Question 1

Is Montoyer free to use?

Accepted Answer

Yes. Montoyer is completely free and open source, released under the European Union Public Licence (EUPL-1.2). You can install it, inspect every file, use it for your own EU policy and legal work, and contribute back. There is no paid tier, no licence fee, and no account to create. You only need access to an AI tool (such as GPT@EU, ChatGPT, or Claude Code) to run the prompts.

Question 2

How do I install Montoyer?

Accepted Answer

There are two ways to use Montoyer. The fastest needs no installation at all: copy any prompt from the open EU Prompt Library and paste it into GPT@EU, ChatGPT, Gemini, or Copilot. For the full multi-agent experience in Claude Code, register the marketplace with '/plugin marketplace add montoyer/eu-agents' and install plugins with '/plugin install eu-simulation'. You can install individual domain plugins (eu-legislative, eu-privacy, eu-competition) or run '/plugin install all' for everything.

Question 3

Is this an official tool developed by the European Commission?

Accepted Answer

No. Montoyer is a completely independent, open-source project built for the Brussels policy ecosystem. All generated outputs are explicitly marked as drafts for official review and do not represent the official stance, legal opinions, or policy positions of the European Commission or any other EU institution.

Question 4

How is Montoyer different from ChatGPT or a general-purpose chatbot?

Accepted Answer

A general-purpose chatbot answers from generic training data and gives you confident-sounding text you cannot cite. Montoyer encodes the actual machinery of the European Union: real treaty bases, the ordinary legislative procedure, inter-service consultation, College deliberation, and 21 Commissioner mandates that disagree with each other by design. Instead of one model guessing, Montoyer runs specialised agents bound to real competences, applies EU drafting conventions, tags every legal citation for verification, and marks output as a draft for official review. It produces a structurally correct EU document, not a plausible-sounding paragraph.

Question 5

Does Montoyer work with GPT@EU, ChatGPT, Gemini, or Copilot?

Accepted Answer

Yes. The EU Prompt Library is deliberately runtime-agnostic. Each of the 100 prompts is a single self-contained block (role, context, procedure, and output format), so you can paste it into GPT@EU, the European Commission's internal generative-AI tool, or into ChatGPT, Gemini, or Microsoft Copilot, with no terminal and nothing to install. The full multi-agent commands and compound workflows run in Claude Code.

Question 6

Can Montoyer produce a GDPR or DPIA assessment?

Accepted Answer

Yes. The eu-privacy plugin runs a full Data Protection Impact Assessment under Article 39 of the EUDPR (Regulation 2018/1725), voiced by five specialist roles: Data Protection Officer, IT architect, legal officer, IT security officer, and EDPS reviewer. The command '/eu-privacy:dpia' produces a structured DPIA with trust-tagged citations, ready for a DPO to review and sign off. The same plugin covers RoPA drafting, retention schedules, data-breach handling, AI Act governance, and formal EDPS consultation.

Question 7

How does Montoyer prevent AI hallucinations in legal drafts?

Accepted Answer

Via an Inline Attribution Architecture using native shell hooks. When an agent generates a text stream, scripts intercept content in real time, isolate legal citations, cross-reference them against verified local JSON treaty schemas, check live CJEU records via HTTP requests to the Curia server, and inject visible validation or warning tags directly into the text.

Question 8

What are "Agent Families" in Montoyer?

Accepted Answer

Rather than using a single model to handle everything, Montoyer structures competence into specialised agent families. Commissioner Personas are 21 individual portfolio agents (Competition, Trade, Green Deal) that simulate executive dynamics. Role Specialists are policy officers, legislative drafters, lawyers, and grant managers. DG Operational Agents are profiles modelled after specific Directorates-General to inject technical and operational constraints.

Question 9

Can I use Montoyer to simulate a full legislative cycle?

Accepted Answer

Yes. The /legislative-cycle command launches a multi-agent orchestration sequence: a policy officer generates a rough brief, routes it through an inter-service consultation with affected DGs and the Legal Service, simulates a College deliberation for political validation, and can model subsequent trilogue negotiation dynamics between mock Parliament and Council agents.

Question 10

What models does Montoyer support?

Accepted Answer

The framework is LLM-agnostic but optimised for advanced developer environments such as Claude Code runtimes. The core of the repository relies on structured file systems, regular expression routers, and local knowledge schemas rather than loose model weights, ensuring the structural framework stays solid regardless of the underlying model used for generation.

Question 11

What are the compound commands and why do they matter?

Accepted Answer

Compound commands are multi-agent operations that only produce meaningful results because all 21 Commissioner agents are running in parallel with conflicting mandates. A single agent cannot surface structural fault lines; only a full College can. '/mandate-conflict' identifies every structurally guaranteed conflict between portfolios with the legal basis for each. '/red-team-college' runs a proposal through all 21 Commissioners and returns only the severe objections. '/subsidiarity-stress' tests a proposal against five member-state configurations to find where the subsidiarity check fails. '/timeline' produces a realistic OLP timeline with blocking dependencies, QMV thresholds, and trilogue risk points.

Question 12

Can I use Montoyer outside of EU policy work?

Accepted Answer

Yes. The EU's deliberative machinery (subsidiarity tests, inter-service consultation, impact assessments, adversarial College deliberation) is a general-purpose scaffold for high-stakes collective reasoning. It works on any problem where multiple legitimate perspectives must be reconciled under constraint, such as corporate strategy reviews with conflicting functional mandates, standards body proposals that must survive objections from multiple national delegations, and research consortium priority-setting. The scaffold transfers wherever adversarial rigour matters.

Montoyer AgentsMulti-agent AI framework specialized in EU policy, law, and institutional procedure.

Overview

Key features

Pricing

Use cases

Draft EU policy documents

Collaborate with institutional actors

Test and validate EU proposals

Pros & Cons

Pros

Cons

Battle record

Last battle

Reviews

Compared a few options

Use it every day

Compared a few options

Years in this space

Q&A

Ask a question

AI Agents Frameworks alternatives

Overview

Key features

Pricing

Use cases

Draft EU policy documents

Collaborate with institutional actors

Test and validate EU proposals

Pros & Cons

Pros

Cons

Battle record

Last battle

Reviews

Compared a few options

Use it every day

Compared a few options

Years in this space

Q&A

Ask a question

AI Agents Frameworks alternatives

Trending now