标签：#agents

The Series F round values Coralogix at $1.6 billion and comes less than a year after its previous raise.

Sepehr Khosravi discusses the evolution of developer productivity tools. Evaluating the strengths of tools like Cursor and Claude Code, he explains actionable techniques for senior engineers - including context engineering, custom rules, and Model Context Protocol (MCP) integrations. He shares real-world benchmarks and strategic frameworks for balancing AI adoption with clean code quality. By Sepehr Khosravi

AI Coding Agents in 2026: From Pair Programming to Autonomous Teams Slug: ai-coding-agents-2026-stack-comparison 1. The Three Categories That Actually Matter The 2024‑2025 hype cycle treated every AI coding tool as a single‑dimensional “best‑of‑list.” 2026 data shows that professional developers now average 2.4 tools per workflow (Stack Overflow Survey 2025). The real decision is architectural: Layer Goal Typical Agent Type Line‑level editing Speed, low latency Editor assistants Repo‑level planning Context depth, multi‑file changes Autonomous agents Enterprise governance Isolation, audit, CI/CD integration Platform agents Choosing a “one best tool” ignores the trade‑off between context window size (how many tokens the model can see) and execution speed (how fast the tool returns a suggestion). A narrow‑window editor assistant excels at instant autocomplete, while a wide‑window autonomous agent can rewrite an entire microservice in a single run. The three‑tier framework aligns the tool’s strengths with the architectural layer where they matter most. 2. Tier 1: Editor Assistants — Speed at the Line Level Tool Market Position Key Feature (2026) Pricing (per developer) Cursor $500 M+ ARR, fastest growth in Q1 2026 Parallel agents update git worktrees; 2‑second latency on 8‑core laptops $15 /mo (individual) – $120 /mo (team) GitHub Copilot 4.7 M paid subscriptions, 75 % YoY growth Agent Mode with multi‑agent workflows; deep VS Code integration $10 /mo (individual) – $100 /mo (enterprise) Windsurf 1.2 M active users, strong UI polish Real‑time code‑style enforcement; limited to 4‑file context Free tier up to 5 k lines, $30 /mo premium Tabnine Enterprise‑only after 2026 pivot Air‑gapped deployment; NVIDIA Nemotron 4‑bit models for on‑prem inference $200 /mo per seat (minimum 10 seats) When to choose each Cursor – prioritize raw typing speed and git‑aware suggestions. Ideal for startups that need rapid iteration without heavy IDE lock‑in. Copilot – best for teams already on

Here's a trace that reset how I think about evaluating tool-calling agents. An agent tries to book a flight. It calls search_flights with departure_date="next Friday" . The endpoint expected an ISO date, so it returns a 400 . The agent retries the same string four times, then apologizes to the user and gives up. Now the part that actually bothered me. Tool selection was correct. The model picked the right function out of a registry of 28. My tool-selection accuracy logged a clean 1.0 . The aggregate task-completion logged a 0 . And neither number told me which of three things broke: the argument was wrong, the model never read the 400 body, or the retry policy looped on the same input. My eval wasn't wrong. It was asking the wrong question. What "tool-call accuracy" actually grades If the only thing you measure is did the agent call the right tool , you're testing intent, not execution. Tool selection is necessary, not sufficient. It passes the moment the right function name shows up in the trace, completely blind to whether the arguments were garbage, whether the model read what came back, or whether it recovered from the 400 . That's the gap. The metric checks that the agent started the right way. Production needs to know whether it finished the right way. The reframe: it's four eval problems, not one The thing I had to internalize is that tool-calling eval is four problems stacked, each with its own root cause: Tool selection , right tool, or correctly no tool Argument extraction , schema-valid and semantically correct Result utilization , did it actually use what the tool returned Error recovery , did it retry, fall back, or escalate Score them separately and "the agent failed" collapses into "the argument extractor regressed on date strings on the flight-booking path." One bisect instead of three days. What I rebuilt Layer 1: Tool selection (with the bucket everyone drops) F1 on the tool name, so a 28-tool registry doesn't hide a regression on one rare endpoint

