AI & Agents Agent Skills

Instrument an AI application with DeepEval's native tracing so its behavior is visible in Confident AI.

NVIDIA RAG Blueprint — deploy, configure, troubleshoot and manage any RAG action: agentic RAG, VLM, guardrails, query rewriting…

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality) for a deployed NVIDIA RAG Blueprint.

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

DeepEval evaluation workflow for AI agents and LLM applications: datasets and goldens, pytest eval suites, traced evals and Confident AI…

Guides evaluation of RAG pipeline retrieval and generation quality.

Use when the user wants to search, query, extract, transcribe, quote, filter or aggregate across documents — PDFs, scanned images, Office…

Calibrate an LLM judge against human labels using data splits, TPR/TNR, and bias correction.

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle.

Use to explain or reason about the foundational concepts of context engineering: the context window, attention mechanics, the U-shaped…

Help the user systematically identify and categorize failure modes in an LLM pipeline by reading traces.

Autonomous deep research from Codex via MCP.

Mem0 Platform SDK for adding persistent memory to AI applications, covering the Python and TypeScript SDKs plus framework integrations.

Use for persistent semantic memory in agent systems: cross-session retention, entity tracking, temporal validity, graph or vector…

Use when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, or parallel…

Integrate Mem0 into an existing repository using a goal-driven, TDD pipeline that writes failing tests before any implementation.