What does the next milestone of DeFi need? - ChainCatcher

Original Title: Decentralized Finance's next milestone: What it'll take for agentic finance to work

Original Author: @Lemniscap

Original text compiled by: Ismay, BlockBeats

Editor’s note: When the world of Decentralized Finance becomes so complex that even professional users find it difficult to grasp, how can we hand the power back to ordinary people?

This article is from a research paper by Lemniscap, systematically outlining the rise of "smart agent finance" and its real-world dilemmas. From &milo, Meridian to SendAI, The Hive, these early products demonstrate how AI can become a new interface for on-chain interactions, while exposing significant gaps in execution reliability, permission security, and verification mechanisms. The author points out that for DeFi to move to the next stage, the key lies not in smarter models, but in more trustworthy underlying structures—making every action of the agent verifiable, traceable, and trustworthy.

This is not only a turning point in the evolution of technology, but also an experiment in the reconstruction of trust. As mentioned in the text: the next milestone of Decentralized Finance is not greater scale, but trust in automation.

By 2025, DeFi will be completely different from its early form.

The data itself speaks volumes: institutional capital inflows exceeded $10 billion in a single quarter, with the number of active protocols across dozens of chains surpassing 3,000. The total locked value of DeFi protocols across the network is expected to reach $160 billion by 2025, a year-on-year increase of 41%; the cumulative trading volume of DEX and Perps is measured in "trillions."

As the scale of Decentralized Finance expands, the possibilities increase, but the complexity also rises sharply. Most people simply cannot keep up with everything happening on-chain. If we want more people to seize these new opportunities, we must build tools that enable users to make the right decisions more easily - and this is precisely the direction of future development.

At the same time, AI has gradually integrated into daily life, and people are starting to develop new habits around automation. This trend has given rise to "Agentic Finance" - the navigation and execution of financial operations handled by intelligent agents.

Even simple browser-based proxies like Comet demonstrate the rapid evolution of such tools. When you execute a DeFi operation through a browser proxy (as exemplified by SendAI founder Yash), you can see the potential of intelligent agent finance.

This vision is actually quite intuitive: you no longer need to search through various dashboards or long posts on X; just tell the AI what goal you want to achieve, and it can automatically help you complete the subsequent steps.

Currently, two types of intelligent agents are emerging:

One type is Copilots, which guide users in making decisions throughout the DeFi world; the other type is Quant Agents, which are more focused on professional automated strategy execution, equivalent to "Autopilots."

Both are still in their early stages and have their flaws, but they point to a new direction together—a fundamentally different AI-driven Decentralized Finance interaction.

as a "co-pilot" intelligent agent

You can think of these smart agents as your personal assistants. You no longer need to browse charts or jump between different protocols; just ask questions in natural language, such as: "What are the hottest tokens right now?" or "Where are the highest yields?" The agent can respond directly and provide the next steps—just like a knowledgeable friend who is always at your beck and call.

Taking &milo as an example, its co-pilot mode can assist you in making investment decisions, rebalancing assets, and gaining insights into your portfolio—allowing you to maintain control while saving you from cumbersome operations.

With natural language explanations and smart prompts, &milo can help users understand positions and compare yield opportunities without having to sift through data across various dashboards. It showcases the evolution of co-pilot agents from simple chat assistants to a fully functional Decentralized Finance guide.

To observe the performance of these agents in actual operations, we tried out several newly released products and personally experienced their ability to handle real Decentralized Finance tasks.

The results show that these agents still have limitations. For example, they can successfully identify popular tokens, but cannot smoothly execute buy operations; there were also two failed transactions, with the system prompting "insufficient balance," even though there was actually enough SOL in the account to cover the fees.

Similar platforms like The Hive have taken a different path - it combines multiple DeFi agents into a "hive," capable of collaboratively completing complex tasks such as cross-chain operations, yield strategies, and liquidation defense, all coordinated through a simple chat interface. This network composed of dedicated agents can complete multi-step on-chain operations using natural language commands.

We tested the same buy order with The Hive. The system did recognize the popular token WEED, but it returned an incorrect contract address when executing the purchase.

Overall, Milo demonstrated how to integrate portfolio management tools into a seamless process, while The Hive is exploring how to enable multiple specialized agents to work together. As the capabilities of smart agents improve, more distinct divisions of labor are beginning to emerge.

For example, Meridian focuses on the other end of the user spectrum - helping beginners take their first steps into Decentralized Finance. It adopts a mobile-first design, combined with clear prompts, making basic operations such as swapping tokens, staking, or checking returns easier to get started.