A post by Ben Halpern

Harness Base Definition: The Control System Outside the Model Previously, we split Agent into several minimal parts: Model: judge the next step Loop: keep the process moving Tools: interact with the real world State: keep the task connected At this point, a natural question appears: If Agent already has model, loop, tools, and state, why talk about Harness? An even easier confusion is: Is Harness a higher-level, smarter Agent that manages other Agents? That sounds plausible, but it bends the architecture in the wrong direction. Harness is not another Agent. It is not a larger prompt, and it is not a framework name. It is the control system outside the model. Continue with the same small CLI Agent: User says: help me figure out why this project's tests are failing, and fix it. If this CLI Agent is only a demo, it can be simple: send user input to model model says read file program reads file put result back into prompt model says edit file program edits file model says run tests program runs tests This chain can work once and already look like an Agent. But as soon as someone else really uses it, questions appear. What if the model wants to execute rm -rf ? What if it wants to read private files under the user's home directory? If it runs for ten minutes and the user interrupts, how is the working state saved? After a tool error, should the next model turn see the full log or only a summary? If the same task continues tomorrow, where does the session resume from? If a modification looks successful but no test verified it, how does the system know it is done? If a user says the Agent damaged a file, how do we reconstruct what happened? These questions do not belong to the model itself. They should not be left for the model to decide. The model only generates the next-step judgment from the current context. Permission, execution environment, session lifecycle, observability logs, verification criteria, and governance policy are engineering responsibilities outside the

A few months ago, I built an AI agent to automate one of the most repetitive parts of my workflow:...

Microsoft missed the boat on apps, so get ready for agents.

The AI agent security community has been converging on a problem. A researcher recently ran an experiment — feeding a memory-retrieval framework 10 scenarios involving certificate operations: signing, issuing, revoking, delegating. The system retrieved the right memory 8 out of 10 times. It matched the external authorization gate 7 out of 10. The conclusion: metadata per item isn't enough. You need a separate authorization gate over the proposed operation. That conclusion is correct. But I want to show what that gate actually looks like when you build it — because the primitive already exists, and it's older than LLMs. The problem is authorization, not retrieval Most agent frameworks today invest in memory and observability. The agent can recall what it did before. You can see what tools it called. Logs, traces, dashboards. What they don't have is a cryptographically enforced answer to the question: was this agent authorized to do this, before it did it? Those are different problems. Retrieval tells you what the agent remembers about its permissions. Authorization tells you what it was actually granted — signed, tamper-proof, at dispatch time. An agent that retrieves "I have revocation permissions" from memory and then revokes a certificate it shouldn't touch is not an authorization failure at the retrieval layer. It's an authorization failure at the gate layer — because there was no gate. Certificates are that gate A certificate is a signed declaration of what an entity is authorized to do. Issued once, verifiable offline in ~1ms, revocable instantly. We've used them for TLS, for IoT devices, for code signing. The same primitive works for agents. The model is simple: Orchestrator issues a certificate at dispatch time The certificate carries the agent's identity and its exact scope in meta Every tool call goes through a gate that verifies the certificate offline On completion — or abort, or timeout — the orchestrator revokes it // Orchestrator — dispatch const { cer

Since the early days of GenAI, when ChatGPT launched in late 2022, we began using prompt engineering to direct chatbots (and later LLMs) with human language instructions to provide us answers to questions or take actions (in a high-level…) In 2025, companies such as OpenAI and Anthropic began releasing a new agentic concept called “AI Agent”, an autonomous system that uses an AI model as its "brain" to perceive an environment, make independent decisions, and execute multi-step tasks using digital tools. Unlike passive chatbots that just answer questions, an agent can plan its own workflow, run commands, and browse the web to achieve a specific goal without constant human supervision. In this blog post, I will explain the concept of Context-as-Code and share some coding examples. Introducing Context-as-Code Traditional prompting is a one-way street. You type out your instructions, send them off, and that text never changes. AI agents operate completely differently. Because they work on their own, every action they take creates a mountain of new data. Every time an agent opens a file, checks an error, or runs a tool, it adds more information to the pile, which quickly overwhelms a standard chat screen. Context-as-Code treats the agent like a stateless compute engine. Instead of a massive text prompt, we use version-controlled files ( CLAUDE.md , AGENTS.md ) to establish structural boundaries, separating the permanent project rules from the temporary, dynamic session memory. Context-as-Code transforms loose AI prompts into version-controlled engineering assets by using structured Markdown files to establish permanent, auditable boundaries directly within a project repository. The Discovery Stage (Onboarding the Agent) Before an agent writes a single line of code, it must parse the overall project layout. These files act as the "map" for an incoming AI. llms.txt Serves as a lightweight text directory mapped out in Markdown format. Placed at the root of a project or webs

