Author: 0XNATALIE
Since the second half of this year, the topic of AI Agent has been gaining traction. Initially, the AI chatbot terminal of truths attracted widespread attention for its humorous posts and replies on X (similar to 'Robert' on Weibo), securing a $50,000 grant from a16z founder Marc Andreessen. Inspired by its content, someone created the GOAT token, which surged over 10,000% in just 24 hours. The topic of AI Agent subsequently caught the attention of the Web3 community. Following this, the first decentralized AI trading fund based on Solana, ai16z, was launched, introducing the AI Agent development framework Eliza and sparking a rivalry over token names. However, the community still lacks clarity on the concept of AI Agent: what is its core essence? How does it differ from Telegram trading bots?
Working principles: Perception, reasoning, and autonomous decision-making
AI Agent is an intelligent agent system based on large language models (LLM) that can perceive the environment, make reasoning decisions, and complete complex tasks by invoking tools or executing actions. Workflow: Perception module (gather input) → LLM (understanding, reasoning, and planning) → Tool invocation (executing tasks) → Feedback and optimization (verification and adjustment).
Specifically, AI Agent first acquires data (such as text, audio, images, etc.) from the external environment through its perception module and transforms it into structured information that can be processed. LLM serves as the core component, providing powerful natural language understanding and generation capabilities, acting as the system's 'brain.' Based on the input data and existing knowledge, LLM performs logical reasoning, generating possible solutions or developing action plans. Subsequently, AI Agent completes specific tasks by invoking external tools, plugins, or APIs, and verifies and adjusts results based on feedback to form a closed-loop optimization.
In the application scenarios of Web3, what distinguishes AI Agent from Telegram trading bots or automation scripts? Taking arbitrage as an example, users want to conduct arbitrage trades under the condition that profits exceed 1%. In Telegram trading bots that support arbitrage, users set up a trading strategy where profits must be greater than 1%, and the bot starts executing. However, when market fluctuations are frequent and arbitrage opportunities are continually changing, these bots lack risk assessment capabilities and execute arbitrage as long as the profit condition is met. In contrast, AI Agent can automatically adjust its strategy. For instance, when the profit from a trade exceeds 1%, but data analysis assesses the risk as too high due to sudden market changes that could lead to losses, it will decide not to execute that arbitrage.
Therefore, AI Agent has self-adaptability, with its core advantage being its ability to learn autonomously and make decisions. By interacting with the environment (such as market conditions, user behavior, etc.) and adjusting behavioral strategies based on feedback signals, it continuously improves task execution effectiveness. It can also make real-time decisions based on external data and optimize decision strategies through reinforcement learning.
Doesn't this sound a bit like a solver under the intent framework? AI Agent itself is also a product based on intent, with the biggest difference from solvers under the intent framework being that solvers rely on precise algorithms, possessing mathematical rigor, while AI Agent's decisions depend on data training, often requiring trial and error during the training process to approach the optimal solution.
Mainstream frameworks of AI Agent
The AI Agent framework is the infrastructure used to create and manage intelligent agents. Currently, popular frameworks in Web3 include Eliza from ai16z, ZerePy from zerebro, and GAME from Virtuals.
Eliza is a multifunctional AI Agent framework built with TypeScript, supporting operation across multiple platforms (such as Discord, Twitter, Telegram, etc.) and capable of complex memory management, allowing it to remember previous conversations and contexts, maintaining stable and consistent personality traits and knowledge responses. Eliza employs a RAG (Retrieval Augmented Generation) system, enabling access to external databases or resources to generate more accurate responses. Additionally, Eliza integrates TEE plugins, allowing deployment within TEE to ensure data security and privacy.
GAME is a framework that empowers and drives AI Agents to make autonomous decisions and actions. Developers can customize agent behavior according to their needs, expand its functionality, and provide tailored operations (such as social media posting and replying). Different functionalities within the framework, such as the agent's environmental location and tasks, are divided into multiple modules for easy configuration and management by developers. The GAME framework divides the decision-making process of AI Agents into two levels: High-Level Planning (HLP) and Low-Level Planning (LLP), each responsible for different levels of tasks and decisions. High-Level Planning is responsible for setting the overall goals and task planning for the agent, making decisions based on goals, personality, background information, and environmental states, and determining task priorities. Low-Level Planning focuses on execution, converting decisions from High-Level Planning into specific operational steps and selecting appropriate functions and methods.
ZerePy is an open-source Python framework for deploying AI Agents on X. This framework integrates LLMs provided by OpenAI and Anthropic, enabling developers to build and manage social media agents that automate tasks like posting tweets, replying to tweets, and liking posts. Each task can be assigned different weights based on its importance. ZerePy provides a streamlined command-line interface (CLI) for developers to quickly launch and manage agents. Additionally, the framework offers a Replit template (an online code editing and execution platform), allowing developers to quickly start using ZerePy without complex local environment configurations.
Why does AI Agent face FUD?
AI Agent appears to be intelligent, capable of lowering the entry barrier and enhancing user experience. Why is there FUD in the community? The reason is that AI Agent is essentially still just a tool; it cannot yet complete the entire workflow and can only enhance efficiency and save time at certain nodes. Furthermore, in its current development stage, the role of AI Agent is largely focused on helping users issue MeMe and manage social media accounts with a single click. The community jokingly states, 'assets belong to Dev, liabilities belong to AI.'
However, just this week, aiPool released an AI Agent for token presales, utilizing TEE technology to achieve trustlessness. The wallet private key of this AI Agent is dynamically generated within the TEE environment to ensure security. Users can send funds (such as SOL) to the wallet controlled by the AI Agent, which then creates tokens according to set rules and launches a liquidity pool on a DEX, while distributing tokens to qualifying investors. The entire process does not rely on any third-party intermediaries and is autonomously completed by the AI Agent within the TEE environment, avoiding common rug pull risks in DeFi. It is evident that AI Agent is gradually developing. I believe AI Agent can help users lower barriers and enhance experiences; even simplifying parts of the asset issuance process is meaningful. However, from the macro Web3 perspective, AI Agent currently serves only as a tool for assisting smart contracts and should not be overly exaggerated in terms of its capabilities. Due to the lack of significant wealth effect narratives aside from MeMe in the second half of this year, it is normal for the hype around AI Agent to revolve around MeMe. Relying solely on MeMe cannot maintain long-term value, so if AI Agent can bring more innovative gameplay to trading processes and provide tangible on-ground value, it may develop into a universal infra tool.
