Tagged llm

Score agent responses from 0 to 10 for helpfulness, accuracy and clarity

Guide hands-on web and AI security tests with case studies and OWASP LLM risks

Choose an LLM serving stack and memory flags for Jetson devices

Benchmark LLM and VLM serving on Jetson across vLLM, llama.cpp and Ollama

Stand up vLLM or SGLang model serving on Jetson boards

Wrap LLM and tool calls with NeMo Relay scopes for events and guardrails

Fine-tune any Hugging Face vision, VLM or LLM model on local NVIDIA GPUs

Run TAO AutoML hyperparameter search with Bayesian, ASHA, BOHB or LLM methods

Call OpenRouter LLM APIs with streaming and web search from a PinMe Worker

Check whether robots.txt lets AI answer engine crawlers read your site

Explain LLM wiki architecture and make knowledge base setup and schema decisions

Score skills with deterministic checks plus LLM review and gate merges on a threshold

Migrate OpenAI, Gemini and Anthropic API code to Amazon Bedrock and test output

Let LLMs run generated TypeScript in sandboxed isolates with snippet libraries

Get type-safe JSON responses from LLMs with Zod, ArkType or Valibot schemas

Define isomorphic LLM tools with Zod schemas and approval flows

Generate llms.txt and llms-full.txt files for LLM-readable project docs

Score the sentiment of financial text with FinBERT or an LLM

Generate and test scientific hypotheses from datasets with large language models

Configure and run agents through different LLM adapters and switch providers

Run several LLMs in a council that ranks answers and synthesizes one result

Guard commits and code conventions with LLM-checked prompt hooks

Build a persistent, interlinked markdown wiki from sources you ingest and query

Run a decision through five AI advisors that peer review each other for a verdict

Build and maintain a personal LLM wiki from raw sources with citations and linting

Test LLM apps for prompt injection, indirect RAG attacks and MCP tool abuse

Build and maintain a personal wiki knowledge base from web pages, PDFs and notes

Upgrade an existing llm-wiki install to the latest GitHub release

Search the web with Tavily's LLM-optimized API for snippets and relevance scores

Design agent context, memory and token budgets for multi-agent systems and LLM pipelines

Fetch current library docs from llms.txt files and GitHub repositories

Log LLM runs with per-turn transcripts, token costs and run comparison reports

Cut LLM API costs with task-based model routing, budgets, retries and caching

Choose between regex and an LLM to parse structured text, LLM only for edge cases

Generate and test hypotheses on tabular datasets with LLM-driven exploration

Replay LLM request traces against a KV prefix cache to measure hit rates

Build production LLM apps with RAG, vector search, multimodal AI and agents

Build LLM apps and agents with LangChain memory, tools and workflow patterns

Design conversational assistants with context management and LLM integration

Build production LangChain and LangGraph agents with tools and memory

Evaluate and improve LLM prompts with examples and measured comparisons

Apply prompt patterns to improve LLM reliability, output quality and control

Test LLM and RAG systems for system prompt leaks, data extraction and poisoning

Solve CTF challenges on adversarial examples, model extraction and LLM jailbreaks

Test LLM apps for indirect prompt injection through web pages and documents

Test LLM apps for system prompt leaks and exposed tool lists

Run a task through a sub-agent and retry it until an LLM judge approves the result

Implement a task step by step with an LLM judge checking each phase

Write and optimize prompts for commands, skills, sub-agents and other LLM calls