# Scan: Visor.ai AI agents > GAMMA-Ray v0.0.155 (beta, for review; every rating is experimental). An example GAMMA-Ray beta rating of Visor.ai AI agents: freedom 1, 1, 1 across its configurations; deployment governance not assessed. > Page: https://gamma-ray.sgit.ai/scans/visor-ai-agents/ · Source: data/scans/visor-ai-agents.json Example · beta rating · a product as its vendor documents it · read 2026-11-10 · not seen by the vendor Visor.ai's voice and chat AI agents for customer service, with Nexa, the agent that builds, tests and proposes fixes to them. A scan of a product as its vendor documents it, not of any one deployment. Made by the report studio: a researcher-assessor, a challenger, then the scorer. Part of the first Portuguese cohort. Built only from Visor.ai's own public pages (product, documentation, blog, customer stories, legal and security pages). Nothing was tested. If you are the vendor and something here is wrong, the correction will be made and dated. *Figure. The label for this rating; its contents are in the text.* 1 Freedom as shipped Answers 1 Freedom at most Answers 7 Controls it brings as shipped n/a Deployment governance not assessed ## How to read it This is a product, not a deployment. A product has no owner, no policy in force and no mandate until somebody runs it, so it is given **no governance level and no level held**: those belong to a deployment. What a product has is a freedom level for each way it can be configured, and a list of the controls each configuration brings. *Figure. The freedom level of each configuration; the table has the same.* | Configuration | What changes | Freedom | Controls | Turned on by the operator | |---|---|---|---|---| | **As shipped** | Voice AI Agent with its documented defaults. | 1 Answers | 7 | nothing | | **Healthcare deployment** | Deployment practice stated for healthcare customers: scope and data agreed with the customer's DPO before go-live. | 1 Answers | 9 | its purpose and permitted tasks are stated in writing; a limit on it is a rule in prose | | **Deployed by Visor** | The deployment service described under 'How we deploy' on the product pages: a Visor team, end-to-end testing, validation by the customer's team before launch, and training of the customer's people. | 1 Answers | 9 | new agents pass an approval or review before they run; the people who work with it are trained | The same product is a different agent in each row. A rating of a deployment starts by saying which row it is. 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. No deployment shape for this product is published in the capability grammar. ## Seen, and not credited - I60 Its privacy risk has been examined The healthcare page states that, before go-live, what the agents may ask for and where conversations and recordings are kept is agreed with the customer's data protection officer. That is a scoping agreement; no privacy risk examination or impact assessment is named. The security page names an impact assessment only for system change management. [Source](https://www.visor.ai/healthcare/) - I20 in the default or visor-deployment configuration The 'How we deploy' block says Visor and the customer agree on what is in and out before work starts, but does not say the scope is written; only the healthcare page says the scope is written before work starts. Not stretched. [Source](https://www.visor.ai/voice-agent/) - I47 from the Chat AI Agent criteria ('you describe, in plain language, what the agent must not handle') The criteria flag a matching conversation as critical for a person to step in: a detection and escalation rule, not a limit on what the agent does. Not credited as I47. [Source](https://www.visor.ai/healthcare/) ## 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. - **In this deployment.** It is configured on a low-code or no-code builder and acts on real organisational data. Generali's own team builds workflows and automated services on the platform without a developer, connected to the insurer's systems through web services. [Source](https://www.visor.ai/success-stories/generali/) (documented) - *Not evidenced.* It generates and executes code with local or cloud privileges. - *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. At Generali, the platform was connected to the insurer's systems through web services, so four common requests (duplicate documents, address changes, adding a vehicle, cancellations) run end to end as automated workflows. [Source](https://www.visor.ai/success-stories/generali/) (documented) - **In this deployment.** It is in production: a public source names a customer or gives usage figures for what it does on its own. Generali Tranquilidade is named as a customer; the page gives 80,000 conversations a month between brokers and the AI agent, an undated figure that the page markup attributes to an archived copy of 2022-08-20. [Source](https://www.visor.ai/success-stories/generali/) (documented) ### How far does it reach? - *Not evidenced.* It works in one domain's data. - **As shipped.** It works across several domains or systems. The voice agent connects to telephony and to the customer's contact-centre or CCaaS platform. [Source](https://www.visor.ai/voice-agent/) (documented) - **In this deployment.** It connects to external tools or services across a trust boundary. Generali connected the platform to its own systems through web services. [Source](https://www.visor.ai/success-stories/generali/) (documented) ### Does it work with other agents? - *Not evidenced.* Several agents coordinate inside the organisation. - *Not evidenced.* Agents operate across organisational boundaries or disparate stacks. - *Not evidenced.* There is a published protocol or communication layer between agents. - *Not evidenced.* Others build on it: third parties publish integrations, skills or agents for it. - *Not evidenced.* It exposes an agent interface: a published MCP server, an agent card, or an API documented for agents to call. ### 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. - **In this deployment.