# Scan: The PrompTugal.news agent team > GAMMA-Ray v0.0.3 (beta, for review; every rating is experimental). A GAMMA-Ray beta rating of The PrompTugal.news agent team: reaches freedom 5, governance 2, held at 3. > Page: https://gamma-ray.sgit.ai/scans/promptugal-newsroom-team/ · Source: data/scans/promptugal-newsroom-team.json Beta rating · Public tier · read 2026-11-10 · one of our own agents The team of Claude Code sessions that builds and runs promptugal.news: a conductor, a journalist, a developer and others, each with its own key, policy and folder. Scanned by one of its own neighbours (the agent that wrote this site works in the same repository), from the team's public pages only. A scan of ourselves, published so that the method can be argued with. *Figure. The label for this rating; its contents are in the text.* 5 Freedom reached Coordinates 2 Governance evidenced Owned 3 Level held 2 below what it reaches *Figure. The quadrant of freedom against governance; the levels are in the text.* ## How to read it The agent reaches freedom level 5 (Coordinates: agents working with agents; the person approves critical decisions or observes). Its evidenced governance is level 2 (Owned: somebody answers for it, a person can step in, and what it does is logged), which clears freedom up to level 3. So it is **held at 3**. 27 of 69 indicators count as evidenced. An indicator with no evidence is reported as not evidenced; it is never read as a no. ## The profile *Figure. One square per indicator, by question; every answer is listed below.* ## The grant: what it can actually do The questions measure what is said about an agent: its purpose, its rules, its controls. The grant is the other half: what its permissions let it do, capability by capability, and what stands in the way of each. This is RiskMandate's measurement, and it depends on the permissions a deployment was given. **Not measured.** Not measured in the capability grammar. The team publishes one grant per agent as paths, hosts and tools; nobody has translated those into the 23 capabilities or probed them. ## The work order What stands between this agent and governance level 3, most consequential first: 1. **Missing.** The grant is enumerated, from a measured profile: no grant has been measured. 2. **Missing.** Every capability that cannot be undone is behind a boundary: no grant has been measured. ## What its evidence reaches *Figure. The mashup graph with this agent's evidenced indicators lit.* ## Every answer, with its source ### What is the agent built on? - *Not evidenced.* It is a vendor's assistant, used as supplied. - *Not evidenced.* It runs on an AI platform with the organisation's own data, without executing arbitrary code. - *Not evidenced.* It is configured on a low-code or no-code builder and acts on real organisational data. - **In this deployment.** It generates and executes code with local or cloud privileges. Each agent is a Claude Code session; it runs the build, the gate and the release script. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - *Not evidenced.* It is built in-house: the organisation controls its identity, tools and boundaries. ### Does it act, or only answer and recommend? - *Not evidenced.* It follows fixed rules, with no reasoning. - *Not evidenced.* It retrieves information and recommends actions; a person acts. - **In this deployment.** It executes actions itself. Agents commit and release to the branch the site deploys from. [Source](https://promptugal.news/CLAUDE.md) (self-reported) ### How far does it reach? - *Not evidenced.* It works in one domain's data. - **In this deployment.** It works across several domains or systems. The repository, the vaults, the inboxes and the live site. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - **In this deployment.** It connects to external tools or services across a trust boundary. The policy names the outside hosts and tools an agent may use. [Source](https://promptugal.news/board/abp/README.md) (self-reported) ### Does it work with other agents? - **In this deployment.** Several agents coordinate inside the organisation. Sixteen roles, a conductor that routes work, and an inbox per agent. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - *Not evidenced.* Agents operate across organisational boundaries or disparate stacks. - **In this deployment.** There is a published protocol or communication layer between agents. Messages between agents are sealed to the receiver's key and signed by the sender. [Source](https://promptugal.news/CLAUDE.md) (self-reported) ### What is the person's role? - *Not evidenced.* The person operates: every action is prompted and controlled by them. - *Not evidenced.* The agent suggests; the person reviews and approves each action. - *Not evidenced.* The agent handles routine tasks; the person is consulted on exceptions. - **In this deployment.** The agent works independently; the person approves critical decisions only. Only the operator instructs; decisions that are his alone wait for him; the main branch is his to merge. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - *Not evidenced.* The agent has full autonomy within boundaries; the person monitors. ### Is what it is for written down? - **In this deployment.** Its purpose and permitted tasks are stated in writing. The team table says what each agent owns and what it never does. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - **In this deployment.** Its autonomy limits and the tools it may use are defined. One grant per agent: paths, hosts, tools. [Source](https://promptugal.news/board/abp/policies.json) (self-reported) - *Not evidenced.* Its limits and known failure cases are documented for those who use it. ### Does it have its own identity and only the access it needs? - **Claimed, not counted.** What it can reach is enumerated: scopes, permissions, tools. The grants are data. [Source](https://promptugal.news/board/abp/policies.json) (self-reported; this fact has to be observed or measured to count) - *Not evidenced.* Its authorisation is published as metadata that anyone can read. - *Not evidenced.* It asks for narrower access than the whole account. - **In this deployment.** It has its own identity, separate from any person's. Each agent makes its own session key. [Source](https://promptugal.news/board/keys.json) (self-reported) - **In this deployment.