「dag」の検索結果

Método da Anthropic para treinar IA inofensiva através de auto-aprimoramento. Abordagem em duas fases - aprendizado supervisionado com auto-crítica/revisão, depois RLAIF (RL from AI Feedback). Use para alinhamento de segurança, redução de outputs prejudiciais sem rótulos humanos. Alimenta o sistema de segurança do Claude.

日本語の概要は準備中です。原文の説明を表示しています。

Expert em LangGraph - o framework de nível produção para construir aplicações de IA com múltiplos atores e estado. Aborda construção de grafos, gerenciamento de estado, ciclos e ramificações, persistência com checkpointers, padrões human-in-the-loop e o padrão ReAct. Usado em produção no LinkedIn, Uber e 400+ empresas. Esta é a abordagem recomendada pelo LangChain para construir agentes. Use quando: langgraph, langchain agent, stateful agent, agent graph, react agent.

日本語の概要は準備中です。原文の説明を表示しています。

Framework de pré-treinamento visão-linguagem que conecta codificadores de imagem congelados e LLMs. Use quando você precisar de legendagem de imagens, resposta a perguntas visuais, recuperação imagem-texto ou chat multimodal com desempenho zero-shot de última geração.

日本語の概要は準備中です。原文の説明を表示しています。

Use when the user starts a non-trivial coding/building task in Claude Code (e.g. "帮我做个 X", "help me build Y", "add feature Z", "搭一个 Z"). Layers an AI-native pedagogical coat over normal coding work — surfaces implicit assumptions in user intent, annotates non-trivial design decisions inline with brief concept-scaffolding for terms the user may not know, and replaces "should I run it?" handoffs with rigorous AI self-verification plus a clean list of what only the user can verify. Skip for pure Q&A, single-line edits, read-only investigation, or refactoring along an existing pattern.

日本語の概要は準備中です。原文の説明を表示しています。

Guide users through a 6-phase pipeline to plan a complete project — from brainstorming through project metadata to blueprint, starter-file generation, and per-milestone micro-task design with inline pedagogical choreography.

日本語の概要は準備中です。原文の説明を表示しています。

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

日本語の概要は準備中です。原文の説明を表示しています。

Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.

日本語の概要は準備中です。原文の説明を表示しています。

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

日本語の概要は準備中です。原文の説明を表示しています。

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

日本語の概要は準備中です。原文の説明を表示しています。

Apache Airflow, dbt, Prefect, Dagster, and modern data orchestration for production data pipelines

日本語の概要は準備中です。原文の説明を表示しています。

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

日本語の概要は準備中です。原文の説明を表示しています。

Develops an implementation plan ready for wave-orchestration to execute. Takes the user's goal or rough plan as input, mines the codebase for facts, grills the user one question at a time for the decisions, drafts the planning/ artifacts (task DAG, wave table, worker prompt template, state file), then reviews its own plan on two axes before seeking approval. Use when the user wants to turn a feature idea, master plan, or backlog into a wave-orchestration execution plan.

日本語の概要は準備中です。原文の説明を表示しています。

Authors reproducible bioinformatics pipelines with Snakemake - rules wired by output-file pattern, wildcards and expand() for sample fan-out, checkpoints for runtime-unknown outputs, resource/retry escalation, and conda/container software deployment on HPC and cloud. Use when deciding rule-based (Snakemake) vs channel/dataflow (Nextflow) authoring; wiring rules by OUTPUT-file pattern rather than imperative order; using wildcards + expand() for sample fan-out and constraining them to stop silent mis-routing; adding checkpoints when the set of outputs is unknown until a step runs (dynamic DAG); diagnosing why a job reran (or did not) under the mtime-plus-provenance trigger set; escalating memory on retry for OOM-killed jobs; and porting a Snakemake 7 `--cluster`/remote-provider command to the Snakemake 8+ executor-plugin and storage-plugin model (snakemake-executor-plugin-slurm) with `--software-deployment-method`.

