The World Cup offers a concrete setting for observing how crypto wallets are changing. Topics that football fans discuss every day, such as whether a team will qualify or how championship odds are moving, become tradable and priceable behavior in prediction markets such as Polymarket. When mainstream Web3 wallets integrate World Cup prediction activities, the activity can be read over a longer timeline as a lightweight starting point for users entering on-chain interaction.
In this World Cup-related exploration, imToken has started placing AI Agents into practical usage scenarios. Its web-based agent and Discord agent are designed around specific prediction needs, helping users complete betting transactions in a more natural way. Users are no longer limited to operating only inside the wallet app. They can participate in prediction markets through Discord or web pages, while being guided by the Agent back into the on-chain process.
From a signing gateway to an interpreter of intent
Over the past decade, the core problems solved by wallets have been clear: where assets are stored, who controls the private key, and who signs the transaction. A user opening imToken has typically done so to check balances, transfer assets, interact on-chain or manage multi-chain holdings. In that phase, the wallet functioned mainly as an asset gateway and a signing gateway. The user already knew what he or she wanted to do, and the wallet was responsible for completing the final step.
The shift in the agentic era is that users do not necessarily know at the beginning what they should click. In the World Cup setting, an ordinary user may not start with the thought: “I need to open Polymarket, find a specific market, evaluate the odds, and complete the trade.” The more natural questions are: “What is interesting about tonight’s match?” “I think Portugal will qualify; is there a related market?” “Is this price already too low?” “If I only want to participate with a small amount, what is the process?”
In the past, these questions were scattered across WeChat groups, social platforms or search engines. Each user had to assemble the information personally and then carry out the steps one by one. Once an Agent is introduced, the interaction changes. The user only needs to express a broad intent; the Agent helps break down the path; the wallet then turns that path into a series of on-chain actions. This is not simply adding a chat box to a wallet. The real change is that the wallet begins to move from being a menu of functions to becoming an interpreter of intent.
Earlier wallets mainly asked the user to decide whether to transfer, swap, stake or connect to a DApp. The next wallet form is more direct: the user can explain in natural language what they want to accomplish. World Cup prediction fits this transition because the event already contains context, gives users a reason to speak, and requires judgment. The Agent does not need to begin by managing a complex asset portfolio. It can first help a user find the interaction path in one specific scenario, while returning final control to the wallet and the user.
World Cup prediction brings the wallet into web and community spaces
The web-based and Discord agents mentioned in relation to imToken are examples of wallet capability being brought into lighter entry points. A user does not always have to open the app first or enter a traditional DApp browser first. Instead, the user can be on an activity page, in a World Cup scenario, or inside a community environment, and find the on-chain interaction path through an Agent.
This means the boundaries of the wallet are extending outward. In the earlier model, the wallet entry point was comparatively clear: open the app, enter the asset page, click a function, and connect to a DApp. In the next model, wallet entry points can be distributed across more places, including web pages, Discord, Telegram, AI chat boxes, activity pages, developer tools, or even a lightweight wallet interface generated by a user. From this perspective, the key point is not World Cup prediction itself, but the fact that it allows the wallet to stand more naturally in front of user intent.
Mastercard and WeChat Pay offer payment references
If viewed only from inside crypto, the agentic wallet can easily be treated as another narrative in which AI helps users read markets, find opportunities and trade. Mastercard’s launch of Agent Pay for Machines on June 10 moved the topic beyond Web3 alone. Mastercard defines Agent Pay as enabling trusted AI Agents to participate in payments under user authorization. The design covers how the Agent is identified, how it is authorized, how it is verified inside the payment network, and how merchants, issuers and users know that the transaction was assisted by an Agent.
This is highly similar to the problem faced by Web3 wallets. When AI only helps write copy, the cost of an error is usually manageable. Once AI begins participating in asset interaction, the questions change: does it actually have permission, has it understood the user’s intent correctly, is the service it calls trustworthy, has the transaction it initiated exceeded its boundaries, and who is responsible if the result does not match the user’s expectation? Mastercard’s answer is to redesign the identity, token, authorization, risk control and dispute handling of trusted Agents inside the payment network.
Domestic payment companies are also moving in the same direction. WeChat Pay is testing AI payment functions together with Tencent’s agent product WorkBuddy, including the launch of an “AI exclusive card” inside WeChat Wallet. Disclosed information shows that the core of such products is not to allow AI to spend freely, but to set boundaries for agent payment through recharge limits, payment authorization scope and password verification. This follows the same logic as Mastercard Agent Pay: AI can participate in payment, but it must be identified, authorized, restricted and audited.
For on-chain wallets, the key is boundaries
Web3 wallets face the on-chain version of the same problem. Traditional payment systems place more emphasis on networks, merchants, issuers and compliance responsibilities, while on-chain wallets place more emphasis on private keys, signatures, authorization, contract calls and user self-custody. In traditional payments, users can rely on banks, card networks, merchants, dispute handling and risk-control systems. In the on-chain world, once a transaction is on-chain, there is often no undo button.
The greater the efficiency brought by AI Agents, the more important the wallet becomes as the final security boundary. A future wallet should not merely allow an Agent to do things; it must ensure that the Agent can only act within the scope permitted by the user. This is why Web3 is well suited for discussing agentic wallets. Many discussions about AI Agents quickly move toward extreme automation: AI automatically trading, managing assets, finding airdrops or arbitraging for the user. That direction is attractive, but the hard problem for wallets is not automation itself. The hard problem is the sense of boundary.
A wallet is not an ordinary app. If AI recommends the wrong song, writes the wrong paragraph or clicks the wrong page in a normal application, the result is usually an experience issue. In a wallet, if AI misunderstands one instruction, calls the wrong contract or grants excessive authorization, the result can become a real asset risk. The first-principles question for the agentic wallet is therefore not “how much can AI do for the user,” but “how does the user know what AI is doing?”
This is also why imToken has continued to emphasize control over the years. From self-custody wallets to multi-chain asset management, and then to today’s AI co-creation and Agent exploration, the continuous thread is not that there are more and more functions. It is that users must still be able to understand, confirm and control their digital world. In the agentic era, this thread becomes more specific. The wallet needs to show who the Agent is, what capabilities it can call, how long authorization lasts, whether it can operate across DApps, when the user must confirm again, and whether the user can pause or revoke it with one action.
These questions may sound detailed, but they are the foundation for an agentic wallet to stand up. The strength of an AI Agent comes from its ability to simplify complex processes. A user can say one sentence, and the Agent can break it into a path of more than ten steps. That is positive for user experience, but it is also a challenge for security. The longer the path and the more links in the middle, the more the wallet needs to bring the key nodes back in front of the user. The World Cup prediction activity is an event entry point, while imToken’s web-based Agent and Discord Agent are community entry points. Together, they show how the agentic wallet is beginning from small, specific scenarios.