The specification lets developer, compliance, and security teams define their own policies for agents to follow in portable policy files.

Four days into a new supplier's first batch, my invoice extraction agent had filed 31 documents with amounts shifted by a decimal. Nothing raised an error. The downstream system accepted every record. The agent returned a 200 each time. The demo had run on five clean PDFs. Clear fonts, properly formatted dates, consistent layout. The extraction agent pulled vendor name, amount, due date, line items. Every field populated, every output valid. I ran it for the stakeholder meeting and it looked exactly like something you would ship. Three months in, the agent had processed around 800 invoices without complaint. Then a new supplier switched to scanned documents. Slightly rotated, thin fonts, OCR doing what it could on degraded source material. The model found text that resembled amounts and dates, and returned confident structured output. 1,247.50 read as 12,475.0. A due date resolved to a valid date three years in the future. The confidence was the problem. The model had no mechanism to say it was uncertain. It just answered. Nobody caught it for four days. What I built after The problem was not the model. The model did what it was designed to do. Find structure in text and return it. The straight pipeline from input to output had no gate in it. The fix was not more prompting or a better model. I added a validation layer between the agent output and the downstream system. It runs synchronously, takes about 80ms, and checks four things: Every required field is non-null. Amounts parse as positive numbers within a configured range for that supplier type. Dates fall within a 90-day future window. Extracted totals are consistent with line item sums, within a small tolerance. Anything failing a check routes to a review inbox instead of the queue. A human looks at it, corrects it if needed, marks it resolved. The system logs which check triggered and what the input looked like. In the first week after deployment, the layer caught 23 documents out of about 1,400. Eleven were b

There are only 3 LLM API protocols, but unlimited providers running the same protocol. Separate protocol from identity — protocol is code, provider is data — and complexity drops from N×M to N+M. 300 lines of TypeScript. Zero dependencies. The problem isn't "it doesn't work." It's "it won't tell you it broke." In May, I built a Claude Code skill called unblind . I use DeepSeek as my daily driver, but it can't see images. So unblind forwards images to Mimo and OpenAI's vision APIs. The MVP had two providers. A few dozen lines of if-else. It worked. Then I noticed something more unsettling: an expired API key — no warning. A network hiccup — no retry. A missing permission — silently skipped. This tool didn't fail. It quietly stopped working without telling you. I added Phase 0 self-healing, circuit breakers, persistent caching, and a security sandbox. Now unblind wouldn't fail silently. But then I noticed something else. The circuit breaker doesn't care if you're calling a vision API or a translation API. The cache doesn't care if the response is an image description or OCR text. The error normalization doesn't care whether the other end is Mimo or OpenAI. A universal provider infrastructure, trapped inside a vision skill. First attempt: follow the ecosystem, hit the ceiling The largest similar project in the ecosystem is vision-support, with 19 providers. The pattern is standard—base class + subclasses, GoF Template Method. I followed it for v2.0. class BaseProvider { async analyzeImage ({ image , prompt , options }) { const { url , body , headers } = this . _buildRequest ( image , prompt , options ); const res = await apiRequest ( url , { body , headers }); return { content : await this . _parseResponse ( res ), model : this . _model }; } } class MimoProvider extends BaseProvider { ... } // 54 lines class OpenAIProvider extends BaseProvider { ... } // 45 lines class GeminiProvider extends BaseProvider { ... } // ~50 lines One subclass per provider. I expanded unblin