日本語の概要は準備中です。原文の説明を表示しています。

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

日本語の概要は準備中です。原文の説明を表示しています。

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

日本語の概要は準備中です。原文の説明を表示しています。

ABP Framework domain layer patterns including entities, aggregates, repositories, domain services, and data seeding. Use when: (1) creating entities with proper base classes, (2) implementing custom repositories, (3) writing domain services, (4) seeding data.

日本語の概要は準備中です。原文の説明を表示しています。

RFC-driven multi-agent DAG execution pattern with quality gates, merge queues, and work unit orchestration.

日本語の概要は準備中です。原文の説明を表示しています。

Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

日本語の概要は準備中です。原文の説明を表示しています。

Build container-based Foundry Agents with Azure AI Projects SDK (ImageBasedHostedAgentDefinition). Use when creating hosted agents with custom container images in Azure AI Foundry.

日本語の概要は準備中です。原文の説明を表示しています。

dbt Core/Cloud data transformations, testing, documentation, and CI/CD. Activate on: dbt, data transformation, analytics engineering, ref, source, staging model, mart, dbt test. NOT for: orchestration/scheduling (use airflow-dag-orchestrator), data warehouse tuning (use data-warehouse-optimizer).

日本語の概要は準備中です。原文の説明を表示しています。

Classify every destructive/gated action an agent body can attempt (git, filesystem, network, shell, github) into block/approve/allow tiers, and audit whether the pre-tool and post-tool governance backing that classification is real: blocked actions proven zero-side-effect by a negative fixture, every denial backed by a receipt and a transcript event, every block-tier denial paired with a safe alternative, and no unmanaged or same-UID body ever marked "contained." Use when building or reviewing Agent Harbor's C5 governance gate (destructive git blocker, approval request/result, denial receipts), gating a new tool surface before it can run destructive commands, or auditing whether an existing "destructive-action blocked" claim actually has evidence behind it. NOT for proving an existing sandbox boundary actually contains an adversary once an action is isolated (use sandboxed-adversarial-test-harness), deciding where in a DAG to place a human review node or designing the approval UX itself (use human-gate-designer), or designing the general work-receipt schema across an entire agent task (use agent-work-receipt-designer).

日本語の概要は準備中です。原文の説明を表示しています。

Tracks cumulative LLM costs across DAG execution and makes real-time decisions to stay within budget. Downgrades models, skips optional nodes, or stops early when cost exceeds thresholds. Use when managing execution budgets, analyzing cost breakdowns, or optimizing model routing for cost. Activate on "cost budget", "too expensive", "reduce cost", "cost optimization", "model downgrade", "budget exceeded". NOT for LLM model selection logic (use llm-router), pricing comparisons across providers, or billing/invoicing.

日本語の概要は準備中です。原文の説明を表示しています。

Produces a narrow-interval quality signal for a WinDAGs skill that a third party can verify without inspecting model weights or method internals. The mechanism is attribution-kNN over a tamper-evident outcome log (task→skills→accept/reject store), combined with a conformal-prediction calibration certificate that provides a formal coverage guarantee. Thompson/Beta sampling is explicitly rejected as a category error: it produces a selection signal for stationary i.i.d. rewards, not an attestation signal for context-dependent LLM output quality. The resulting bundle — outcome-log Merkle root + conformal threshold + optional TEE guardrail signature — constitutes a "narrow-interval trust" credential: verifiable, bounded, and internals-opaque.

日本語の概要は準備中です。原文の説明を表示しています。

Design a normalized, machine-readable "work receipt" that answers what changed, why, by whom, and with what validation, for any AI-coding-agent task regardless of backend (Claude Code, Codex, Cursor, Aider, CI, or homegrown). Use when defining a receipt schema, normalizing heterogeneous agent logs into one evidence shape, gating PR merges on artifact-backed proof, or designing an OSS maintainer's fast-reject/fast-merge workflow. NOT for validating a DAG node's output against its own schema (use output-contract-enforcer), continuous runtime monitoring of a live coordination daemon (use runtime-verification-for-agents), or general Port Daddy claims/notes/salvage mechanics (use port-daddy-agent-skill).

日本語の概要は準備中です。原文の説明を表示しています。