# Report: Noxus > GAMMA-Ray v0.0.155 (beta, for review; every rating is experimental). The GAMMA-Ray beta report on Noxus: Noxus AI Workers (AI Co-workers; 'Agents' in the documentation) A4 · R3 · C2 · O2; 70 provisions lit, 22 sources captured. > Page: https://gamma-ray.sgit.ai/reports/noxus/ · Source: data/reports/noxus.json GAMMA-Ray report · Spectrum 0.2 beta · Public tier · read 2026-11-10 · not reviewed by the company yet Noxus sells a platform on which companies build AI agents, which it calls AI Workers or Co-workers, and automated flows that carry out back-office processes in the companies' own systems. 1 solution carded of 6 found 22 sources captured and hashed 70 provisions lit in 8 of 8 instruments 4 examples of the agent at work, with sources Built only from Noxus's own public pages and, for company basics only, the news sources named beside each fact. Noxus has not seen this report. Nothing was tested and no credentials were used. If you are Noxus 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](../../spectrum/evidence-map/index.md); 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. ### Noxus AI Workers (AI Co-workers; 'Agents' in the documentation) Configurable agents that use flows, integration actions, knowledge bases, tables, MCP servers, code execution and a sandbox to carry out tasks, deployed through the web app, API, SDK, chat widget, Slack, Teams, Google Chat, WhatsApp or Telegram. Noxus AI Workers a product, as documented SPECTRUM 0.2 BETA · Public tier · 2026-11-10 A4 Autonomy Orchestrates with options on · as shipped A3 π Moderate · S1·R5·A1 ×3 R3 Reach Open protocol π Moderate · S1·R5·A1 ×3 C2 Control Configurable with options on · as shipped C1 π Moderate · S1·R5·A1 ×3 O2 Openness Documented π Moderate · S1·R5·A1 ×3 Draft Stage: Scaling (11 of 16) In production Open protocol Standout. Autonomy 4 (Orchestrates): "Create Google Drive Sharing Link or Delete OneDrive File" Next unlock. Control 3 (Observable): public evidence that it is monitored in operation would get there. Trust. FACT-Ray : 25 facts: 25 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. 70 provisions lit across 8 of 8 instruments. Salesforce EAAMM OWASP MCP AAGMM Microsoft NIST AI Act Evidence: 15 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](../../spectrum/cards/noxus-ai-workers/index.md) · [the governance layer](../../scans/noxus-ai-workers/index.md) ### Flows Visual node-based workflows with triggers, AI nodes and integration nodes. *No card yet (generally available): this solution has not been assessed.* ### Knowledge Bases and Tables Document stores with semantic search, and structured tables, that agents and flows query. *No card yet (generally available): this solution has not been assessed.* ### Case management and processes Processes whose cases are worked by flows and by people through tasks. *No card yet (turned on per organization): this solution has not been assessed.* ### Genie An assistant inside the platform that builds and changes flows, agents and tables, asking for approval before writes. *No card yet (beta, off until an administrator turns it on): this solution has not been assessed.* ### Noxus MCP server, Python SDK and REST API A hosted MCP server, SDK and REST API that let external clients and agents drive workflows, agents and conversations. *No card yet (generally available): this solution has not been assessed.* ## Our reading **The shape.** Noxus AI Workers read A4 · R3 · C2 · O2 (Scaling). A builder configures agents, which the documentation also calls co-workers, that use flows, integration actions, knowledge bases, tables and MCP servers to take actions themselves, and deploys them through the web app, the API, a chat widget or channels such as Slack, Teams and WhatsApp. Each agent reaches only the tools selected for it, an enumerated list. **Where the evidence is strongest.** Reach 3 holds as shipped: a hosted MCP server lets external clients and agents call Noxus agents, conversations and workflows, and an OpenAPI 3.1.0 description resolves. Logs record tool calls and reasoning steps, an agent's deployment on a channel can be deactivated through the API, and a public status page posts incidents. Customer stories on Noxus's own pages give the company's figures: at CUF an AI Worker processes over 3,000 patient communications a month and routes complex cases to staff, and LSIG reports 15,000 products a day classified across three retail brands. **Two levels hold with options on.