Meta Description: Learn how to build AI agents with persistent memory using Azure AI Foundry Memory Service. A complete developer guide covering concepts, memory types, scope, provisioning, and a full Python implementation with the Foundry Hosted Agent Framework. Persistent Agent Memory with Azure AI Foundry: A Complete Developer Guide Table of Contents Introduction What Is Azure AI Foundry Memory? Memory Types Deep Dive Memory Architecture: How It Really Works Access Patterns: Tool vs. Low-Level API Understanding Scope Hands-On: Provisioning a Memory Store Hands-On: Building the Foundry Hosted Memory Agent Running & Deploying the Agent Security Best Practices Quotas, Limits & Regional Availability Conclusion + Next Steps Introduction Imagine you've just shipped a polished AI assistant for your SaaS product. Users log in, ask questions, and get sharp, helpful responses. The launch goes well. Then the complaints start rolling in. "Why does it keep asking me for my name every single session?" "I told it last week that I'm vegetarian — why is it recommending steak again?" "It feels like talking to someone with amnesia." This is the stateless agent problem — one of the most frustrating gaps between the promise of conversational AI and the lived reality of production deployments. Every conversation starts from a blank slate. The agent has no idea who it is talking to, what that person prefers, or what was discussed yesterday, last week, or a month ago. The result is a user experience that feels hollow and repetitive — the opposite of the intelligent, personalized assistant your users were promised. The solution is persistent memory, and Azure AI Foundry Memory is Microsoft's production-grade answer to exactly this problem. Introduced as part of the Azure AI Foundry platform, the Memory Service gives agents the ability to remember facts across sessions, distill long conversation histories into concise summaries, and retrieve the right context at the right moment — all wit

In the first post I told you the story: 20 years as a developer, six months of being scared of AI, $800 in burned tokens, and a stubborn agent named Claudio who taught me — by failing over and over — how to ask for things properly. This post is the method that came out of all that pain. Five rules, one per letter of FORGE. I want to be honest about one thing up front: this is not a framework I invented at a whiteboard. Every rule here is a scar. Each one is the lesson from a specific mistake that cost me money, time, or sleep. I'm going to tell you the mistake first, and then the rule. Because the rule only makes sense once you've felt the pain that created it. Let's go. First, the idea behind all of it Here's the thing nobody told me when I started: A task is not a post-it. It's a contract. When you ask an AI agent for something with no structure, you're not giving an order — you're placing a bet. The agent interprets, assumes, improvises, and the result depends on how much context it managed to reconstruct on its own. Sometimes it guesses right. Often it doesn't. And you only find out after the tokens are gone. The Forge Method is the agreement between you and your agents: you bring the structure, they execute with precision . That's it. Five rules to hold up your end of that contract. F — Focused The mistake: My early tasks had titles like "Fix bug" and "Update stuff." I'd come back twenty minutes later to find the agent had fixed a bug — just not the one I meant. It wasn't wrong. It just had no way of knowing which thing I was talking about. **The rule: **If the title is vague, the task is vague. Vague in, vague out. A focused title needs a domain, an action, and a scope. Two words minimum, and no generic placeholders. ❌ Rejected: - "Fix bug" - "Update auth" - "Do the thing" ✅ Accepted: - "Fix authentication timeout on Nginx reverse proxy" - "Update JWT expiry from 1h to 24h in src/auth/config.ts" The test: Read the title with no context. Do you know the domain,

A security reviewer finds a critical issue a day or two before the release of an application. While it's an important issue, it sets the team back weeks, frustrating their product management partners and customers. The review came at the most expensive time in the process. There are many examples of how work items move through different processes to deliver software in large companies. While GenAI has allowed us to rapidly create code, it also moved and exposed the bottlenecks in our processes. It has also caused us to re-examine where it is most effective to make certain decisions. This is the challenge, and a deliberate blend of automated, programmatic, and human judgment is well suited to help you solve it. We can borrow from the well-trodden path of value stream mapping here. It is useful for spotting bottlenecks and waste in a given process, but it's also valuable to ask the deeper question of who or what should own each step. Each option earns its place differently. Is there an earlier step that may reduce costs with an agent where it was previously limited by human availability? Or is the stronger determinism of a programmatic step more important for a critical piece of the flow? Some decisions should stay with human judgment, where confidence without context is a liability. The opportunity for security teams and other stakeholders is to scale their impact across these options rather than scaling headcount. Workflow-as-code is not a new idea. There are a number of existing engines where the workflow definition is its own entity, separate from the work itself. GitHub Actions defines pipelines in version-controlled files, while the execution happens on separate runners. Airflow and Temporal follow a similar pattern for data and application workflows. Because the definition lives on its own, a team can change how a given step runs without rebuilding the whole flow. That separation is what makes it practical to adjust who or what owns each step over time. Rather

