source, figure or citation. What we teach you to demand of the machine, we first demanded of ourselves.