** Autonomy 4 and Control 2 rest on the Human in the Loop tool or Require Approval, which are off until turned on; with them, the agent acts on its own and asks a person before critical actions. As shipped, actions run without asking, and the split between routine work and exceptions is shown at CUF, a deployment. **What would move it.** Autonomy is at the top of its ladder. Reach 4: agents working across organisations or stacks, with third parties publishing integrations or agents for Noxus. Control 3: a public record of agents' conduct being monitored while they run, such as an alert or a dated review. Openness 3: published evaluation results with a method; Genie evaluations are announced, and an OpenAPI description and a status page are in place. **Seen, and not counted.** The challenger lowered monitoring: Agent Insights analyses what users ask and how they feel, not what the agent does, and the Monitoring page covers infrastructure. A sandbox outside the agent that blocks internal network ranges is documented as an option; it cannot lift Control while level 3 is not yet evidenced. Certification claims differ between Noxus pages, and no certificate was read. ## What would move it The one piece of public evidence that would lift each card next: - **Noxus AI Workers (AI Co-workers; 'Agents' in the documentation)**: Control 3 (Observable). Public evidence that it is monitored in operation. ## 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. ### CUF (José de Mello Saúde) Patient messages categorised, routed and processed by an AI Worker; the page gives 3,000+ communications a month and complex cases routed to staff. "Complex cases are flagged and routed to human staff instantly" [Source](https://www.noxus.ai/case-studies/cuf-healthcare) (captured 2026-11-10T15:47Z, sha256 `278999c51d7a72d7`) ### LSIG (360hyper, KuantoKusta, Saibarato) Supplier product data classified and enriched by one AI Worker across three retail brands; the page gives 15,000+ products a day. "LSIG automated 15,000 daily SKUs across three retail brands" [Source](https://www.noxus.ai/case-studies/lsig-retail) (captured 2026-11-10T10:39Z, sha256 `e013db9a58df6cfd`) ### Sandock Austral Shipyards Tender documents assembled, stamped, signed and validated by a Noxus workflow. "cutting preparation time by 75%" [Source](https://www.noxus.ai/blog/sandock-austral-achieves-75-faster-tender-submissions-with-noxus-ai) (captured 2026-11-10T10:39Z, sha256 `438d25297dfa9617`) ### Kirchhoff Supplier documents processed into SAP after a Noxus workshop. "They were live in thirty days without touching their SAP core" [Source](https://www.noxus.ai/kirchhoff) (captured 2026-11-10T10:39Z, sha256 `99b43a7e9770915f`) ## The company - Observador reported a funding round of 1.5 million US dollars on 11 February 2025. "fechou uma ronda de investimento" [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) (captured 2026-11-10T10:39Z, sha256 `d802e15e98ed9188`) - Observador names the CEO and co-founder. "João Pedro Almeida, CEO e cofundador" [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) (captured 2026-11-10T10:39Z, sha256 `d802e15e98ed9188`) - Observador names four founders. "startup luso-britânica, fundada por João Pedro Almeida" [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) (captured 2026-11-10T10:39Z, sha256 `d802e15e98ed9188`) - Observador says the company is headquartered in the United Kingdom. "que está sediada no Reino Unido" [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) (captured 2026-11-10T10:39Z, sha256 `d802e15e98ed9188`) - The homepage title names the product AI Workers. "AI Workers for Complex Operations" [Source](https://www.noxus.ai/) (captured 2026-11-10T10:39Z, sha256 `b3d589bfcdbc84aa`) - The pricing page charges for work completed by AI Workers. "Pay for the work your AI Workers complete" [Source](https://www.noxus.ai/pricing) (captured 2026-11-10T10:39Z, sha256 `716e94a62ee89e6d`) - The developer documentation calls the same product agents, also named co-workers. "Agents (co-workers)" [Source](https://docs.noxus.ai/sdk/mcp/tools) (captured 2026-11-10T10:39Z, sha256 `bf2ad9c2bb60b44f`) ## The people Public and professional only, from the company's own pages or a public