Results for “llm-prompting”

Wire Promptfoo and DeepTeam into CI/CD for automated regression red-teaming of LLM apps against OWASP LLM Top 10 and OWASP Agentic presets, failing the build when jailbreak or injection vulnerabilities regress.

Learn and apply prompt engineering techniques for LLMs, image generators, and video models using the inference.sh CLI.

Test LLM applications for system prompt leakage using manual payloads, garak, and Promptfoo to extract embedded secrets and routing logic.

Detect prompt injections and jailbreak attempts in LLM applications using Meta's 86M parameter classifier. Filter user inputs, third-party data, and RAG documents with low latency and multilingual support.

Routes prompts to any LLM model across multiple providers via CLI tools or APIs, with auto-discovery of new models and benchmark data.

Designs, optimizes, and evaluates prompts for LLMs, including structured outputs, chain-of-thought, and evaluation frameworks.

Designs and optimizes prompts for LLM-powered applications, covering system prompt architecture, context management, output formatting, and evaluation.

Guides project-level decisions for LLM-powered systems: task-model fit, pipeline architecture, token and cost estimation, and agent-assisted iteration.

Provides expertise in Langfuse for LLM observability, including tracing, prompt management, evaluation, and integration with LangChain, LlamaIndex, and OpenAI.

Deploy Llama Guard, NeMo Guardrails, and LLM Guard as runtime input/output scanners to block jailbreaks, prompt injection, and toxic content in production LLM applications.

Guides building production-grade AI features with LLM integration patterns, RAG architecture, prompt engineering, and cost optimization.

Provides guidance and code for production AI workflows including RAG pipelines, vector databases, embedding indexing, prompt engineering, cost estimation, semantic caching, and quality evaluation.

Convert human-written CLAUDE.md files into a structured label format that AI models follow more reliably using fewer tokens.