Meridian performs smoothly and executes quickly on these core tasks, and more importantly, it is very clear about its own boundaries. When users ask it to perform operations beyond its scope, it explains the reasons instead of blindly attempting—this "honesty" makes it a reliable starting point for newcomers exploring the on-chain world.

Meridian founder Benedict explained:

"Meridian allows users to conduct secure research and operations using natural language. We have made the proxy research feature available to the public for free at meridian.app. Users who register for the Meridian mobile app can utilize the proxy's swap, multi-swap, and portfolio purchase functions. Currently, accounts are still in a closed testing phase, and interested users can contact @bqbrady on Twitter to apply for an experience."

Through our testing, we found that most AI agents focused on DeFi navigation are still largely in the role of "teachers" or "assistants," primarily helping users complete the most basic operations (such as exchanging tokens).

Further improvements are still needed to enable them to reliably handle more complex processes—such as providing liquidity, managing leveraged positions, and so on.

As pointed out by Rishin Sharma, head of AI at the Solana Foundation:

"Large language models (LLMs) are prone to hallucinations when handling broad tasks and struggle to perform deterministic operations. A function call mechanism like MCP may be better suited for translating 'action plans' into actual execution. While LLMs perform well at the conceptual and guidance level, they still fall short in precise execution. To make intelligent financial agents truly reliable, we must go beyond LLMs and develop specific function call mechanisms, clear execution strategies, verifiability, and secure permission systems. In other words, today's intelligent agent execution layer is still underdeveloped—AI's 'brain' is smart enough, but it still lacks a 'body' capable of robust action."

as an "autonomous driving" intelligent agent

If the "co-pilot type" of agency is more like a mentor, then the "quantitative type" of agency is more like an autonomous driving system. They not only can build strategies but also truly execute them—monitoring the market in real-time, testing trades, and automatically acting at machine speed, allowing complex Decentralized Finance strategies to enter "fully automated operation" mode.

A typical case that is taking shape comes from SendAI. It is not a quantitative agent itself, but a toolkit that enables others to create these agents. Its "Agent Kit" designed for Solana supports over 60 autonomous operations, including token swaps, new asset issuance, lending management, and can interact directly with mainstream protocols such as Jupiter, Metaplex, and Raydium.

In other words, it provides developers with a "track system" that allows them to directly execute decision models on-chain.

The founder of SendAI, Yash, clearly summarized their vision:

"We believe that every AI agent will have its own wallet in the future. SendAI is building the tools and economic layer necessary for this system, allowing these agents to perform any operation on Solana. We are creating a platform that enables these agents to have contextual awareness and supports long-running, persistent, and asynchronous execution of complex tasks."

At the same time, other teams are trying to make this capability more accessible. Lomen is responsible for selecting strategies and enabling users to "deploy with one click," lowering the barrier to enjoy quantitative automation without the need to write code.

For "advanced players" who prefer a more customized system, Unblinked offers an AI-driven strategy experiment environment. It's like Cursor in the trading realm: users can first outline their strategy ideas, run and optimize them in a secure sandbox environment, and then decide whether to invest real money.

Some platforms also choose to call multiple agents to collaborate and complete tasks.

For example, Almanak combines "programming agents" with "backtesting agents": users describe strategies in natural language, and the AI automatically generates production-level code, conducting over 10,000 Monte Carlo simulations for backtesting, ultimately producing a "ready-to-use" strategy result.

Finally, the team has also focused on real-time market advantages.

The ARMA agent of Giza actively reallocates funds among various lending protocols to maximize stablecoin yields. Instead of letting funds remain in a single pool, ARMA continuously monitors interest rates, liquidity, and Gas costs, dynamically moving assets. Its flagship agent has managed over 17 million dollars in funds, claiming a yield 83% higher than static holdings.

Overall, these quantitative agents significantly reduce time costs and allow ordinary users to access complex strategies that were originally reserved for professional quantitative teams. However, at the same time, they also reveal the vulnerabilities of automation: when there are data delays, protocol pauses, or severe market fluctuations, the agents may still "stumble."

In other words, they can indeed make you faster, but they are far from being "invincible."

Their dilemma lies in

After spending some time with the current smart agents, you will notice some similar issues: sometimes they suggest executing operations that no longer exist, such as a liquidity pool that has already been closed; the data they rely on often lags behind the real on-chain state; if there is an error midway through a multi-step plan, they do not self-correct but instead repeatedly attempt the same action.

