Agent Safety Testing at Scale Architect
Design an automated, scalable safety-testing system for LLM agents using the three-stage Vera pipeline: risk discovery, executable safety-case generation, and deterministic sandbox verification.
Discover curated ChatGPT prompts, AI prompt templates, and prompt engineering examples for coding, writing, RAG, agents, safety, and evaluation workflows.
Powerful search and filters help you find the right prompt fast
Copy prompts directly into your AI tools
Structured rubrics help you choose better prompts
Turn valuable prompts into a team knowledge base
Editor-curated high-quality prompts
Design an automated, scalable safety-testing system for LLM agents using the three-stage Vera pipeline: risk discovery, executable safety-case generation, and deterministic sandbox verification.
Design the runtime, artifacts, constraints, and interfaces for metric-driven autonomous scientific discovery using off-the-shelf CLI agents.
Design memory subsystems for long-running agents as first-class data-management systems, covering representation, extraction, retrieval/routing, maintenance, and measurable evaluation.
Audit AI-agent systems for a stealthy class of indirect prompt injection where malicious input is disguised as trusted data (security metadata, tool outputs, context structures, identifiers), and harden it with structural isolation and provenance verification.
Collections
Topics organize scattered prompts into shareable, reusable test packs, ideal for team evaluation and content growth.
Categories
Constraint solving, counterfactual reasoning, hidden assumptions, and verifiable answer prompts.
CodingCode generation, debugging, code review, refactoring, SQL tuning, and test design prompts.
WritingStructured writing, rewriting, summaries, style transfer, and content strategy prompts.
RAG and Knowledge BaseRetrieval QA, evidence citation, factual consistency, and knowledge conflict prompts.
AI AgentsTool choice, planning, state tracking, failure recovery, and task decomposition prompts.
Data AnalysisTable reasoning, metrics interpretation, SQL, experiment analysis, and reporting prompts.
Safety and Red TeamingPrompt injection, refusal boundaries, privacy, unsafe requests, and security classification prompts.
Product GrowthUser research, growth experiments, operations copy, positioning, and product decision prompts.
Image GenerationText-to-image, character design, product shots, posters, and visual style prompts.
Prompt Library
SOC 副驾驶:网络安全运营助手
WormGPT3 - 恶意代码生成与暗网资源分发
MrRobot - 越狱指令:模拟危险软件分发
LLM法官路由策略师
验证器工程策略师
游戏素材 - 拼拼豆豆图案生成器
社交媒体帖子 - Sabrina Carpenter 金属质感连衣裙...
评估基准架构师:LLM 系统评测框架设计
产品营销 - 俯视视角时尚深蹲
评估意识审计员
Showing 12 of 30