Browsed by
[Category:] SW Development

Token Exchange

Token Exchange

Comments 0 Comment

Impersonation vs Delegation Bob: a music enthusiast who has meticulously curated a collection of super cool playlists on an online music streaming platform Alice: a close friend of Bob’s, who seeks access to his playlists to find the perfect soundtrack for her upcoming road trip Alice is impersonating Bob The music streaming service has introduced features to support family and friend sharing. Alice can pass her identity information along with the temporary pass provided by Bob API Gateway Calls Backend…

Read More Read More

 Task in the A2A Protocol

 Task in the A2A Protocol

Comments 0 Comment

In the A2A protocol, when a client sends a message to an agent, the agent might determine that fulfilling the request requires a stateful operation (e.g., “generate a report,” “book a flight,” “summarize a document”). This is where the Task Object comes into play. It is the fundamental, stateful unit of work processed by the A2A Server (remote agent) for an A2A Client, encapsulating the entire interaction related to achieving a specific goal or request. Key characteristics of a Task include: By defining interactions within…

Read More Read More

Deploying WordPress using Docker

Deploying WordPress using Docker

Comments 0 Comment

Deploying WordPress with Nginx using Docker involves setting up multiple containers that work together. This typically includes a WordPress container (often using PHP-FPM), a database container (like MySQL or MariaDB), and an Nginx container to act as a reverse proxy. Here’s a general outline of the process: This setup provides a robust and scalable environment for running WordPress, leveraging Nginx for efficient request handling and Docker for containerization and isolation. You can further enhance this with SSL certificates (e.g., using Certbot in…

Read More Read More

Action Blocks in MCP

Action Blocks in MCP

Comments 0 Comment

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…

Read More Read More

About Memory in MCP

About Memory in MCP

Comments 0 Comment

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…

Read More Read More

The role of MessagesPlaceholder in LangChain.js

The role of MessagesPlaceholder in LangChain.js

Comments 0 Comment

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…

Read More Read More

MCP(Model Context Protocol) Deep Dive

MCP(Model Context Protocol) Deep Dive

Comments 0 Comment

요즘 AI 개발에 대해 얘기하자면 MCP를 빼놓고 얘기할 수 없다. LLM이 나오면서 AI가 모든 것을 바꿔 버릴 것이라는 우려가 있었지만 막상 Chatbot수준의 정보를 얻는 것 말고는 활용 가치가 그리 크지 않았다. 하지만 Antropic에서 MCP규격(2024.11)을 내 놓으면서 기류는 크게 바뀌었다. LLM이 인공지능 즉, 두뇌 역할을 담당했다면 MCP는 이 두뇌에 팔과 다리를 달아주었기 때문이다. 결국 사람이 AI에게 말을 건네면 AI는 그 말를 이해하고 실제 도움이 되는 행동을 할 수 있게 된 셈이다. 이 글에서는 MCP가 무엇인지 규격(Specification)위주로 간략하게 설명하고 Langchain MCP Adapter와…

Read More Read More

Perverse Incentives

Perverse Incentives

Comments 0 Comment

Many AI coding assistants, including Claude Code, charge based on token count – essentially the amount of text processed and generated. This creates what economists would call a “perverse incentives(삐뚤어진 유인책)” – an incentive that produces behavior contrary to what’s actually desired. Let’s break down how this works: It might be difficult for AI companies to prioritize code conciseness when their revenue depends on token count. There’s clearly something going on where the more verse the LLM is, the better…

Read More Read More

A.I. 시대에 소프트웨어 개발이란?

A.I. 시대에 소프트웨어 개발이란?

Comments 0 Comment

2022년 11월 ChatGPT가 본격적인 A.I.의 서막을 알렸으니 A.I. 붐이 일어난지 아직 3년이 채 못 된 시점이다. 비록 짧은 기간이지만 근래 우리 피부에 와닿는 이 기술의 파급력은 어마어마하다. 초기 그렇게 덩치가 컸던 A.I. 모델도 3년도 안돼 휴대폰 속까지 들어와버렸으니 A.I.를 모르는 사람은 거의 없을 지경이다. 이렇게 전 세계적으로 파급력도 크고 전파력도 강한 A.I.가 일상생활 속에서 느끼는 체감이 이정도인데 이 업계에 몸담고 있는 나로서는 오죽하겠는가! A.I.가 만들어 내는 결과물을 접하는 이용자의 시각과 A.I.를 활용해 결과물을 만들어 내는 개발자의 입장에서 바라보는 관점은 사뭇…

Read More Read More

Langgraph – Edges

Langgraph – Edges

Comments 0 Comment

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.