Permission management is also quite cumbersome - either users must grant full access to the entire wallet, or they have to manually approve every minor operation. The testing phase is similarly superficial, as the simulated environment struggles to accurately replicate real-world chaos such as sudden changes in on-chain liquidity or adjustments to governance parameters.

One of the most serious problems is that these agents operate almost like a "black box."

Users cannot know what inputs it read, how it weighed options, whether it checked the real-time status, nor can they understand why a specific transaction was chosen to be executed. Without signed verification of operation records, it is impossible to verify the consistency between the "promised outcome" and the "actual execution."

Users can only "watch over" the automation process while using it — not only is this inefficient, but it also makes performance difficult to assess.

If there is no mechanism to verify decisions and prove that actions truly adhere to established strategies, users will never be able to distinguish between a "reliable system" and "well-packaged marketing."

For larger-scale capital, DeFi platforms must shift from "trust us" to "please verify." This is also a key turning point in establishing a "verifiable, governable, and trustworthy" smart agent financial infrastructure.

infrastructure gap

The core issue is that the current system lacks the foundational tools that allow agents to remain trustworthy, consistent, and secure in large-scale scenarios. To address this, we need infrastructure that can verify agent behavior, confirm execution results, and adhere to unified rules across all environments. Only then will people feel secure in entrusting their hard-earned money to them.

However, most users actually do not care about the "thought process" of the agent; they just want to confirm that the output is correct, verified, and within safe boundaries. In building trust, "verifiable reliability" is more important than "visibility."

This is exactly the meaning of "Verifiable Reliability." Agents do not need to record every internal operation, but should operate under clear strategies and reasonable checks: setting spending limits, execution time windows, confirmation nodes before key operations, etc.

At the core, these rules can be ensured through Trusted Execution Environments (TEE) or similar systems—without exposing all the details, yet able to prove that the agents indeed adhere to the boundaries. The result is: auditable outputs when needed, and operations that ordinary users can trust immediately.

This verification layer does not have to be a "one-size-fits-all" solution. Lightweight security measures and standardized metrics can be adopted for everyday scenarios, while higher-risk or institutional-level situations may require stronger proof and formal verification. The key is that each layer of infrastructure should provide measurable reliability that matches its risk level.

Prepare the protocol for the agent.

The next step to be added is to make the protocol "agent-friendly".

Currently, most DeFi protocols are not designed for smart agents. They need to provide more stable and secure execution interfaces: allowing for operation previews, secure retries, and execution based on consistent data structures. Permission design should also be "scope-limited" rather than "fully open," allowing agents to operate within clear boundaries rather than controlling the entire wallet.

In the absence of these foundational elements, even the smartest agent frameworks can be tripped up by weak underlying structures. Once these foundations are improved, users will no longer need to manually monitor automated processes; development teams can reduce debugging time and focus on innovation; and the execution results from different service providers can be comparable due to shared benchmarks—no longer just promotional slogans.

The part that must be changed

The solution is actually not complicated: make the agent provable and prepare the protocol for the agent. Add a policy layer between the agent and the wallet, and require that all execution processes are traceable and verifiable, rather than operating as a "black box."

For example, the SVM engine of Termina is built on this concept—it provides a true Solana runtime environment for AI agents, allowing them to model, make decisions, and learn based on on-chain data. At the same time, the protocol parties should open up operation interfaces that allow for "dry-run" operations, clear error codes, safe retry mechanisms, consistency of core data structures (positions, fees, health), and session-based permission control.

When these features are implemented, users will be able to free themselves from the burden of "custodial" agents; teams can reduce system failures; institutional investors will finally be able to obtain the security safeguards and verifiable proof they need.

Real-time schedule

In the next six months, the "co-pilot" agents are expected to improve the fastest. More refined data pipelines will enhance their reliability in everyday use cases.

Within a year, as testing standards improve, agents will be able to coordinate execution across protocols, with humans only needing to approve critical steps. In the longer term, as the infrastructure matures, smart agents may gradually blur into the default interaction layer of Decentralized Finance—no longer separate "tools," but becoming the primary way people interact with financial systems in their daily lives.

Conclusion

"Agentic Finance" is lowering the barriers to participation, making automation no longer just a tool for experts. However, to truly operate on a large scale, it needs a better "foundation": real-time data, more secure permission mechanisms, stronger testing systems, and more transparent execution results.

Relying solely on smarter AI cannot solve these problems. Real progress will come from improving the underlying structure.

The next milestone of DeFi is not just the growth in scale, but rather the trust in automation. This day will truly arrive only when AI agents are no longer just "concept demonstrations" but become truly reliable executors.