875 个 · 按相关度排序
Configure OpenTelemetry to send AI application traces, records of execution steps, to Confident AI. Reuse existing exporters, choose the regional endpoint, and add AI-specific attributes without requiring the deepeval Python package.
中文简介正在准备中。当前显示英语简介。
Add DeepEval tracing to Python AI applications so execution steps appear in Confident AI. Choose a supported integration or manual @observe instrumentation, then capture inputs, outputs, step types, tags, and metadata.
中文简介正在准备中。当前显示英语简介。
Inspect suspicious PDFs without opening them in a reader. Use PDFiD, pdf-parser, and peepdf to examine internal objects, extract scripts, embedded files, and URLs, and document how the suspected attack works.
中文简介正在准备中。当前显示英语简介。
Build repeatable DeepEval tests for AI agents, chatbots, and applications that retrieve documents to answer questions. Reuse or generate evaluation datasets, inspect failures, and improve prompts, tools, or retrieval through repeated evaluation runs.
中文简介正在准备中。当前显示英语简介。
Assigns confidence scores to agent outputs based on multiple factors including source quality, consistency, and reasoning depth. Produces calibrated confidence estimates. Activate on 'confidence score', 'how confident', 'certainty level', 'output confidence', 'reliability score'. NOT for validation (use dag-output-validator) or hallucination detection (use dag-hallucination-detector).
中文简介正在准备中。当前显示原文说明。
Inspect suspicious PDFs without opening them in a document viewer. Use peepdf, pdfid, and pdf-parser to examine internal objects, extract embedded code and files, and report threat indicators such as URLs and hashes.
中文简介正在准备中。当前显示英语简介。
Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.
中文简介正在准备中。当前显示原文说明。
Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.
中文简介正在准备中。当前显示原文说明。
Use when assigning a confidence level to an analytical judgment, the user asks "how confident are we?" / "what is the confidence on X?", or the orchestrator's tradecraft pipeline calls for a confidence level before publishing. Provides three named levels (High, Moderate, Low) with 0-100 score ranges aligned to STIX, and the rule that confidence cannot exceed what the weakest load-bearing claim supports.
中文简介正在准备中。当前显示原文说明。
Expert knowledge for Azure Confidential Ledger development including troubleshooting, decision making, security, integrations & coding patterns, and deployment. Use when configuring ACL auth/attestation, integrating with Blob/Cosmos, using MST payloads, or deploying via ARM/Terraform, and other Azure Confidential Ledger related development tasks. Not for Azure Confidential Computing (use azure-confidential-computing), Azure Key Vault (use azure-key-vault), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Payment Hsm (use azure-payment-hsm).
中文简介正在准备中。当前显示原文说明。
Guides compliance with India's Digital Personal Data Protection Act 2023. Covers consent manager registration, data fiduciary obligations under Sections 4-7, significant data fiduciary requirements under Section 10, data principal rights, and Board enforcement framework. Keywords: DPDP Act, India data protection, consent manager, data fiduciary, significant data fiduciary, data principal rights.
中文简介正在准备中。当前显示原文说明。
Process calibrated one-dimensional NMR signals into spectra, candidate peaks, and signed integration results. Supports manual phase adjustment, baseline correction, and recorded processing settings so results can be reviewed and reproduced.
中文简介正在准备中。当前显示英语简介。
Generate candidate positions and orientations for small molecules binding to proteins with DiffDock and DiffDock-L. Prepare single or batch docking runs, organize predicted poses by model confidence, and review validation needs without treating confidence as binding affinity.
中文简介正在准备中。当前显示英语简介。
Compare evidence from cyber operations to assess which attacker may be responsible. Weigh shared infrastructure, attack methods, malware similarities, timing, and language clues against competing explanations, then report attribution findings with justified confidence levels.
中文简介正在准备中。当前显示英语简介。
Expert knowledge for Azure Confidential Computing development including decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using SGX/SEV-SNP, AKS confidential containers, attestation/SKR, Fortanix CCM, or SGX capacity planning, and other Azure Confidential Computing related development tasks. Not for Azure Enclave (use azure-enclave), Azure Dedicated HSM (use azure-dedicated-hsm), Azure Cloud Hsm (use azure-cloud-hsm), Azure Payment Hsm (use azure-payment-hsm).
中文简介正在准备中。当前显示原文说明。
Reads model uncertainty from token log-probabilities. Covers collecting logprobs and aggregating multi-token labels, confidence tiers and margins for triage, calibration assessment with ECE, Brier scores, and reliability diagrams against human labels, responsible downstream use of confidence, and reproducibility archives. Use when the user asks about classifier confidence by item, logprobs, top-k tokens, calibration, ECE, Brier, reliability diagrams, or routing low-confidence cases to human review. Codebook and validation design go to text-classification.
中文简介正在准备中。当前显示原文说明。
VRChat エコシステムツール（ModularAvatar / liltoon / VRCFury / AvatarOptimizer 等）の ナレッジを 4 フェーズで段階的に調査・検証し `knowledge/*.md` に再現可能な形で蓄積する。 ソースコード読解 → inspect 実測まで進めると confidence を `high` に昇格できる。 トリガー: 新しい VRChat コミュニティツールに初めて遭遇した、 既存ナレッジの confidence が low で作業に支障がある、 ユーザーから「このツールについて調べて」と依頼された場合。
中文简介正在准备中。当前显示原文说明。
帮助设计表单、发票和题集的信息提取流程，先用正则表达式提取并清理文本，再评估置信度，仅将不确定的条目交给LLM检查和修正，同时介绍测试与指标记录。
用于处理Paperclip的非公开漏洞报告，涵盖调查、私有分支中的修复验证、CVE申请、安全公告发布，以及紧急版本发布后的确认。
将HTML生成的PPTX与源文件对照，检查文字裁切、页脚重叠及斜体丢失等问题。整理原因，调整布局规则，再次导出并验证是否越界。
Assess a repository without changing it and report its type, suggested agent roles, risk, MCP connections, test confidence, and publication readiness. Use the results for setup decisions, comparisons over time, or automated risk checks in CI.
中文简介正在准备中。当前显示英语简介。
Design a role permission matrix showing which business areas each role should view or edit, including confidentiality levels. Get a review workflow and, on request, empty CSV templates, SQL table definitions, JSON Schema, or Notion mappings.
中文简介正在准备中。当前显示英语简介。
Draft a Confidential Information Memorandum, a detailed company document for prospective buyers in an M&A sale. Organize business, market, customer, and financial information into a Word document with charts and a separate Excel financial appendix.
中文简介正在准备中。当前显示英语简介。
Set up Cisco Duo multi-factor authentication for VPN, RDP, SSH, and web applications. Configure access rules based on users and device health, introduce security keys, and establish authentication monitoring and emergency access procedures.
中文简介正在准备中。当前显示英语简介。