'hallucination' 검색 결과

Govern FriendlyBet agent values, professional standards, anti-hallucination behavior, truthfulness, risk reporting, AI resource discipline, feedback loops, skill improvement, performance reviews, decision-rights hygiene, and team quality. Use when creating, reviewing, promoting, correcting, or retiring agents; reducing hallucinations or mistakes; reviewing AI/tool usage; handling agent incidents; or aligning work with Eyal's philanthropic user-first approach.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Claude API (platform.claude.com) のプロンプトエンジニアリング・評価リファレンス。 prompt engineering, XML タグ, few-shot, system prompts, モデル別プロンプティング（Fable 5.1 / Fable 5 / Opus 5.5 / Opus 5 / Sonnet 5.5 / Sonnet 5 / Haiku 5.5）。 evals, grading（LLM-graded 等）, jailbreak・prompt leak 対策, hallucination 低減, classification, ticket routing, commerce agent 等ユースケース実装。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Validates agent outputs against expected schemas and quality criteria. Reports structural and content checks within the declared evidence scope. Activate on 'validate output', 'output validation', 'schema validation', 'check output', 'output quality'. NOT for confidence scoring (use dag-confidence-scorer) or hallucination detection (use dag-hallucination-detector).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

공개 전 글이나 코드를 두 독립 에이전트가 같은 기준으로 심사합니다. 모두 통과할 때까지 수정과 재심사를 반복하고, 반복 한도에 도달하면 미해결 문제를 사람에게 넘깁니다.

• 공개 전 글의 사실관계 확인
• 고객용 글과 브랜드 규칙 대조
• 운영 환경 배포 전 독립 심사 추가

Check important factual claims in courses or supplied content against available materials and authoritative sources. Review numbers, definitions, and contradictions, then receive a concise report with evidence and suggested corrections, or have generated course pages checked before delivery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking facts in a completed course
• Verifying important numbers and technical definitions
• Finding contradictions between course pages

Check factual claims in AI responses by extracting statements, searching for supporting or conflicting sources, and reviewing common error patterns. Receive a linked report that highlights uncertainties and helps people verify the evidence themselves.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check statistics and citations in an AI-generated report
• Add ongoing factual checks to a conversation
• Review legal explanations against linked sources

Create and run evaluations in Arize using an LLM as the judge. Define scoring criteria, connect them to actual data fields, evaluate recorded operations or experiment results, and set up continuous scoring for new data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Check answers for unsupported claims
• Score experiment results for correctness
• Continuously evaluate new production records

When a user corrects a factual error, trace it through stored knowledge, memory, identity settings, and fact records. Fix the underlying source, check related records where needed, and report the cause, changes, and safeguards against recurrence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Tracing the source of a repeated factual error
• Correcting mistaken facts about people or companies
• Updating outdated information and related records

Check that functions, methods, and imports exist in the software version being used before writing code. Identify uncertain calls, framework mix-ups, and deprecated interfaces so implementation decisions rely on verified details.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking functions against an installed library version
• Avoiding API mix-ups between frameworks
• Verifying package import paths before coding

Ask questions about documents in Google NotebookLM from Claude Code and receive source-grounded answers with citations. Manage a local notebook library, find notebooks by topic, and combine follow-up answers into a response.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find answers in uploaded documentation
• Register a notebook with a description and topics
• Search saved notebooks by topic

Guide Claude Code to check files, documentation, data, and execution results before presenting answers. The skill sets verification steps for coding, analysis, and writing, including checking citations and numbers, diagnosing errors, and clearly stating what cannot be verified.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking function names and arguments before coding
• Inspecting data columns and file paths before analysis
• Verifying row counts and missing values after joins

[omh] Audio, video, or screenshot to process: user-sent media - audio, video, YouTube links, screenshots, receipts, OCR, meeting recordings, transcripts, timestamps, and clip summaries, gated for source, permission, and hallucination risk. Use when the user says: media-input-operator, media input operator, media input, audio transcription, audio transcript, transcribe audio, transcribe this audio, meeting recording.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

[omh] Dataset or table to analyze: scope supplied data with provenance, causal-claim, and hallucination guards. Use when the user says: data-analysis, data analysis, dataset analysis, csv analysis, json analysis, log analysis, table analysis, analyze csv.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

[omh] Product or company copy to publish or rewrite: scope publish-ready writing, rewriting, summarization, translation, release-note, newsletter, customer-copy, social-copy, README-copy, and email-draft work with audience, tone, style, source, review, and hallucination gates. Use when the user says: content-operator, content operator, content workflow, writing workflow, publish-ready writing, publish ready writing, release notes, release note draft.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Memory integrity audit. Detects hallucinations, circular confirmations, and state poisoning. Runs automatically after 2 consecutive failures or at nightly deep dive. Uses Opus 4.6 as the auditor model.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Generates audit-grade, hallucination-free documentation from codebase features with full traceability. Use when documenting features, creating technical specs, or generating verified documentation with code references.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Make an AI agent or automation reliable enough to trust — the tests, checks, and guardrails that catch its failures before they reach anything real. Use when asked how do I test my AI agent, make my automation reliable, my agent works sometimes, or how do I trust an AI workflow in production. Produces a map of where the agent can fail (bad input, hallucination, wrong tool call, edge cases, silent errors), the checks that catch each (validation, evals on real cases, human-in-the-loop gates, monitoring), a right-sized reliability plan scaled to the stakes, and a rollout that earns trust incrementally.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Check AI output before you trust or use it — where it's likely wrong, what to verify, and how to catch confident-sounding errors. Use when asked can I trust this AI answer, how do I verify what AI told me, fact-check this AI output, or is this AI response reliable. Produces a risk read on the specific output (the claims most likely to be wrong or made up), the parts that need independent verification vs the parts that are low-risk, how to actually verify each, the tells of AI hallucination and overconfidence, and a habit for building verification into your AI use — because AI is confidently wrong often enough that unchecked trust is a real risk.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Monitor and evaluate RAG systems with retrieval quality metrics, groundedness checks, hallucination detection, and continuous regression testing.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Pre-publish QA framework for content. Brief adherence, voice consistency, fact accuracy, structure and clarity, AI-content audit, SEO and AEO compliance, internal linking and schema validation, QA at scale via sampling, the QA workflow, and the discipline that distinguishes catch-problems QA from checkbox QA. Triggers on editorial QA, content review, pre-publish review, content audit, content QA process, AI-content audit, hallucination check, content sampling, programmatic QA, voice consistency check, brief adherence check. Also triggers when a content team is shipping sloppy work, when AI-co-authored content is reaching publish unaudited, when a QA process burns reviewers out, or when a programmatic SEO set needs sampling discipline. On a voice consistency check, this skill owns checking a draft against an existing voice system at the publish gate; use `brand-voice` when the voice system itself needs defining or documenting.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tune eval thresholds: dimension minimums, weights, auto-reject floors. "raise the hallucination threshold"

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Design a structured protocol for auditing AI-generated text against Ennis's six CT standards. Use when students need to critically evaluate AI output in any subject.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.