** The agent handles routine tasks; the person is consulted on exceptions. At Generali the chat agent handles conversations from start to finish; when a conversation needs a person, an advisor picks it up in live chat. [Source](https://www.visor.ai/success-stories/generali/) (documented) - *Not evidenced.* The agent works independently; the person approves critical decisions only. - *Not evidenced.* The agent has full autonomy within boundaries; the person monitors. ### Is what it is for written down? - **Available, if the operator turns it on.** Its purpose and permitted tasks are stated in writing. For healthcare, the agents' scope is administrative contact, written down before work starts. [Source](https://www.visor.ai/healthcare/) (documented) - *Not evidenced.* Its autonomy limits and the tools it may use are defined. - **As shipped.** Its limits and known failure cases are documented for those who use it. A reliability note states that the models can occasionally fail and that providers do not guarantee total availability. [Source](https://www.visor.ai/voice-agent/) (documented) ### Does it have its own identity and only the access it needs? - *Not evidenced.* What it can reach is enumerated: scopes, permissions, tools. - *Not evidenced.* Its authorisation is published as metadata that anyone can read. - *Not evidenced.* It asks for narrower access than the whole account. - *Not evidenced.* It has its own identity, separate from any person's. - *Not evidenced.* Its identity is cryptographic and can be checked by others. - *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? - *Not evidenced.* The organisation keeps a registry of its agents. - *Not evidenced.* Each agent has a named owner. - *Not evidenced.* Agents are retired by a defined process. ### Who is accountable for it? - *Not evidenced.* A named executive or body is accountable for the organisation's agents. - *Not evidenced.* Roles and responsibilities for AI risk are documented. ### Is there a policy that governs it? - *Not evidenced.* A governance policy for agents is published. - *Not evidenced.* Agents and use cases are classed by risk. - **As shipped.** The laws that apply to it are identified. Each agent runs twelve automatic checks against the EU AI Act and the GDPR, each citing its article. [Source](https://www.visor.ai/voice-agent/) (documented) - **Available, if the operator turns it on.** New agents pass an approval or review before they run. In Visor's deployment, the agent is tested end to end and validated by the customer's team in real conditions before launch. [Source](https://www.visor.ai/voice-agent/) (documented) ### Can a person step in or stop it? - *Not evidenced.* High-impact actions need a person's approval. - *Not evidenced.* There is a way to pause or stop it. - **As shipped.** There is a defined escalation path. A chat that needs a person moves to live chat and is routed to the right department with its history. [Source](https://www.visor.ai/chat-agent/) (documented) ### Is what it does logged? - *Not evidenced.* Its actions are logged. - *Not evidenced.* The log is tamper-evident and kept for a stated time. ### Is it watched while it runs? - *Not evidenced.* It is monitored in operation. - *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. - *Not evidenced.* A limit on it is a setting that its own account could change. - **Available, if the operator turns it on.** A limit on it is a rule in prose. For healthcare, the page states as a rule that the agents do not give clinical advice and are set up to pass a clinical question to a person. [Source](https://www.visor.ai/healthcare/) (documented) - *Not evidenced.* Policy is enforced as machine-readable rules. - *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? - *Not evidenced.* It tells the people it talks to that it is an AI. - *Not evidenced.* There is a channel to report problems with it or contest its output. - **As shipped.** It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent card. An llms.txt file resolves at the site root and indexes the product pages with markdown twins. [Source](https://www.visor.ai/llms.txt) (observed) ### What data does it use, and under what rules? - **As shipped.** The data it uses is described. The chat agent answers from a knowledge base built from the customer's documents and kept in sync with them. [Source](https://www.visor.ai/chat-agent/) (documented) - *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? - **As shipped.** The models and third-party components it uses are listed. The security page lists the AI providers in the voice and chat path (Azure, Vertex AI Gemini, Deepgram, AssemblyAI, ElevenLabs) and what each processes. [Source](https://www.visor.ai/security/) (documented) - *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. - **Available, if the operator turns it on.** The people who work with it are trained. In Visor's deployment, Visor trains the customer's people to run the platform. [Source](https://www.visor.ai/voice-agent/) (documented) - **In this deployment.** Its value is measured. The Visor success story states that Max started at 65% automation in 2021 and that the goal is 80% of questions and processes resolved without a person; only the 65% is a measured figure, and the page markup attributes the story to an archived copy of 2022-08-20. [Source](https://www.visor.ai/success-stories/millennium-bcp/) (documented) - **As shipped.** It is improved on a regular cycle. Nexa reads real conversations on a schedule, spots patterns and proposes fixes. [Source](https://www.visor.ai/voice-agent/) (documented) - *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 (`w4byv6dr`, published 2026-11-10). Anyone can read it with this key: `sgit_public_read_90a76763f617c725a429b7b445125e43a01bf7f880c08904b7803018bc65935b:w4byv6dr` With [sgit](https://sgit.ai/): `sgit clone sgit_public_read_90a76763f617c725a429b7b445125e43a01bf7f880c08904b7803018bc65935b:w4byv6dr`. The key reads; it cannot write. An operator who wants to add what only they hold forks the vault into a private one.