Ethereum Could Become Easier to Use for AI Agents and Humans Alike via Proposed Standard
番茄鱼塘
04-07 22:01
Ai Focus
Biconomy introduced Ethereum standard ERC-8211 for smart batching, allowing multiple blockchain operations to execute together in DeFi. This system resolves transaction values in real time, addressing the challenge of unknown outputs in transactions.
Helpful
No.Help

A new Ethereum proposal aims to make it easier for AI agents and applications to execute complex decentralized finance transactions in a single step, rather than several separate actions.

The proposed Ethereum standard ERC-8211 was introduced on Tuesday by Biconomy, a blockchain infrastructure company that builds developer tools for decentralized applications. The system, called smart batching, allows several blockchain operations to execute together while resolving transaction values in real time.

According to Biconomy, ERC-8211 addresses a common problem in DeFi. Many blockchain transactions depend on outputs that cannot be known in advance. When someone swaps one token for another, the final amount received can change because of price movement or trading fees.

“When you have an output from something like a swap, you don’t know how much that will be,” Biconomy co-founder Ahmed Al-Balaghi told Decrypt. “Developers have to either hard code that or find another way for that output to be used as an input for something else, like a deposit.”

ERC-8211 works by allowing each step in a transaction to reference the result of the previous one, instead of relying on fixed numbers written when the transaction is signed. In current Ethereum batch systems, transaction parameters are locked before execution begins.

Al-Balaghi emphasized that ERC-8211 is not an Ethereum Improvement Proposal (EIP), but a standard that developers can implement directly on the network. ERCs, or Ethereum Requests for Comment, define technical rules for how applications, tokens, and other features operate on Ethereum without requiring changes to the core protocol.

“EIPs are still somewhat harder on Ethereum, just because that does needs more stakeholders. That's why ERCs exist, because they don't need a protocol change,” he said. “If an ERC happens to get a lot of success in terms of adoption and awareness, then either it just stays as an ERC, or it could even be included in the protocol itself.”

According to Biconomy, with smart batching, each step resolves its value at execution time and must meet predefined conditions before continuing. An agent could withdraw funds from a lending protocol, swap the exact amount received, and deposit the result into another protocol within one signed transaction. This same functionality, Al-Balaghi said, also includes controls that can restrict what an agent is allowed to do.

Al-Balaghi said the system runs on existing Ethereum infrastructure and compatible networks, and does not require a change to the core protocol or a hard fork, creating a new chain.

“What we’ve built lets developers just say: Whatever the balance is of the user, just compose that with the next action. And it’s done,” Al-Balaghi added. “That means you can create these really powerful flows without writing new smart contracts. You can just do it in TypeScript.”

Barnabé Monnot, a research scientist with the Ethereum Foundation, said the proposal aligns with the organization’s effort to improve blockchain usability.

“The protocol cluster of the Ethereum Foundation has ‘Improve UX’ as one of its strategic priorities,” Monnot told Decrypt. “ERC-8211 support is coming from this strategic priority.”

Monnot said the collaboration began during a workshop in 2025 organized by the Foundation’s Improve UX initiative.

“The agentic execution angle is new, but has imposed itself given the rapid developments of agents over the last three months,” Monnot said. “It's a perfect use case since agents can orchestrate complex cross-chain interactions, and ERC-8211 gives them the right platform to do so.”

According to Al-Balaghi, the Ethereum Foundation chose to collaborate on the effort because it had not explored this area in its own work, and recognized it could not address every challenge alone. That makes partnerships with teams like Biconomy a way to build the technology while moving more quickly than it could alone, and reflects a richer depth of interaction with the builder community following a series of Foundation changes made last year.

“I think the Ethereum Foundation, and this is from what I've seen personally by working with them—they're way more willing to win,” he said. “Seeing that level of interactivity, that more competitive nature, wanting things to get done quicker, and being willing to work with the ecosystem is very promising compared to what it was just two years ago.”

Tip
$0
Like
0
Save
0
Views 590
CoinMeta reminds readers to view blockchain rationally, stay aware of risks, and beware of virtual token issuance and speculation. All content on this site represents market information or related viewpoints only and does not constitute any form of investment advice. If you find sensitive content, please click“Report”,and we will handle it promptly。
Submit
Comment 0
Hot
Latest
No comments yet. Be the first!
Related
Cognition argues that AI-programmed agents should not replace humans.
Cognition CEO Scott Wu stated that AI programming agents should assist rather than replace programmers, and Devin is currently closer to the level of a junior to mid-level engineer.
TechCrunch
·2026-05-30 00:27:00
714
Billions Network claims AI agents are impacting advertising models.
Billions Network states that AI agents are undermining traditional web advertising models and driving up demand for on-chain traceability infrastructure.
CoinDesk
·2026-06-03 14:56:03
113
Anthropic CEO Discusses Frequent AI Use: Value Will Gradually Emerge
Anthropic President Daniela Amodei stated that high-frequency use of AI by enterprises is still in its early stages, and model capabilities and application scenarios will continue to expand in the coming years.
Business Insider
·2026-06-05 02:47:38
237
Companies like Meta are increasing their use of AI to track employees.
Companies like Meta, JPMorgan Chase, and KPMG are increasing their efforts to track employee AI usage, practices that have sparked controversy over costs, performance, and privacy.
Business Insider
·2026-06-04 00:07:08
564
Foreign media: Large-scale deployment of AI agents is accumulating security risks.
CertiK claims that AI agents' rapid access to local files, credentials, and financial instruments is creating new security vulnerabilities, and automated scams targeting AI systems are also emerging on the blockchain.
CoinDesk
·2026-05-29 23:48:19
231