Legal Prompting - Introduction

NICOLA FABIANO

ITALIAN LAWYER

NICOLA FABIANO

Hello, I'm Nicola Fabiano, an Italian lawyer,

NICOLA FABIANO

and welcome to the first episode of a new series dedicated to legal prompting.

Before we dive in, I want to clarify one point straight away.

This series is not meant to explain, in general terms,

how to use chatGPT or, more broadly, generative AI systems.

It is not a tutorial, nor is it meant to follow the kind of superficial enthusiasm

that often surrounds these tools.

The goal is different, to understand how artificial intelligence

can be used in legal and professional contexts with method, awareness, and critical judgment.

When I speak of legal prompting, I do not simply mean the ability to ask questions to a language model.

I mean the ability to formulate instructions in a legally structured way,

taking into account the logic of legal reasoning, the hierarchy of legal sources,

interpretive criteria, professional duties, and the practical consequences

that a response may have for a client, an organization, or an operational decision.

And this is where the real difference lies.

The difference between a generic prompt and a well-constructed legal prompt

does not lie in the technology. It lies in the method.

And, in law, method cannot be improvised.

A legal professional cannot simply accept a text because it appears plausible.

It must be evaluated, verified, contextualized, and, where necessary, substantially revised.

In other words, you cannot delegate to a model what you are not able to assess critically yourself.

Three fundamental premises will guide this series.

The first is that language models do not reason like lawyers.

They produce plausible text, often well-written, sometimes even persuasive.

But plausibility is not the same as legal accuracy.

A model may confuse legal sources, cite provisions that do not exist,

mix different jurisdictions, invert the relationship between general and special rules,

or produce summaries that are formally elegant but substantively wrong.

For that reason, human oversight is not optional. It is central.

And for those working in regulated professions, it is also a specific professional responsibility.

The second premise is that the use of artificial intelligence in professional settings does not take place in a vacuum.

There is already a legal and regulatory framework that requires close attention.

The GDPR, the AI Act, the principles of confidentiality, data minimization, and accountability,

professional ethical duties, and the organizational obligations that apply to law firms, companies, and public authorities.

That means AI is not a neutral tool to be adopted lightly.

It is a powerful tool, but also a regulated one, and its use requires informed and responsible choices.

The third premise is perhaps the most underestimated.

The choice of model and infrastructure is not a purely technical decision.

It is also, and often above all, a compliance decision.

Using a cloud-based system to process confidential information, personal data, or material protected by professional secrecy,

without having properly assessed the relevant legal and organizational requirements,

can expose professionals and organizations to very serious risks.

We must ask where the data goes, who processes it, for what purposes, with what safeguards,

under which contractual terms, and with what implications in terms of transfers, security, and liability.

In other words, even before asking what can this model do, we should ask,

under what conditions can I use it lawfully and responsibly?

And that is exactly why this series was created.

In recent months, legal prompting has become increasingly central to my work, research, and training activities.

I address it in articles, public speaking engagements, academic contexts, and professional discussions.

But I wanted to create a space that is more direct, more reflective, and, in a sense, more practical.

This podcast is meant to be exactly that.

A space for in-depth discussion where we can address concrete cases, real-world problems,

and the questions faced by those working in law, compliance, data protection, cybersecurity,

and, more broadly, innovation governance.

So we will not be discussing artificial intelligence in abstract terms.

We will discuss how to use it and how not to use it when drafting a privacy notice,

analyzing a decision of a data protection authority,

preparing a legal assessment,

designing a retrieval system or a legal AI project,

or integrating AI into the internal processes of a law firm or an organization,

without creating new risks.

We will also focus on another essential point.

Using these tools well does not simply mean getting better answers.

Above all, it means building better processes.

Because a good prompt on its own is not enough.

What is needed is the right context, a method of verification,

and the ability to distinguish between operational support

and the improper substitution of professional judgment.

That is why, at least as I understand it, legal prompting is not an isolated technique.

It is a point of convergence between legal expertise, critical judgment,

data governance, and professional responsibility.

In the coming episodes, we will go further into detail.

We will discuss the structure of legal prompts, common mistakes,

the reliability of outputs, sources and controls,

and the use of AI in document drafting, compliance workflows, and decision support systems.

And we will always do so starting from a simple idea.

Innovation is only useful when it remains governable.

If these topics are of interest to you, you can also follow my in-depth analysis

on my blog www.nchfab.eu and subscribe to the weekly NCHFAB newsletter, every Tuesday.

Also available on my blog, where every week I share analysis,

references and insights on privacy, data protection, artificial intelligence,

cybersecurity and regulatory innovation.

I look forward to joining you again in the next episode dedicated to legal prompting.

Thank you for listening to this first episode of the NCHFAB podcast.