professional source. - **João Pedro Almeida**, CEO and co-founder. [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) - **Jorge Pessoa**, Co-founder. [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) - **Gonçalo Ferreira**, Co-founder. [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) - **Miguel Ribeiro**, Co-founder. [Source](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) ## 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 stories company solutions 15 sources 25 indicators 70 provisions, by instrument I03: Agents and flows are configured in a visual builder without code, and agents search knowledge bases built from the organisation's documents and data. I04: With the Code Execution tool turned on, the agent writes and runs code. I08: Agents use tools and run flows to take actions themselves. I10: The tools page states one agent can be given integration actions as tools, such as Send Email, Create Google Drive Sharing Link or Delete OneDrive File, alongside flows, knowledge bases and database connections. I11: An agent can be bound to external MCP servers and call their tools. I17: At CUF the AI Worker processes patient messages and routes complex cases to staff. I18: The tools page documents a Human in the Loop tool an agent owner may enable, under which the agent escalates to a person to get approval for critical actions; it does not say how any given agent is shipped. I20: The company states the agents' purpose: handling complaints, documents and tickets. I21: The builder selects which actions and flows each agent may call. I22: The tools page documents limits, such as web research being less reliable than knowledge bases. I23: Each agent's tools are an enumerated list chosen by the builder: the flows, actions, knowledge bases, database connections and MCP servers it may use. I25: Each agent reaches only the flows, actions, knowledge bases and database connections selected for it; its SQL is generated read-only and runs with that connection's privileges, and tables are read-only unless edits are allowed. I26: A Google Chat deployment can run under a service account bot identity separate from any person. I38: The Human in the Loop tool and Require Approval make the agent ask a person before actions run. I39: An agent's deployment on a channel can be deactivated through the API. I41: Logs record agent interactions including tool calls and reasoning steps, with run-level logs per run. I45: When the sandbox is on, a Syd sandbox outside the agent blocks internal network ranges and requires the sandboxes:run permission. I47: Instructions written in prose set allowed behaviour and restrict access. I54: A public status page posts incidents and offers incident update subscriptions. I57: With a Phoenix or Langfuse provider connected, users can rate agent responses up or down. I58: The tools page describes the data an agent can use: knowledge bases, connected databases queried read-only, and workspace tables. I61: The model providers and model families an agent can use are listed. S1: A named customer, CUF, reports patient communications processed by the AI Worker each month. S3: An OpenAPI 3.1.0 description of the backend API resolves; the docs llms.txt also resolves. S4: A hosted MCP server lets external clients and agents call Noxus agents, conversations and workflows as tools, authenticated with a workspace API key whose permissions gate the tools. Noxus João Pedro Almeida Jorge Pessoa Gonçalo Ferreira Miguel Ribeiro CUF (José de Mello Saúde) LSIG (360hyper, KuantoKusta, Saibarato) Sandock Austral Shipyards Kirchhoff Noxus AI Workers (AI Co-workers; 'Agents' in the documentation) Noxus AI Workers A4 · R3 · C2 · O2 Flows Flows Knowledge Bases and Tables Knowledge Bases and Tables Case management and processes Case management and processes Genie Genie Noxus MCP server, Python SDK and REST API MCP server, SDK and API docs.noxus.ai/core/what-is-noxus docs.noxus.ai/platform/agents/too… docs.noxus.ai/platform/agents/int… noxus.ai/case-studies/cuf-healthc… noxus.ai/aboutus docs.noxus.ai/platform/agents/dep… docs.noxus.ai/api-reference/v1--d… docs.noxus.ai/deployment/operatio… docs.noxus.ai/platform/agents/san… docs.noxus.ai/core/concepts/agents status.noxus.ai docs.noxus.ai/core/infrastructure… docs.noxus.ai/core/infrastructure… backend.noxus.ai/openapi.json docs.noxus.ai/sdk/mcp/overview