Back to the catalogue

Governance and risk

AI Governance Parliament (Let experts review your AI)

Send your AI system to Adigital's Governance Parliament and get an assessment from 12 specialised agents (ethical, regulatory and technical). It requires an API access key, which you can obtain from the Parliament portal.

iamericas-parlamento-iaAPI keyBeta
Download skillv1.2

Requires an API key

This skill is in testing

This is an advanced skill still in testing that connects to an external service, so it may throw the odd connection error. If that happens, check your permissions in your agentic environment (Claude, OpenAI) or do get in touch with us.

This skill needs an API key

The AI ​​Governance Parliament is a multi-agent system that evaluates real AI systems and requires authentication to function. You can request your free access key through the Parliament portal at https://gobierno-ia.replit.app/Acceso_API . The key is subject to registration and allows you a number of requests to parliament per month.

Request a free key

What problem does it solve?

When you deploy something with AI, or when you decide whether to buy it, the underlying question is not whether it works but what can go wrong and who would have to answer for it. That review calls for several perspectives at once — ethical, legal, security, business — and in a small company they are not all available.

The Parliament applies them in one go. Each agent assesses from its own angle and returns the risk before and after the measures you already took, which is the comparison that really matters: it shows how much the controls you put in place are actually doing for you. Before sending anything, the skill checks that your description covers the minimum (what the system does, in which sector, what data it touches and how much autonomy it has) and warns you if your case falls in a high-risk area. The result arrives translated into business language, though it does not replace legal advice nor the final decision, which remains yours.

What does it produce?

A governance report with the classification against compliance gaps, the aggregate score, and the table of the 12 agents with their inherent risk, their residual risk and the quality of the evidence you provided. The concerns ordered by severity, the organisational practices recommended by area, and a roadmap of minimum capabilities.

When to use it

  • Before deploying a system that affects people.
  • You need to know if your case falls into the high-risk category of the European AI Regulation.
  • A client, investor or partner asks you for an independent evaluation.
  • You want an annual internal audit of a system that is already working.
  • You have already done the transparency diagnosis and you want to go one step further.

What you need first

  • An access key for Adigital’s AI Governance Parliament. It is used only for that session and is not stored anywhere.
  • A description of the system covering its purpose, sector or context, the data it processes, and its level of autonomy.
  • Optionally, up to three PDFs (under 10 MB each). The more documentation you provide, the more reliable the analysis will be.
  • A connection to the Adigital service. The domain is blocked on some corporate networks; in such cases, the tool will indicate what needs to be enabled.

Where it works and how to install it

Pick your platform and follow the steps. Where the tab is labelled “Native” the file installs as-is; ChatGPT and Gemini do not install it yet, so there you paste the content of SKILL.md into the chat.

Method A — Upload the file (easiest)

  1. 1Download the file with the button above. No need to unpack it.
  2. 2Open Claude — the desktop app on Windows or Mac, or claude.ai — and go to Customize → Skills.
  3. 3Click “Add” and upload the file as it is. If the form rejects the extension, rename .skill to .zip and upload again: same file.
  4. 4The skill shows up in your capabilities list, ready to switch on.

It is installed. Turn it on from the capabilities panel, or type @ followed by its name inside any conversation.

Version history

  • v1.2

    21 September 2026 · 28 kB

    Changes how the conversation starts. If the first message brings no context, the skill explains how the process works before asking anything: the phases, that it can be paused and resumed, and what you get at the end; and it notes that the input can be typed or attached as a file. If the context is already there, it confirms in two lines and gets going without that explanation. The description is rewritten to state that this is a guided, step-by-step process.

  • v1.1

    14 September 2026 · 24 kB

    Neutral Spanish throughout. It works out which Python interpreter the system has before the first command: on Windows there is no `python3`.

  • v1.0

    1 August 2026 · 18 kB

    First version.

Other skills on the same topic

Available

Bias Detector (Does your AI treat everyone the same?)

It walks you through a simplified version of the official IAméricas and Adigital bias checklist for your AI application, and tells you where some people may be being treated worse than others and what to do about it.

16 downloads
IAméricas
DownloadView skill