멀티 에이전트(Multi-agent) AI 시스템은 여러 AI 에이전트가 역할을 분담하고 서로 통신하면서 복잡한 업무를 자율적으로 처리하는 구조다. 한 에이전트가 처음부터 끝까지 처리하는 싱글 에이전트와 달리, 검색·분석·실행·검증을 각각 다른 에이전트가 병렬로 맡고 그 결과를 조율(orchestration)한다. 2026년 한국 기업 AI 도입은 단일 챗봇 단계를 지나, 다단계 의사결정과 도메인 특화 작업을 자동화하는 멀티 에이전트 단계로 이동 중이다. 이 글은 멀티 에이전트와 싱글 에이전트의 구조적 차이, 도입 비용·기간·실패 위험, 국내 도입 사례, 외주 발주 시 업체 선택 기준까지 발주 담당자가 의사결정에 바로 쓸 수 있는 비교표·체크리스트를 제공한다. 멀티 에이전트와 싱글 에이전트, 무엇이 다른가? 싱글 에이전트는 하나의 LLM 인스턴스가 도구(tool)를 직접 호출하면서 모든 단계를 처리한다. 작업 흐름이 선형적이고 컨텍스트가 한곳에 모이므로 구현이 단순하다. 반면 멀티 에이전트는 작업을 여러 하위 작업으로 쪼개고, 각 에이전트가 자기 역할(role)·시스템 프롬프트·도구 집합을 따로 가진 채 협업한다. 가장 흔한 패턴 세 가지를 정리하면 다음과 같다. Supervisor 패턴 : 상위 supervisor 에이전트가 작업을 받아 worker 에이전트들에게 분배하고 결과를 통합한다. 의사결정 라인이 명확해 디버깅이 쉽다. Peer 패턴 : 동등한 에이전트들이 메시지 큐로 정보를 주고받으며 합의(consensus)를 이룬다. 창의적 결과가 필요한 리서치·기획에 적합하다. Hierarchical 패턴 : supervisor 아래 sub-team을 두고, sub-team 안에서 다시 supervisor-worker 구조를 반복한다. 대규모 RPA·복합 업무 자동화에 쓰인다. 구분 싱글 에이전트 멀티 에이전트 적합한 작업 1~3단계 선형 작업 5단계 이상, 분기·검증 필요 컨텍스트 관리 단일 컨텍스트 윈도우 에이전트별 분리 + 공유 메모리 토큰 비용 낮음 1.8~3배 (병렬·검증 오버헤드) 구현 난이도 낮음 높음 (조율·실패 처리) 정확도 단순 작업에 충분 복잡 작업에서 10~25%p 향상 외주 비용(국내) 800만~3,000만 원 3,000만~1.2억 원 구축 기간 4~8주 10~16주 Anthropic의 멀티 에이전트 리서치 시스템 사례 에서는 단일 Claude 에이전트 대비 멀티 에이전트 구조가 리서치 품질 평가에서 약 90% 더 높은 점수를 받았다. 다만 토큰 사용량은 약 15배로 늘어, 모든 작업에 멀티 에이전트가 정답은 아니라는 점도 같은 글에서 강조한다. 언제 멀티 에이전트가 필요한가? — 도입 판단 트리 발주 담당자가 자주 묻는 질문은 "우리 업무에 멀티 에이전트가 정말 필요한가"이다. 다음 네 가지 조건 중 두 개 이상에 해당하면 멀티 에이전트가 ROI를 만든다. 작업이 5단계 이상이고, 각 단계가 다른 전문성을 요구한다 — 예: 시장 리서치 → 경쟁사 분석 → 보고서 작성 → 사실 검증. 결과의 신뢰도가 비즈니스 결정에 직결된다 — 검증 에이전트(critic)를 두면 환각 비율이 의미 있게 떨어진다. 작업 분기(branching)가 데이터에 따라 동적으로 결정된다 — 단순 if/else로는 표현 어려운 휴리스틱 분기. 여러 외부 시스템(SaaS·DB·내부 API)을 동시에 다뤄야 한다 — 도구 권한을 에이전트별로 격리하면 보안 관리도 쉬워진다. 반대로 다음에 해당하면 멀티 에이전트는 과잉이다. 싱글 에이전트로 충분하다. 단순 FAQ 챗봇, 분류·태깅 같은 단발성 작업. 작업당 비용이 100원 미만이어야 하는 대규모 트래픽 환경. 인간 검수자(HITL)가 매번 결과를 확인하는 워크플로우 — 멀티 에이전트의 자율성이 오히려 검수 부담을 늘린다. 나무숲에서도 초기에는 모든 자동화를 싱글 에이전트로 구축했다가, 검증·분기·외부 API 호출이 동시에 일어나는 마케팅 자동화 파이프라인부터 멀티 에이전트로 재설계한 경험이 있다. 무조건 멀티 에이전트가 좋은 게 아니라, 위 네 조건을 충족한 영역만 옮긴 것이

