5:01

S01:E10 May 25, 2026

Legal Prompting - Synthesis and perspectives

Tenth and final episode of the first season of Legal Prompting. We close the loop of the journey built episode after episode: Legal Prompting is not a trick, it is a method. A disciplined practice for querying AI systems while remaining a lawyer, without delegating reasoning but structuring it into verifiable instructions. In this episode: The three threads of the season: prompt quality, human verification, infrastructure choice. The three cross-cutting operational rules: document, update, share with caution. The outlook: local models, vertical tools, consolidation of the regulatory framework (AI Act, GDPR, Italian Law 132/2025). Why AI does not replace the lawyer but compels the lawyer to make explicit premises, reasoning, sources and evaluation criteria. Thank you for following the first season. To stay in touch and continue the deeper discussions between seasons, subscribe to the newsletter at nicfab.eu.

6:14

S01:E09 May 18, 2026

Legal Prompting - AI Act: obligations for legal professionals

Ninth episode of Legal Prompting. After discussing professional secrecy as a criterion for choosing an AI infrastructure, we shift our focus to the regulatory framework: the European AI Act and the obligations placed on legal professionals as deployers of AI systems. The central principle: those who use AI in legal practice are not mere users but regulated subjects under the AI Act, with precise obligations. To these is added the cross-cutting duty of AI literacy (Article 4), already applicable since February 2025. Three concrete applications: Classify the risk of the system used (prohibited, high, limited, minimal) Notice to the client and transparency under Article 50 of the AI Act Documenting use: logs, standard prompts, human controls Three cross-cutting operational rules: effective human oversight, preliminary assessment of tools, continuous updating on the Regulation’s deadlines. In the next episode we will close the journey with a synthesis of the method and a look at the perspectives of evolution. To dive deeper, subscribe to the newsletter at nicfab.eu.

5:29

S01:E08 May 11, 2026

Legal Prompting - Professional secrecy and AI infrastructure

When a legal professional uses an AI system to handle information covered by professional secrecy, choosing the infrastructure is a deontological decision, not just a technical one. No well-written prompt can compensate for inadequate infrastructure. In this episode: Three concrete applications: confidential files, advice on special-category data, opinions on extraordinary transactions and criminal proceedings Three operational rules: classify before prompting, document the choice, favor abstraction References to Italian Law 132/2025, the AI Act and the implications of extra-EU data transfers Weekly insights at nicfab.eu.

5:26

S01:E07 May 4, 2026

Legal Prompting - Legal Prompting in corporate compliance workflows

In the previous episode we saw how to use AI to analyse contracts and clauses. Now we take a step further: those prompts do not live in isolation, but inside business processes involving people, documents, deadlines and responsibilities. In this episode we discuss Legal Prompting in corporate compliance workflows: privacy, anti-corruption, anti-money laundering, information security, organisational liability models, internal controls. The starting principle: AI is not a neutral tool that adds to an existing process. AI changes the process, changes who does what, how a decision is documented, who is responsible for an outcome. Three concrete applications: Handling data subject requests under the GDPR: first classification, extraction of relevant information, preliminary check of deadlines. Periodic review of corporate policies: codes of conduct, privacy policies, internal procedures, comparison with updated legal references. Monitoring of internal reports (whistleblowing): triage and categorisation, with the highest caution on infrastructure. Three cross-cutting working rules: Every use of AI in compliance must be documented (prompt, model, operator, outcome). AI introduces the risk of automating error: corporate prompts must be versioned, tested, validated, updated. Responsibility remains human: the controller, the employer, the professional. Human oversight is not a formal detail. In the next episode we will enter the territory of professional secrecy and the choice of AI infrastructure. 📩 Subscribe to the newsletter at nicfab.eu to stay updated. 🎙️ All episodes: podcast.nicfab.eu #LegalPrompting #GDPR #Privacy #AI #Podcast

