{"id":14647,"date":"2026-10-21T23:43:38","date_gmt":"2026-10-21T21:43:38","guid":{"rendered":"https:\/\/say-digital.io\/blog\/ai-agents-right-to-act-super-apps-hermes-agent\/"},"modified":"2026-10-21T23:43:50","modified_gmt":"2026-10-21T21:43:50","slug":"ai-agents-right-to-act-super-apps-hermes-agent","status":"publish","type":"post","link":"https:\/\/say-digital.io\/blog\/ai-agents-right-to-act-super-apps-hermes-agent\/?lang=en","title":{"rendered":"AI agents: who controls the right to act, from super-apps to Hermes Agent?"},"content":{"rendered":"
\n

AI agents: who controls the right to act, from super-apps to Hermes Agent?<\/h1>\n

\u201cChange this order and let the customer know.\u201d A short request hides several separate permissions. An agent needs to locate the order, check who can change it, consult stock or fulfilment information and obtain permission to send a message. A better model may understand the request perfectly without having any of those rights.<\/p>\n

An AI agent\u2019s right to act is the set of operations a business and its service providers actually authorise it to perform.<\/strong> That authority depends on identity, software connections, permissions and required approvals. Model capability matters, but it cannot replace the chain of authorisation.<\/p>\n

The contrast between Chinese super-apps and more fragmented US services helps explain where that authority sits. It also makes the case for Hermes Agent, the open-source framework from Nous Research<\/strong>: an execution layer a business can organise around its own tools, without confusing technical independence with unrestricted access.<\/p>\n

Integrated platforms and separate tools create different obstacles<\/h2>\n

In a fragmented customer journey, commerce, payments, messaging and identity may belong to different services. Moving between them requires connections, access rules and checks. Joining those steps creates integration work and a market for infrastructure that agents can use.<\/p>\n

A super-app brings several functions into one environment. That can simplify the journey for users and approved partners. Yet the platform still decides which third parties may use each function. An integrated journey is not necessarily an open one.<\/strong><\/p>\n

This is an architectural comparison, not a complete description of two countries. The United States also has integrated platforms; China has several ecosystems and business agents. The distinction cannot support a prediction that agents will succeed in one country and fail in the other.<\/p>\n

The APIs exist. Access conditions are the real issue.<\/h2>\n

It would be wrong to say that super-apps have no APIs. Official Weixin Mini Program documentation describes both authentication through wx.login<\/a> and payments through wx.requestPayment<\/a>. An API is a software interface through which an application can use a function. Its existence does not authorise any agent to use that function on any account.<\/p>\n

The infrastructure work crosses the supposed geographical divide. On 30 April 2025, Visa announced Intelligent Commerce<\/a>, extending its infrastructure and standards towards agent-led commerce. On 11 September 2026, Ant International announced the rollout of its Agentic Mobile Protocol<\/a> with wallets and super-apps, naming Alipay China among its first-phase wallet partners.<\/p>\n

These vendor announcements describe a direction and a phased rollout, not universally available autonomous payments. They show that agent access is being developed inside integrated ecosystems too. For a buyer, the useful question is specific: which services can this agent access, on whose behalf and under what safeguards?<\/p>\n

A universal consumer agent and a business agent face different constraints<\/h2>\n

A consumer assistant expected to move freely between applications depends on many platforms whose rules it does not control. A business agent can have a much narrower remit: orders, CRM records and documents that one company is entitled to make available.<\/p>\n

That difference changes what is feasible. A small business need not wait for an agent that can do everything on the internet before testing case reconciliation or response preparation. It does need to establish that its software supports the required operations and that it has the authority to delegate them.<\/p>\n

An independent execution layer can coordinate several tools without moving the entire business into one super-app. Each connection still operates within the relevant service\u2019s permissions.<\/p>\n

What Hermes Agent adds to that architecture<\/h2>\n

As its official documentation<\/a> explains, Hermes Agent is an agent framework built by Nous Research, not an AI model. It manages a working loop: receive a task, supply context to the model, call available tools, inspect their results and continue or stop.<\/p>\n

Several documented capabilities matter when assessing it for business use:<\/p>\n