클로드로 한글파일(HWP) 변환·자동화하는 법 2026 — 요약·표 추출·일괄 처리 실전 한글파일을 Claude로 다루려는 한국 기업 실무자가 가장 먼저 부딪히는 벽은 " 읽기는 됐는데, 그래서 뭘 어떻게 자동화하지? "다. HWP-MCP를 설치해 Claude가 한글 문서를 읽게 만드는 것까지는 HWP-MCP 도입 가이드 에서 다뤘다. 이 글은 그 다음 단계 — 실제 업무에서 한글파일을 요약·변환·일괄 처리하는 구체적 방법 을 실전 예시로 보여준다. 한글파일 AI 자동화의 핵심은 "한컴 오피스 라이선스 없이, 사람 손을 거치지 않고, 반복 작업을 Claude에게 위임하는 것"이다. 계약서 100건 요약, 요구사항서의 표를 CSV로 추출, 폴더 안 HWP 일괄 변환 — 이런 작업이 자동화 대상이다. 한글파일 자동화로 풀 수 있는 업무 3가지 업무 수동 작업 시간 자동화 후 적용 키워드 문서 요약 1건당 10~15분 50건 30초 claude 한글파일 요약 표 → 데이터 추출 1표당 5분 (재입력) 표 자동 CSV 변환 hwp 표 추출 일괄 변환·정리 100건 8시간 100건 1시간 20분 한글파일 일괄 처리 세 업무 모두 "사람이 한글파일을 열어 읽고, 내용을 옮겨 적는" 반복 작업이다. Claude + HWP-MCP 조합은 이 중간 단계를 없앤다. 전제: HWP-MCP 연결 확인 자동화에 들어가기 전, Claude가 한글파일을 읽을 수 있는 상태인지 확인한다. (설치 절차는 HWP-MCP 도입 가이드 참조.) # Claude Desktop 설정에서 hwp-mcp 서버가 연결됐는지 확인 # MCP 도구 목록에 hwp_read, hwp_extract_tables 등이 보여야 함 연결이 확인되면 아래 3가지 워크플로우를 바로 쓸 수 있다. 워크플로우 1: 한글파일 요약 자동화 계약서·보고서·요구사항서처럼 길이가 긴 한글 문서를 Claude에게 요약시키는 패턴이다. 단일 문서: "이 한글파일을 읽고 다음 3가지로 요약해줘: 1. 핵심 내용 5줄 2. 의사결정이 필요한 항목 3. 누락되거나 모호한 조항" 여러 문서 일괄 요약: 폴더 경로를 주고 "이 폴더의 모든 .hwp 파일을 각각 위 형식으로 요약하고, 결과를 하나의 마크다운 표로 정리해줘"라고 지시하면, Claude가 HWP-MCP로 파일을 순회하며 처리한다. 50개 문서 기준 약 30초. 요약 품질을 높이는 팁: "요약 기준"을 구체적으로 명시 할수록 결과가 좋다. "계약 금액·기간·위약 조항 중심으로" 같은 도메인 컨텍스트를 주면 일반 요약보다 실무 적합도가 크게 오른다. 워크플로우 2: 표 → CSV 데이터 추출 한글파일의 표는 복사-붙여넣기로 옮기면 서식이 깨지는 게 가장 큰 골칫거리다. HWP-MCP의 표 추출 기능을 쓰면 구조를 유지한 채 데이터만 뽑는다. "이 한글파일에 있는 모든 표를 추출해서 CSV로 변환해줘. 표가 여러 개면 각각 별도 파일로, 헤더 행을 포함해서." 활용 시나리오: 견적서·정산표 : 한글 견적서의 항목·단가·합계를 회계 시스템에 올릴 CSV로 요구사항 명세 : 기능 목록 표를 이슈 트래커(Jira/Linear) import 형식으로 설문·조사 결과 : 한글 보고서의 통계 표를 분석용 데이터프레임으로 표 안에 병합 셀이 있으면 Claude에게 "병합 셀은 상위 값으로 채워줘(forward fill)"라고 미리 지시하는 게 데이터 정합성에 좋다. 워크플로우 3: 폴더 일괄 처리 가장 ROI가 큰 패턴. 수백 개 한글파일이 쌓인 폴더를 통째로 처리한다. "./contracts 폴더의 모든 .hwp 파일에 대해: 1. 계약 상대방·금액·시작일·종료일을 추출 2. 하나의 CSV로 통합 (파일명을 첫 열에) 3. 종료일이 30일 이내인 계약은 ⚠️ 표시" 100건 기준 수동 8시간 작업이 약 1시간 20분으로 줄어든다(실측). 핵심은 추출 스키마를 먼저 정의 하는 것 — 무엇을 뽑을지 명확할수록 일괄 처리 정확도가 높다. python-docx·한컴 API와 무엇이 다른가 방식 한글파일(.hwp) 지원 자동화 난이도 AI 통합 한컴 오피스 자동화

