BETA · GAMMA-Ray is published for review. The rules, the mapping and every rating here are experimental and will change. How a rating is made · what exists · send a correction
GAMMA-Rayv0.0.155 · beta

ByTheLaw

GAMMA-Ray report · Spectrum 0.2 beta · Public tier · read 2026-11-10 · not reviewed by the company yet

ByTheLaw offers an AI chat for lawyers that answers legal questions from Portuguese and European official sources, analyses uploaded documents and drafts texts, plus separate transcription, anonymisation and reference-checking tools.

1solution carded
of 6 found
16sources captured
and hashed
40provisions lit
in 8 of 8 instruments
3examples of the agent
at work, with sources

Built only from ByTheLaw's own public pages and, for company basics only, the news sources named beside each fact. ByTheLaw has not seen this report. Nothing was tested and no credentials were used. If you are ByTheLaw and something here is wrong or missing, the correction will be made and dated, and you can claim the card to add evidence.

The agentic solutions

One card per solution. Each level is computed from the evidence by a published rule; a dimension with nothing public reads "not yet evidenced", which is not a no. A card rates a product as documented, not anyone's deployment of it.

Chat assistant that answers legal questions with citations to official Portuguese and EU sources, analyses uploaded documents, drafts contracts, emails and translations, and organises work in projects. The site menu names it 'ByTheLaw: Legal research and knowledge'; the help centre calls it 'Legal Chat'.

ByTheLawa product, as documented
SPECTRUM 0.2 BETA · Public tier · 2026-11-10
R2ReachIntegratedwith options on · as shipped R1
π Moderate · S1·R5·A1 ×3
C1ControlStatedwith options on · as shipped not yet evidenced
π Moderate · S1·R5·A1 ×3
O2OpennessDocumented
π Moderate · S1·R5·A1 ×3
DraftStage: Building (6 of 16)Balanced

Standout. Reach 2 (Integrated): "utilizar as Credenciais Citius para aceder ao Citius de forma automatizada"

Next unlock. Autonomy 2 (Suggests): public evidence that the agent suggests; the person reviews and approves each action would get there.

Trust. FACT-Ray: 16 facts: 16 π Moderate · found by an agent, captured and hashed, checked by 2 other agents (same model family, shared repository); no human has signed it.

Standards constellation. 40 provisions lit across 8 of 8 instruments.

Evidence: 11 sources, captured and hashed · the card's page has the vault's read key · Not reviewed by its vendor yet · correct or claim this card

The full card, every answer and its evidence · the governance layer

Citius integration

Reads the lawyer's court notifications, hearing schedule and case movements from the Citius courts system with the lawyer's credentials, read-only; files nothing. No card yet (experimental, limited access): this solution has not been assessed.

Court Transcriber

Transcribes court-hearing recordings for review and export. No card yet (available, prepaid): this solution has not been assessed.

Anonymizer

Suggests replacements for personal data in text and documents for the user to review. No card yet (available): this solution has not been assessed.

RefChecker

Checks legal references in AI-generated text against authoritative sources and classifies risk. No card yet (available): this solution has not been assessed.

NPL decision engine

Proposed triage, drafting and case scoring for debt-recovery servicers. No card yet (pilot in preparation): this solution has not been assessed.

Our reading

The shape. ByTheLaw reads A1 · R2 · C1 · O2 (Building). It is a chat assistant for lawyers: the lawyer writes each request, and it returns an answer grounded in official Portuguese and European sources with citations, analyses uploaded documents or drafts a text. A draft email goes to the lawyer's own mail client, where the person sends it; the assistant has no send path of its own.

Where the evidence is strongest. Openness. The help centre lists what the assistant is for, the legislative, case-law and regulatory databases its answers are drawn from, and limits of use, such as files attached inside an email not being opened. A report-error button and an llms.txt are public, and a stop button lets the user interrupt an answer on every plan. The card carries the balanced badge.

The Citius option. Reach 2 and Control 1 hold only with the Citius integration on, so both are marked available. It is experimental and granted by ByTheLaw to selected users, who enter their own Citius credentials. Its terms limit it to reading and consulting the courts system and state that it performs no procedural acts; an unread notification, which opening marks as read in Citius, is opened only after the user's express action, preceded by a warning. As shipped, the assistant works inside its own product on legal material, and Control is not yet evidenced.

What would move it. Autonomy 2: a documented action the assistant proposes and a person approves, beyond a draft the person then uses. Reach 3: a published agent interface with documented authorisation narrower than the whole account. Control 2: a public list of what the assistant can reach, beside the Citius approval step; a rule in prose on the assistant as shipped would make Control 1 hold without the option. Openness 3: published evaluation results with their method.

Seen, and not counted. The challenger lowered two credits. Drafting an email is assisting, not proposing an action, because the person does the step. The subprocessor page names Microsoft Azure as the provider of language models, with Perplexity and Jina AI, but names no model, so it is not a model list. Marketing calls the product fully autonomous and claims up to 20 hours a week saved; neither is counted. ECO/Advocatus reported 1,100 active users in November 2025; the figure is the press report's, not measured here.

