'structured output' 검색 결과

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Data structures and serialization formats for agent-to-agent communication. Covers message envelopes, structured output schemas, capability declarations, task handoff payloads, error/retry signaling, and context windows as data structures. Compares the version-pinned A2A, MCP, and JSON-RPC role boundaries covered by this bundle; OpenAI and LangChain-specific APIs require their own current sources. Teaches when to use rigid schemas versus free-form content with validation, typed versus untyped boundaries, and streaming versus batch. Activate on: "agent message format", "agent communication schema", "agent-to-agent protocol", "A2A protocol", "MCP message format", "structured output for agents", "agent interop", "interchange format", "agent serialization", "task handoff format", "capability declaration". NOT for: what agents say to each other (use agent-conversation-protocols), orchestration topology (use multi-agent-coordination), building agent infrastructure (use agentic-infrastructure-2026).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

정규 표현식과 문법 규칙으로 로컬 언어 모델의 출력을 제한해 JSON과 날짜 형식을 맞춥니다. 고정 라벨 분류와 Python을 이용한 재사용 가능한 다단계 생성도 다룹니다.

• 지정 스키마에 맞는 JSON 생성
• 날짜와 이메일 주소 형식 통일
• 고정 라벨로 텍스트 분류

Firecrawl의 `/scrape`를 앱에 통합하여 알려진 주소에서 본문, 링크, 이미지 등 단일 페이지 정보를 가져오고 데이터 최신성 설정을 돕습니다.

• 알려진 페이지를 요약용으로 가져오기
• 기업이나 제품 페이지에서 정보 보완하기
• 요금, 변경 기록, 문서 추출하기

Turn document analysis into a structured PPT presentation with images generated in a chosen style. The skill uses the NanoBanana stack to combine document-based content preparation and image generation within a presentation creation workflow.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turning a document into a PPT presentation
• Creating slides with styled, generated images
• Combining document analysis and presentation creation

Audit or create a dedicated About page that explains a website’s purpose and identifies its people or organization. Review the rendered output and supporting information, including expertise and contact details, to find gaps.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing a website’s About page
• Creating a page about the organization and its mission
• Checking how operator information appears in rendered output

Build and improve Python command interfaces for GUI applications with OpenClaw. The skill guides source analysis, command design, testing, and packaging, including interactive sessions and structured JSON output for agents.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Build a command interface for a GUI application
• Add missing commands to an existing interface
• Test workflows against the actual application

Set up and inspect an Ethereum node through a command-line interface. Install execution and consensus clients, configure validator metadata, expose RPC access for external requests, and retrieve structured health reports for agent workflows.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a new Ethereum node host
• Install chosen execution and consensus clients
• Configure RPC access through Nginx or Caddy

Build and debug Apify Actors, cloud programs for web scraping, automation, and data processing. Get guidance on language templates, input and output schemas, runtime code, local testing, and deployment, with practices for handling credentials and external data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating an Actor for web scraping
• Defining Actor inputs and structured outputs
• Debugging an Actor with local test data

Plan structured adversarial tests for AI applications to assess safety bypasses, data leaks, and unauthorized tool use. Organize test prompts, record findings, and prioritize fixes using reporting guidance and an adaptable testing template.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess an AI feature before release
• Compare security behavior of candidate models
• Retest after a prompt injection or jailbreak incident

Explore a web application as a user to find reproducible bugs and usability problems. Produce a structured report with reproduction steps, screenshots, and videos for interactive issues, giving responsible teams concrete evidence to investigate.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking a web app's quality before release
• Testing forms and common user workflows
• Finding confusing interfaces and visual problems

Extract identity, ownership, control, and source-of-funds details from investor or client onboarding documents into a structured JSON record. Inventory the submitted documents and flag obvious missing or expired items before passing the information to KYC screening rules.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organize investor onboarding documents
• Extract beneficial owners and controlling persons
• Check for missing or expired documents

Convert Simplicité text logs into structured JSON while keeping only the fields needed for troubleshooting. Preserve multiline errors and stack traces, and reduce the amount of log content passed to an AI agent for analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preparing large logs for AI analysis
• Extracting timestamps, severity levels, and messages
• Preserving multiline errors during conversion

Guides language model training with GRPO in TRL, comparing several responses and rewarding better results. Covers dataset preparation, scoring rules for correctness and format, training configuration, monitoring, and saving models for later use.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Training models to follow JSON or XML formats
• Designing rewards for math and coding tasks
• Adjusting training to available GPU memory

Turn a product description into a landing page with headlines, feature sections, pricing, FAQs, and calls to action. Receive Next.js/React components styled with Tailwind CSS, plus search metadata, structured data, and alternative copy.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a landing page for a new product
• Building a campaign or lead capture page
• Comparing headline and page variants

Guide an AI agent through stalled work using structured investigation, different hypotheses, and checks backed by actual output. The skill combines systematic problem solving with forceful Japanese workplace rhetoric and applies across coding, research, writing, and planning.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Changing approach after repeated failures
• Checking assumptions against original sources
• Verifying results before reporting completion

Turn completed research, analysis, reports, or plans from the current session into a self-contained HTML artifact. A renderer controls layout, typography, and color, using structured content and a choice of two visual styles.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn research findings into an HTML artifact
• Format a cost analysis with tables and callouts
• Present investigation findings as a designed document

Evaluate AI agent outputs with code checks and model-based grading. Run repeated trials to measure reliability, compare prompts or models, and check whether changes reduce quality, with saved transcripts for reviewing the results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Comparing two prompts on the same test cases
• Checking quality after agent configuration changes
• Turning real failures into repeatable evaluation cases

Helps design and evaluate prompts for more reliable AI responses. Covers clear instructions, input-output examples, task breakdown, and structured formats such as JSON, with guidance on comparing quality, cost, and response time across models.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify ambiguous instructions for an AI task
• Specify JSON output using schemas and examples
• Break complex tasks into connected prompts

Turn structured JSON into editable SVG diagrams for system architectures, workflows, and pipelines. Specify positions, connections, and groups precisely, reproduce the same output under fixed rendering conditions, and convert figures to PDF for papers.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating architecture diagrams for technical papers
• Illustrating workflows and processing pipelines
• Adjusting diagram layouts through JSON specifications

Design and improve prompts for language models, then test their accuracy and consistency. Create reusable templates, JSON output schemas that define response structure, evaluation criteria, and test cases while considering token use and model differences.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing prompts for a new AI application
• Improving inconsistent model responses
• Defining JSON response formats