Claude Code에서 Codex로 옮길 때 — 실전 마이그레이션 가이드 2026 Claude Code 기반 워크플로우를 OpenAI Codex CLI로 옮기려는 팀이 늘고 있다. 모델 가격, 멀티 벤더 리스크 분산, 특정 코딩 워크로드의 성능 차이 등 이유는 다양하다. 그런데 두 도구는 같은 "AI 코딩 에이전트"라는 카테고리에 속해도 컨벤션·확장 메커니즘이 다르다. 무작정 옮기면 자동화 파이프라인의 절반이 깨진다. 이 가이드는 Claude Code → Codex 마이그레이션을 실제로 끝내본 팀이 어떤 순서로 무엇을 옮기고, 무엇을 포기하고, 무엇을 대체했는지 정리한다. 자동 변환 툴( claude2codex )을 어디서 쓰고 어디서 안 쓰는지, 일주일 점검 체크리스트, 양쪽을 분기 사용하는 하이브리드 패턴까지 다룬다. 마이그레이션 전 의사결정 — 옮길지 말지부터 옮기는 게 모두에게 정답은 아니다. 다음 세 질문에 모두 "예"여야 본격 마이그레이션을 권한다. 현재 Claude Code 비용의 60% 이상이 일상적인 코드 편집·리뷰에서 발생하는가? (Codex의 GPT-5-codex가 단가 우위를 보이는 영역) — 만약 디자인·기획·문서 분량이 큰 워크플로우라면 Claude를 유지하는 게 합리적이다. Skills·Hooks·서브에이전트 같은 Claude 고유 기능에 의존하지 않는가? 의존도가 높다면 마이그레이션 비용이 비용 절감을 초과한다. 하나의 벤더 락인을 줄이는 게 중요한 전략적 우선순위인가? 멀티 벤더 운영은 그 자체로 관리 비용이 든다. 세 질문 중 하나라도 "아니오"라면, 통째 마이그레이션 대신 하이브리드 분기 사용 (아래 5절)이 더 낫다. Claude Code와 Codex의 핵심 차이 비교 영역 Claude Code OpenAI Codex CLI 마이그레이션 난이도 메인 모델 claude-opus-4-7 / sonnet-4-6 / haiku-4-5 GPT-5 / GPT-5-codex / o1 계열 낮음 (모델 교체) 컨벤션 파일 CLAUDE.md AGENTS.md (멀티 벤더 표준) 낮음 (rename + 어조 조정) 확장 메커니즘 Skills (markdown SKILL.md + 메타데이터) 별도 표준 없음, 수동 컨텍스트 로딩 높음 (가장 큰 갭) 자동화 훅 Hooks (PreToolUse, SessionStart, UserPromptSubmit 등) 라이프사이클 이벤트 미지원 높음 (외부 wrapper 필요) 슬래시 커맨드 /명령 형태 + 인자 파싱 CLI 인자로 대체 중간 MCP 서버 1급 지원, 자동 도구 노출 일부 지원, 설정 형식 다름 중간 서브에이전트 Agent tool (subagent_type) 외부 오케스트레이션 필요 높음 권한 모드 acceptEdits / plan / dontAsk 등 --auto / --confirm 류 낮음 가장 큰 갭 세 곳: Skills · Hooks · 서브에이전트 . 이 세 가지에 깊이 의존하는 팀은 마이그레이션 ROI가 마이너스로 나올 수 있다. 마이그레이션 절차 — 7단계 1단계: 자산 인벤토리 (1일) .claude/ 디렉토리, CLAUDE.md , 프로젝트 루트의 slash command 정의, hook 설정, MCP 서버 목록을 전부 추출한다. find . -path "*/.claude/*" -type f > migration/inventory.txt ls .claude/skills/ .claude/hooks/ .claude/commands/ 2>/dev/null >> migration/inventory.txt cat .claude/settings.json | jq '.mcpServers // {}' > migration/mcp.json 이 파일들이 모두 변환되거나, 대체되거나, 폐기되는지 명시적으로 매핑되어야 한다. "그냥 옮기면 되겠지"는 거의 항상 일주일 후 장애로 돌아온다. 2단계: claude2codex 자동 변환 적용 (반나절) 오픈소스 claude2codex 마이그레이션 툴 이 자동으로 처리하는 것: CLAUDE.md → AGE