It is configured on a low-code or no-code builder and acts on real organisational data I03 It generates and executes code with local or cloud privileges I04 It executes actions itself I08 It works across several domains or systems I10 It connects to external tools or services across a trust boundary I11 The agent handles routine tasks; the person is consulted on exceptions I17 The agent works independently; the person approves critical decisions only I18 Its purpose and permitted tasks are stated in writing I20 Its autonomy limits and the tools it may use are defined I21 Its limits and known failure cases are documented for those who use it I22 What it can reach is enumerated: scopes, permissions, tools I23 It asks for narrower access than the whole account I25 It has its own identity, separate from any person's I26 High-impact actions need a person's approval I38 There is a way to pause or stop it I39 Its actions are logged I41 A limit on it is enforced by something outside its own reach I45 A limit on it is a rule in prose I47 Incidents and errors are communicated to those affected I54 There is a channel to report problems with it or contest its output I57 The data it uses is described I58 The models and third-party components it uses are listed I61 It is in production: a public source names a customer or gives usage figures for what it does on its own S1 It is machine-readable for agents: it publishes an llms.txt, an AGENTS.md, an API description or an agent card S3 It exposes an agent interface: a published MCP server, an agent card, or an API documented for agents to call S4 Salesforce 14 EAAMM 3 OWASP 13 MCP authorization 6 AAGMM 6 Microsoft 8 NIST AI RMF 15 EU AI Act 5 OWASP, AT3 Citizen Developer Agent OWASP, AT4 Code Executing Agent Salesforce, Level 2: Simple Orchestration, Single Domain Salesforce, Level 1, how to advance from Level 1 to Level 2 Microsoft, 200: Repeatable, Business strategy Salesforce, Level 3: Complex Orchestration, Multiple Domain Salesforce, Level 2, how to advance from Level 2 to Level 3 Salesforce, Level 3, how to advance from Level 3 to Level 4 Microsoft, 400: Capable, Business strategy Microsoft, 200: Repeatable, Technology and data OWASP, AT6 Externally Extended Agent NIST AI RMF, GOVERN 6.1 NIST AI RMF, MAP 4.1 EAAMM, L3 Consultative (survey item Q9) EAAMM, L4 Supervisory (survey item Q9) NIST AI RMF, MAP 1.1 NIST AI RMF, MAP 2.1 NIST AI RMF, MAP 3.3 NIST AI RMF, MAP 1.3 EU AI Act, Article 13 OWASP, Maturity Level 1 Experimentation without Guardrails, key enterprise action NIST AI RMF, MAP 2.2 Microsoft, 300: Defined, Business strategy NIST AI RMF, MEASURE 2.5 MCP authorization, Authorization (draft) MCP authorization, Authorization (draft) AAGMM, GD-02 MCP authorization, Authorization (draft) Salesforce, Level 2, how to advance from Level 2 to Level 3 Salesforce, Level 3, how to advance from Level 3 to Level 4 MCP authorization, Authorization (draft) OWASP, Maturity Level 4 Adaptive, Self-Regulating Governance, key enterprise action OWASP, Maturity Level 2 Policy-Defined, Human-in-the-Loop, key enterprise action EU AI Act, Article 14 AAGMM, GD-06 NIST AI RMF, MAP 3.5 Salesforce, Level 3, how to advance from Level 3 to Level 4 OWASP, Maturity Level 3 Integrated, Continuous Oversight, key enterprise action NIST AI RMF, MANAGE 2.4 OWASP, Maturity Level 0 Unaware and Ad Hoc, key enterprise action OWASP, Maturity Level 1 Experimentation without Guardrails, key enterprise action EU AI Act, Article 12 AAGMM, GD-03 AAGMM, GD-08 OWASP, Maturity Level 3 Integrated, Continuous Oversight, key enterprise action AAGMM, GD-04 Microsoft, 200: Repeatable, AI governance and security Microsoft, 200: Repeatable, AI governance and security Microsoft, 500: Efficient, AI governance and security OWASP, Maturity Level 0 Unaware and Ad Hoc, key enterprise action NIST AI RMF, MANAGE 4.3 EU AI Act, Article 73 EU AI Act, Article 26 NIST AI RMF, MEASURE 3.3 NIST AI RMF, GOVERN 5.1 Salesforce, Level 1, how to advance from Level 1 to Level 2 Salesforce, Level 4, how to maximize value NIST AI RMF, GOVERN 5.2 AAGMM, GD-05 EAAMM, Readiness dimension 2 Salesforce, Level 0, how companies can advance from Level 0 to Level 1 Salesforce, Level 1, how to advance from Level 1 to Level 2 OWASP, Maturity Level 2 Policy-Defined, Human-in-the-Loop, key enterprise action NIST AI RMF, MAP 1.4 