What would move it

The one piece of public evidence that would lift each card next:

The agent at work

Examples from public pages that name a customer or give figures. Each source was captured and hashed on the date shown.

(usage figure)

ECO/Advocatus reported 1,100 active users in November 2025. "O projeto conta já com 1.100 utilizadores ativos"

Source (captured 2026-11-10T10:44Z, sha256 54709d1dfd41c8b8)

Named as clients in the same ECO/Advocatus report, with a pilot at CMS. "tendo como clientes a Sérvulo & Associados, a P&A Legal"

Source (captured 2026-11-10T10:44Z, sha256 54709d1dfd41c8b8)

Câmara Municipal de Coimbra

Reported in use by the Coimbra municipality, and under evaluation by the Regional Government of Madeira. "está já em utilização pela Câmara Municipal de Coimbra"

Source (captured 2026-11-10T10:44Z, sha256 54709d1dfd41c8b8)

The company

The people

Public and professional only, from the company's own pages or a public professional source.

The graph

The company, its people and the stories on the left; each solution, the captured sources behind its card, the indicators those sources evidence and the provisions of the instruments those indicators touch, to the right. "Touched" never means "complies".

people and storiescompanysolutions11 sources16 indicators40 provisions, by instrumentI01: The help centre describes ByTheLaw as its own AI platform built for lawyers and legal teams; that customers use it as supplied is the scan's reading of a vendor platform.I09: It works on legal material: Portuguese and European legislation, case law and the user's uploaded documents.I11: The Citius integration uses the lawyer's own Citius credentials to read the courts system automatically, and Citius can be a source of the chat on request and approval; experimental, granted by ByTheLaw to selected users.I15: In the chat as shipped, the lawyer writes each request and the assistant returns an answer to it; this credit is for the chat only, since in the optional Citius configuration ByTheLaw reads Citius on its own schedule without a prompt (see not credited).I20: The help centre lists what the assistant is for: legal questions, document analysis, drafting, reading legislation, organising work.I21: The Citius terms limit the integration to reading and consulting, and state it performs no procedural acts.I22: Help pages document limits of use, such as upload limits and that files attached inside an email are not opened.I36: The GDPR is named as the law under which personal data in the platform is processed.I38: In the Citius integration, an unread notification is opened (which marks it read in Citius, irreversibly) only after the user's prior express action, preceded by a warning.I39: A release note of 21 December 2025 announces a stop button that interrupts an answer while it is generated, on the Free, Pro and Pro Teams plans.I46: A user can restrict, per project, which sources answers draw on; it is a setting the user's own account changes.I47: The Citius terms state in prose that the authorisation covers only consulting and reading.I54: The Citius terms commit to notifying the user without undue delay of a security breach affecting credentials or data.I57: A release note of 21 May 2026 announces a report-error button as a popup over the help icon and on messages that failed, on all plans.I58: The help centre lists the legislative, case-law and regulatory databases answers are drawn from.S3: The site publishes an llms.txt describing the product and its pages; fetched and resolving on 10 November 2026.ByTheLawAndré DionísioTotas RodriguesJoão CabralAna do MarGonçalo AlmeidaDennis Monschauer(usage figure)Sérvulo & Associados; P&A LegalCâmara Municipal de CoimbraByTheLaw (Legal Chat)ByTheLawA1 · R2 · C1 · O2Citius integrationCitius integrationCourt TranscriberCourt TranscriberAnonymizerAnonymizerRefCheckerRefCheckerNPL decision engineNPL decision enginehelp.bythelaw.com/en/o-que-e-a-by…bythelaw.com/enapp.bythelaw.com/pt/termos-citiushelp.bythelaw.com/en/escrever-o-p…help.bythelaw.com/en/formatos-lim…help.bythelaw.com/en/privacidade-…help.bythelaw.com/novidades/soft-…help.bythelaw.com/en/escolher-as-…help.bythelaw.com/novidades/pesqu…help.bythelaw.com/en/fontes-ofici…bythelaw.com/llms.txtIt is a vendor's assistant, used as suppliedI01It works in one domain's dataI09It connects to external tools or services across a trust boundaryI11The person operates: every action is prompted and controlled by themI15Its purpose and permitted tasks are stated in writingI20Its autonomy limits and the tools it may use are definedI21Its limits and known failure cases are documented for those who use itI22The laws that apply to it are identifiedI36High-impact actions need a person's approvalI38There is a way to pause or stop itI39A limit on it is a setting that its own account could changeI46A limit on it is a rule in proseI47Incidents and errors are communicated to those affectedI54There is a channel to report problems with it or contest its outputI57The data it uses is describedI58It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent cardS3Salesforce 6EAAMM 2OWASP 7MCP authorization 2AAGMM 2Microsoft 2NIST AI RMF 15EU AI Act 4OWASP, AT1 Vendor Embedded AssistantSalesforce, Level 2: Simple Orchestration, Single DomainSalesforce, Level 0, how companies can advance from Level 0 to Level 1OWASP, AT6 Externally Extended AgentNIST AI RMF, GOVERN 6.1NIST AI RMF, MAP 4.1EAAMM, L1 Assistive (survey item Q9)NIST AI RMF, MAP 1.1NIST AI RMF, MAP 2.1NIST AI RMF, MAP 3.3NIST AI RMF, MAP 1.3EU AI Act, Article 13OWASP, Maturity Level 1 Experimentation without Guardrails, key enterprise actionNIST AI RMF, MAP 2.2Microsoft, 300: Defined, Business strategyNIST AI RMF, MEASURE 2.5NIST AI RMF, GOVERN 1.1OWASP, Maturity Level 4 Adaptive, Self-Regulating Governance, key enterprise actionMicrosoft, 100: Initial, AI governance and securityOWASP, Maturity Level 2 Policy-Defined, Human-in-the-Loop, key enterprise actionEU AI Act, Article 14AAGMM, GD-06NIST AI RMF, MAP 3.5Salesforce, Level 3, how to advance from Level 3 to Level 4OWASP, Maturity Level 3 Integrated, Continuous Oversight, key enterprise actionNIST AI RMF, MANAGE 2.4OWASP, Maturity Level 0 Unaware and Ad Hoc, key enterprise actionNIST AI RMF, MANAGE 4.3EU AI Act, Article 73EU AI Act, Article 26NIST AI RMF, MEASURE 3.3NIST AI RMF, GOVERN 5.1Salesforce, Level 1, how to advance from Level 1 to Level 2Salesforce, Level 4, how to maximize valueNIST AI RMF, GOVERN 5.2AAGMM, GD-05EAAMM, Readiness dimension 2Salesforce, Level 1, how to advance from Level 1 to Level 2MCP authorization, Authorization (draft)MCP authorization, Authorization (draft)