AI Builder Notes - May 2026 AI-assisted notes from my liked-tweets feed, organized around agent workflows, browser traces, model loops, and guardrails. Practical takeaways Start with the workflow, not the agent. A useful agent task has a source of truth, a narrow action, a verifier, and a stop condition. “Review this repo” is vague. “Find auth bugs in these routes, cite file lines, run the relevant tests, and stop after the first credible exploit path” is a workflow. Use dynamic workflows in claude code - to do the vibe bits for thinking through a workflow. Think of it like this - you can describe in natural language an entire workflow consisting of multiple agents at various steps - I want the docs updated, tests passed, security review done and also playwright tests done. Dynamic workflows figures out which parts can be divided in parallel and what should be done sequentially. Creates a flowchart - and writes JS code for it. Its a JS script that can execute subagents at scale and deterministically [1] Planner/executor split is the way to go. Spend the expensive model on taste, decomposition, and risk discovery. Use cheaper or narrower models for repeatable implementation once the task has tests, rubrics, logs, or examples. [2] Do not judge an agent workflow by the model name alone. If the loop has repo access, a rubric, a way to inspect tool calls, and a verifier, a less fashionable model can still do useful work. The Letta Code / GLM 5.1 review-bot example is interesting for that reason, not because “someone used X instead of Y” is interesting by itself. [3] Prefer small interfaces to giant tool menus. MCP tool call definitions are rotting your context! The monday.com GraphQL example was the clearest cost warning: one task used 15k tokens through SDK/code-mode and 158k tokens through a real MCP server. MCP is useful, but a menu of tools is not automatically an efficient interface. [4] [5] For browser work, save the trace. Run the workflow once, inspect wasted act