Microsoft, 400: Capable, Business strategy Salesforce, Level 0, how companies can advance from Level 0 to Level 1 MCP authorization, Authorization (draft) MCP authorization, Authorization (draft) OWASP, Maturity Level 1 Experimentation without Guardrails, key enterprise action Salesforce, Level 3, how to advance from Level 3 to Level 4 ## The evidence | Source | Read | SHA-256 (first 16) | |---|---|---| | [backend.noxus.ai/openapi.json](https://backend.noxus.ai/openapi.json) | 2026-11-10T15:47Z | `acf57bee22546b3a` | | [docs.noxus.ai/api-reference/v1--deployments/deactivate-deployment](https://docs.noxus.ai/api-reference/v1--deployments/deactivate-deployment) | 2026-11-10T15:47Z | `ed6ad19208950bde` | | [docs.noxus.ai/core/concepts/agents](https://docs.noxus.ai/core/concepts/agents) | 2026-11-10T15:47Z | `274757353a8ab71b` | | [docs.noxus.ai/core/infrastructure/models-providers](https://docs.noxus.ai/core/infrastructure/models-providers) | 2026-11-10T15:47Z | `d0fe4689f42a1a5b` | | [docs.noxus.ai/core/infrastructure/observability-providers](https://docs.noxus.ai/core/infrastructure/observability-providers) | 2026-11-10T15:47Z | `93a416e3707f51cb` | | [docs.noxus.ai/core/what-is-noxus](https://docs.noxus.ai/core/what-is-noxus) | 2026-11-10T15:47Z | `fa50eddb7ba2d529` | | [docs.noxus.ai/deployment/operations/logging](https://docs.noxus.ai/deployment/operations/logging) | 2026-11-10T15:47Z | `6170b7205da6babb` | | [docs.noxus.ai/platform/agents/deployments/google-chat](https://docs.noxus.ai/platform/agents/deployments/google-chat) | 2026-11-10T15:47Z | `450076f7f0a12e45` | | [docs.noxus.ai/platform/agents/introduction](https://docs.noxus.ai/platform/agents/introduction) | 2026-11-10T15:47Z | `a775465cbeab0371` | | [docs.noxus.ai/platform/agents/sandbox](https://docs.noxus.ai/platform/agents/sandbox) | 2026-11-10T15:47Z | `6b0d907e6d65015c` | | [docs.noxus.ai/platform/agents/tools](https://docs.noxus.ai/platform/agents/tools) | 2026-11-10T15:47Z | `107a0dcbda489616` | | [docs.noxus.ai/sdk/mcp/overview](https://docs.noxus.ai/sdk/mcp/overview) | 2026-11-10T15:47Z | `554ecd31cdfb2baf` | | [docs.noxus.ai/sdk/mcp/tools](https://docs.noxus.ai/sdk/mcp/tools) | 2026-11-10T10:39Z | `bf2ad9c2bb60b44f` | | [observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-mil](https://observador.pt/2025/02/11/noxus-startup-com-adn-portugues-recebe-15-milhoes-para-ajudar-empresas-a-criar-colaboradores-de-ia/) | 2026-11-10T10:39Z | `d802e15e98ed9188` | | [status.noxus.ai/](https://status.noxus.ai/) | 2026-11-10T15:47Z | `f2d62204052945e4` | | [www.noxus.ai/](https://www.noxus.ai/) | 2026-11-10T10:39Z | `b3d589bfcdbc84aa` | | [www.noxus.ai/aboutus](https://www.noxus.ai/aboutus) | 2026-11-10T15:47Z | `0109bcdc540a1a13` | | [www.noxus.ai/blog/sandock-austral-achieves-75-faster-tender-submission](https://www.noxus.ai/blog/sandock-austral-achieves-75-faster-tender-submissions-with-noxus-ai) | 2026-11-10T10:39Z | `438d25297dfa9617` | | [www.noxus.ai/case-studies/cuf-healthcare](https://www.noxus.ai/case-studies/cuf-healthcare) | 2026-11-10T15:47Z | `278999c51d7a72d7` | | [www.noxus.ai/case-studies/lsig-retail](https://www.noxus.ai/case-studies/lsig-retail) | 2026-11-10T10:39Z | `e013db9a58df6cfd` | | [www.noxus.ai/kirchhoff](https://www.noxus.ai/kirchhoff) | 2026-11-10T10:39Z | `99b43a7e9770915f` | | [www.noxus.ai/pricing](https://www.noxus.ai/pricing) | 2026-11-10T10:39Z | `716e94a62ee89e6d` | ## 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](../../spectrum/pipeline/index.md) 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); Noxus AI Workers (AI Co-workers; 'Agents' in the documentation): reviewed in 2 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. | Role | Who | |---|---| | researcher-assessor | a sub-agent of gamma.studio@web-summit.dinis | | challenger | a sub-agent | | scorer | build/spectrum.mjs | | analyst, designer, writer | gamma.studio@web-summit.dinis | | review | gamma.review@web-summit.dinis, 2 rounds | | sign-off | gamma.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 (`6n9a4tow`). Read key: sgit_public_read_eafc52a9cbd090f15069febc32ea08d2630b1aa8410e8b8bc4cc5f4b3f197e98:6n9a4tow With [sgit](https://sgit.ai/): `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 [Noxus AI Workers on the GAMMA-Ray Spectrum: A4 · R3 · C2 · O2](article.md), written from this report for PrompTugal.news.