5:29

S01:E06 Apr 27, 2026

Legal Prompting - AI-assisted contract and clause analysis

In this sixth episode we apply prompting techniques to contract analysis. Four distinct operations, each with its own prompt: Structured review of a single contract: role, applicable law, point of view, areas to examine, output format. Comparison between versions: substantive differences, risk classification, few-shot prompting to standardize the format. Verification against a checklist: the quality of the output depends on how specific the checklist is, and it must be built beforehand. DPA analysis against article 28 of the GDPR: each letter of paragraph 3 as an item in a structured verification. Three non-negotiable cautions: the model does not negotiate, it does not know the commercial context, and it does not replace the full reading of the contract by the professional. In the background, a recurring theme: where the model that you use to analyze a client’s contract is actually running. A compliance choice before it is a technical one.

5:57

S01:E05 Apr 20, 2026

Legal Prompting - Chain-of-thought e few-shot prompting nel legal

Two techniques change the way a model approaches a legal problem: chain-of-thought — the explicit request to lay out the logical steps before the conclusion — and few-shot prompting — providing two or three well-chosen examples to steer format and method of the answer. In this episode we look at: how to structure step-by-step reasoning with a concrete example on data transfers outside the EU (Chapter V GDPR, Schrems II); how to pick few-shot examples without introducing bias; how to combine the two techniques for the analysis of complex decisions; the three limits to be aware of: context length, example bias, and plausibility that is not legal correctness; why documenting prompt, examples and verification is already AI governance. Chain-of-thought and few-shot are not tricks: they are the way we translate our legal method into instructions understandable to the model. In the next episode we will apply these techniques to the analysis of contracts and clauses. 🎧 Also on Apple Podcasts, Spotify, Amazon Music, and Podcast Index. 🌐 nicfab.eu

7:17

S01:E04 Apr 13, 2026

Legal Prompting - RAG and its risks in the legal domain

In this episode, we talk about RAG — Retrieval-Augmented Generation — in the legal domain. What it is, how it works, and, most importantly, what risks it introduces for the legal professional. RAG allows a model to work with documents provided by the user rather than relying solely on its training data. The idea is powerful, but the process conceals concrete pitfalls: retrieval based on linguistic rather than legal similarity, document fragmentation that breaks argumentative structure, outdated sources retrieved without validity checks, opacity in how fragments are used, and implications for professional secrecy. Four practical safeguards: verify the sources, check the segmentation, choose the infrastructure carefully, and document every use. Subscribe to the newsletter at nicfab.eu

7:47

S01:E03 Apr 7, 2026

Legal Prompting - Drafting privacy notices with artificial intelligence

How to use artificial intelligence to work on privacy notices without losing legal control. Three concrete operations: checking completeness against Article 13 of the GDPR, simplifying the language in compliance with Article 12, and adapting a base notice to different contexts, such as employees or apps. Each operation includes a structured prompt example. With the three Legal Prompting premises: human supervision, regulatory framework, and infrastructure choice. Episode 3 of the Legal Prompting series — NicFab Podcast. Newsletter and insights: nicfab.eu

16:33

S01:E02 Mar 30, 2026

Legal Prompting - Analyzing Supervisory Authorities' Decisions

Second episode of the Legal Prompting series. How to use artificial intelligence to analyze a supervisory authority’s decision on data protection: why “analyze this document” is not enough, how to build a structured prompt (role, context, specific instructions, output format), the traps to watch for — normative hallucinations, loss of argumentative nuances, fabricated cross-references — and the compliance implications of using cloud-based models. Read the column in the newsletter → nicfab.eu

10:16

S01:E01 Mar 23, 2026

Legal Prompting - Introduction

The first episode of the NicFab Podcast is dedicated to Legal Prompting: how to use artificial intelligence in legal and professional contexts with method, awareness, and a critical eye. This episode introduces the three fundamental premises of the series: language models do not reason like lawyers; the use of AI in professional settings falls within a specific regulatory framework (GDPR, AI Act, professional ethics); and the choice of model and infrastructure is a compliance decision even before it is a technical one.