숲 해설을 위한 영어 공부
AI Agents typically focus on executing predefined tasks efficiently, automating repetitive workflows. On the other hand, Agentic AI interprets goals, plans across tools, makes independent decisions, and adapts in real time – bridging the gap between automation and true intelligence. This difference shapes how business can reduce costs, boost efficiency, and create experiences that feel less like command and more like collaboration.
When developing AI agents, understanding prompt engineering is essential. Prompt engineering is the key to effectively working with LLMs. It involves crafting inputs that guide these sophisticated AI systems to generate accurate and relevant responses. Mstering skill ensures that developers can leverage the full potential of LLMs, making interactions with AI more productive and precise. There is a. lot of hype surrounding prompt engineering, with numerous videos, blogs, and articles claiming to reveal its “secrets.” However, it’s important to be…
Encapsulating Thoughts and Intent Action blocks represent a model’s decision at a given point in its reasoning loop. Rather than producing only a final answer, the model under MCP generates intermediate actions that reflect its plan. Each action block contains structured metadata describing what the model intends to do next. This can include calling a tool, representing clarification, storing an observation, or generating final output. For example, an agent tasked with summarizing documents might produce this action block: This tells…
Memory: Persistent Context Across Reasoning Cycles Memory in MCP serves as the persistent, structured storage that an agent can use to reference previous interactions, maintain state, or build context over time. Unlike traditional LLM memory, which is simulated by stuffing previous outputs into the next prompt, MCP memory is external, addressable, and queryable. Memory can include: Each memory object can be assigned an identifier and passed to the model as part of the context. The model can then reason over…
The MessagesPlaceHolder in LangChain.js plays a crucial role in enabling dynamic and flexible construction of chat prompts by acting as a placeholder for a list of messages within a ChatPromptTemplate. Its primary functions are Dynamic Message Insertion It allows you to inject a list of BaseMessage objects (like HumanMessage, AIMessage, SystemMessage, etc) into a specific position within your chat prompt template during runtime. This is particularly useful for managing chat history, where the list of past messages needs to be…
Low environmental standards helped China become the world’s low-cost producer of rare earths, but Beijing was also focused on helping the industry. 몇 달 전 중국이 희토류의 수출을 일시 중단할 때까지 대부분의 세계 지도자들은 희토류를 그리 중요하게 생각하지 않았다. 그러나 약 반 세기동안 중국 정부의 최고위급들은 이들 희토류에 대해 꾸준한 관심을 가져왔다. 마오쩌둥이 27년의 통치기간 동안 얼마만큼의 철과 스테인레스를 생산 할지에만 초점을 맞췄지 품질에는 크게 신경을 쓰지 않았다. 그 결과 업계의 요구를 충족시키지 못하는 저품질의 철과 스테인레스의 생산만 많아졌다. 1940년대…
Edges define how the logic is routed and how the graph decides to stop. This is a big part of how your agents work and how different nodes communicate with each other. There are a few key types of edges: A node can have MULTIPLE outgoing edges. If a node has multiple out-going nodes, all of those destination nodes will be executed in parallel as a part of the next superstep.
“A little piece of advice. You see an agent, you do what we do. Run!” – Cypher to Neo in the movie, “The Matrix” When it comes to LLM-based agents, there is no universally accepted definition, but we can extend the philosophical definition to say that an agent is an intelligent(?) entity that leverages LLMs to solve complex tasks by interacting with the environment via a set of tools. Since LLMs possess good understanding, reasoning & generation capabilities, it makes…
Java언어로 Enterprise 어플리케이션을 작성하거나 기존의 Enterprise 어플리케이션이 있다면 Virtual Thread에 관심을 둘 필요가 있다. Virtual Thread는 Java 21에 소개된 새로운 기능으로 어플리케이션의 확장성(Scalability)를 획기적으로 높여주며 프로젝트에 드는 비용을 줄여 준다. 이 문서는 문제의 근간을 들여다 봄으로써 Virtual Thread를 활용할 경우 왜 확장성이 개선 되는지를 설명하고자 한다. Platform Thread Java 21 이전에 구현된 Thread를 Platform Thread 라고하며 근본적으로 OS(Operating System) Thread를 Wrapping한 형태로 구현되어 있다. 따라서 Platform Thread와 OS Thread간의 관계는 1:1 매핑이라고 생각하면 된다. 위 그림을 보면 가장 밑 부분은…
최근 A.I. 모델은 추론모델(Reasoning)을 기반으로 한다. OpenAI, Google, DeepSeeke들도 이런 추론모델을 기반으로 A.I. bot들을 만들고 있다. 하지만 이른 추론모델을 기반으로 하는 A.I.가 이전 모델보다 hallucination이 더 심해지고 있다. OpenAI의 경우 가장 강력하다고 하는 모델인 o3모델에서 PersonQA테스트를 했을 때 33%의 hallucination이 발생했다고 하며 이는 이전의 추론 시스템인 o1보다 두 배 이상의 hallucination이 발생되는 수치이다. 새 모델인 o4-mini는 이보다 더 높은 48%의 hallucination이 발생되고 있다. Hallucination을 줄이기 위한 노력들은 하고 있지만 모델이 방대한 데이터를 기반으로 학습을 하기 때문에 원인을 정확하게 어떤 경로를…