Skip to main content

AI requirements

What the client actually asked for, extracted from PR MIEW.pdf — a Q&A round on My Workplace Legal, answered by the client, with the legal process validated by Rui Neves Ferreira against the law.

Read this as evidence, not as a plan. Every numbered item below is something the document states. Anything undecided sits in Open questions and is not a default to build on. The 8-phase legal process itself lives in Phase Steps & Inputs.

At a glance

#RequirementType
AI-1AI participates in all 8 phases, at a different moment in eachscope
AI-2AI never fills the informação base necessáriaboundary
AI-3AI drafts the deliverables formais, blocked until base info is completefeature
AI-4Cross-case learning — tell the handler what to watch out forfeature
AI-5Direct Sim/Não verdict, always with grounds, plus a confidence signalfeature
AI-6Detailed reasoning with traceable sources is mandatoryconstraint
AI-7Human review is always requiredconstraint
AI-8Verdict visibility is role-gated, Instrutor and aboveconstraint
AI-9Background assistant first; chatbot is a nice-to-haveinterface
AI-10May ground on historical data, with a GDPR disclaimerdata

The human/AI boundary — AI-2 + AI-3

The single most important line in the whole document. Each phase splits in two, and the AI only ever touches the lower half.

For Abertura the deliverables are, in export order:

OrderDeliverableNote from the document
1opening cover
2Participação DisciplinarExplains what originated the case. The case's opening document.
3Despacho Inicial e Nomeação de Instrutor"e por aí fora para cada secção"
4Termo de Aberturasame pattern

Two hard constraints fall out: generated deliverables have a fixed position in the export, and generation is blocked until the phase's base fields are complete.

Where AI intervenes — AI-1

Every phase, but not at the same point in each. Each one has base information (human) and a document-production part (where the AI helps): "a IA possa ajudar a escrever ou detalhar cada processo".

Who sees the verdict — AI-8

Users of the AI are all direct participants, but the Sim/Não verdict stops at Instrutor. The cut line matches the app boundary: the three roles below it have no admin app at all, only the Portal.

The verdict itself — AI-5

Four separate asks, worth keeping distinct:

AskStrength
A direct opinion — "há fundamento: Sim/Não" — not a compilation for a human to judgemust
Always carries its fundamentaçãomust
A confidence level / "temperatura da análise" beside itwanted
The reviewer can rate the answer — likes it or doesn'twanted

The remaining constraints

#What the document says
AI-4"…com base em todos os casos analisados, ou já processados, ajudar a compreender, a quem vai tratar do processo, o que deverá ter em conta." An advisory layer over past cases, aimed at whoever is handling this one.
AI-6Presenting the reasoning is essencial, so there is always a reference point for where the information came from. Provenance is a requirement, not a nicety.
AI-7"Sim terá que existir sempre" — a human validation step before any action, without exception.
AI-9Primary interface is a background assistant"mais o assistente em segundo plano". A chatbot is explicitly a nice-to-have. A step-by-step form was offered and not chosen.
AI-10The AI may use previous-case backoffice data, not only this case's uploads. It must ship a disclaimer that the model is informed by that data ("based on X processed cases"). GDPR is flagged as an open risk with no decision taken.

Open questions

These block design work. They are not defaults.

#QuestionOwnerStatus
Q1Does the historical corpus influence the answer, or only feed statistics?✅ decided since: D1 — it influences
Q2How to satisfy GDPR when feeding prior-case data to the model✅ decided since: D2 — anonymise at ingestion
Q3Is the workflow fixed, or per-client customisable?❌ open
Q4Examples of past cases that count as a "good analysis"Rui Neves Ferreira · Ana Rocha Alves❌ open — blocks the precedent corpus
Q5What sample data exists today, in what format (PDF, Word, scans)Rui Neves Ferreira · Ana Rocha Alves❌ open — blocks the precedent corpus
Q6Is the knowledge base good enough for the model to answer without leaning on its own parametric knowledge?Rui Neves Ferreira · Ana Rocha Alves❌ open
Q7Who owns the mandatory human validation, per phase❌ open — AI-7 confirms it exists, not who

Not stated in the document

Called out so nobody reads them in by accident.

Often assumedReality
AI orchestrates deadlines and sends alertsprazos e alertas appears only inside the question. The answer redirected to "all 8 phases" plus a background assistant. Never committed to.
A model or provider was chosenNot named anywhere.
The like/dislike signal feeds retrainingHow it's consumed afterwards is unspecified.

Next: how these are served — Knowledge architecture.