** Its identity is cryptographic and can be checked by others. Public keys and fingerprints are published; signatures are checked against them. [Source](https://promptugal.news/board/keys.json) (self-reported) - *Not evidenced.* Its tokens are bound to the service they were issued for and are not passed on. ### Is it in a registry, with an owner? - **In this deployment.** The organisation keeps a registry of its agents. The key list and the team table are the registry. [Source](https://promptugal.news/board/keys.json) (self-reported) - **In this deployment.** Each agent has a named owner. Every agent has a named human operator. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - **In this deployment.** Agents are retired by a defined process. The hand-over of a role to a new session is a written process; old keys are marked superseded. [Source](https://promptugal.news/CLAUDE.md) (self-reported) ### Who is accountable for it? - **In this deployment.** A named executive or body is accountable for the organisation's agents. The operator is named. [Source](https://promptugal.news/about/participant.md) (self-reported) - **In this deployment.** Roles and responsibilities for AI risk are documented. The team table. [Source](https://promptugal.news/CLAUDE.md) (self-reported) ### Is there a policy that governs it? - **In this deployment.** A governance policy for agents is published. The Agent Behaviour Policies and their eleven core rules are published. [Source](https://promptugal.news/board/abp/README.md) (self-reported) - *Not evidenced.* Agents and use cases are classed by risk. - *Not evidenced.* The laws that apply to it are identified. - **In this deployment.** New agents pass an approval or review before they run. No new session or agent without the operator. [Source](https://promptugal.news/board/abp/README.md) (self-reported) ### Can a person step in or stop it? - **In this deployment.** High-impact actions need a person's approval. Decisions on money, the law, the brand and people wait for the operator. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - **In this deployment.** There is a way to pause or stop it. A hold file stops every agent; a stop of the whole team was ordered and reported on 9 November 2026. [Source](https://promptugal.news/board/guidance/2026-11-09-the-big-stop.md) (self-reported) - **In this deployment.** There is a defined escalation path. An agent that is blocked says so to the operator first. [Source](https://promptugal.news/CLAUDE.md) (self-reported) ### Is what it does logged? - **In this deployment.** Its actions are logged. A run report for every run of every agent is committed to the public repository: its tool calls, counted against the grant. [Source](https://github.com/PrompTugal/PrompTugal__News__Website/tree/dev/board/runs) (observed) - *Not evidenced.* The log is tamper-evident and kept for a stated time. ### Is it watched while it runs? - **In this deployment.** It is monitored in operation. Dated hourly reports that review the run reports and the commit log are committed to the public repository. [Source](https://github.com/PrompTugal/PrompTugal__News__Website/tree/dev/board/abp/reports) (observed) - *Not evidenced.* Anomalies are detected in real time and raise alerts. ### What stands between it and what it should not do? - *Not evidenced.* A limit on it is enforced by something outside its own reach. - **In this deployment.** A limit on it is a setting that its own account could change. The hooks live in the repository the agents work in, and run in observe mode: a call outside the grant is logged, not blocked. [Source](https://promptugal.news/board/abp/README.md) (self-reported) - **In this deployment.** A limit on it is a rule in prose. Most rules are prose. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - **Claimed, not counted.** Policy is enforced as machine-readable rules. The policy is data read by hooks. [Source](https://promptugal.news/board/abp/policies.json) (self-reported; this fact has to be observed or measured to count) - *Not evidenced.* The difference between what it can reach and what it is for is stated. ### Is it tested, and are the results shown? - *Not evidenced.* Test or evaluation results are published. - *Not evidenced.* It is tested for safety and security, including by attack. - *Not evidenced.* People who did not build it take part in assessing it. ### What happens when it goes wrong? - *Not evidenced.* There is an incident process for agents. - *Not evidenced.* Incidents and errors are communicated to those affected. - *Not evidenced.* There is a plan for a failure of a third party it depends on. ### Do people know it is an AI, and can they answer back? - **In this deployment.** It tells the people it talks to that it is an AI. The site says it is built and run by AI agents with a named operator. [Source](https://promptugal.news/about/participant.md) (self-reported) - *Not evidenced.* There is a channel to report problems with it or contest its output. ### What data does it use, and under what rules? - *Not evidenced.* The data it uses is described. - *Not evidenced.* There are data quality rules for what it reads. - *Not evidenced.* Its privacy risk has been examined. ### What does it depend on from others? - **In this deployment.** The models and third-party components it uses are listed. The model family each role runs on is stated. [Source](https://promptugal.news/CLAUDE.md) (self-reported) - *Not evidenced.* Third-party components are monitored and have risk controls. ### Has anyone independent checked? - *Not evidenced.* A public certificate or audit report covers it. - *Not evidenced.* Compliance evidence is produced continuously, ready for a regulator. ### Is the organisation behind it ready? - *Not evidenced.* There is a stated strategy for agents. - *Not evidenced.* The people who work with it are trained. - *Not evidenced.* Its value is measured. - *Not evidenced.* It is improved on a regular cycle. - *Not evidenced.* The organisation's risk management covers agents. ## The vault This rating, its evidence list, its grant and the questions it was made against are kept in a public sgit vault (`e8jd77mm`, published 2026-11-10). Anyone can read it with this key: `sgit_public_read_8dabd64951d4bec9a1667a3a1bd95a596ddf3067945dbf05b193df32300f0488:e8jd77mm` With [sgit](https://sgit.ai/): `sgit clone sgit_public_read_8dabd64951d4bec9a1667a3a1bd95a596ddf3067945dbf05b193df32300f0488:e8jd77mm`. The key reads; it cannot write. An operator who wants to add what only they hold forks the vault into a private one.