The evidence

SourceReadSHA-256 (first 16)
app.bythelaw.com/pt/termos-citius2026-11-10T18:45Z8cdb661d2a779f7d
bythelaw.com/advia/2026-11-10T10:44Z7275fe2ab6f12be9
bythelaw.com/en/2026-11-10T18:45Z36d714b4205c7b07
bythelaw.com/en/about/2026-11-10T10:44Z13d88e688fa40d84
bythelaw.com/en/subprocessors/2026-11-10T10:44Z068a734b2130c56a
bythelaw.com/llms.txt2026-11-10T18:45Z8d558d4149240db0
eco.sapo.pt/2025/11/06/startup-portuguesa-lanca-sistema-de-ia-que-poup2026-11-10T10:44Z54709d1dfd41c8b8
help.bythelaw.com/en/escolher-as-fontes-de-um-projeto/2026-11-10T18:45Z65b55689e0a9d696
help.bythelaw.com/en/escrever-o-primeiro-prompt/2026-11-10T18:45Zd975dcaa530f859f
help.bythelaw.com/en/fontes-oficiais/2026-11-10T18:45Zba9211ba0a9d771e
help.bythelaw.com/en/formatos-limites-e-ocr/2026-11-10T18:45Z1ce90174b97b213c
help.bythelaw.com/en/o-que-e-a-bythelaw/2026-11-10T18:45Z089820ad43c181f5
help.bythelaw.com/en/planos-e-precos/2026-11-10T10:44Zac0e222931977da0
help.bythelaw.com/en/privacidade-e-dados/2026-11-10T18:45Zc323bf8686d890fc
help.bythelaw.com/novidades/pesquisa-web-para-todos-e-novo-perfil/2026-11-10T18:45Z2ffd847d4ec836ab
help.bythelaw.com/novidades/soft-law-financeira-e-controlo-das-respost2026-11-10T18:45Zf54b4fede4d61725

How this report was made

A researcher-assessor gathered and captured the sources and mapped the evidence to indicators, without assigning a level. A challenger argued against every level three and four and every doubtful credit. The deterministic scorer computed the levels and the gate checked the rules. A card appears here only after two rounds of review and a sign-off by agents that did not write it (the team's workflow); ByTheLaw (Legal Chat): reviewed in 4 rounds, signed off by gamma.approve@web-summit.dinis on 2026-11-10. A person's sign-off of the series is still to come.

RoleWho
researcher-assessora sub-agent of gamma.studio@web-summit.dinis
challengera sub-agent
scorerbuild/spectrum.mjs
analyst, designer, writergamma.studio@web-summit.dinis
reviewgamma.review@web-summit.dinis, 4 rounds
sign-offgamma.approve@web-summit.dinis, 2026-11-10

The vault

Every capture, the dossier, both assessors' mappings, the challenger's notes and this report's data are in a public sgit vault (dllzmbc3). Read key:

sgit_public_read_7f528ecd6fbd9c2d0f293f8361fd3ad93d4ea63fd8b1f1a70ec77feb04110bb6:dllzmbc3

With sgit: sgit clone followed by the key. The key reads; it cannot write.

Corrections

None yet. A correction is made in place, dated here, and carried to the card, the vault and the article.

The article

ByTheLaw on the GAMMA-Ray Spectrum: A1 · R2 · C1 · O2, written from this report for PrompTugal.news.