Product Marketing - Mediterranean Male Sun-Drenched Portrait
An editorial-style photograph of a Mediterranean man in a linen shirt, featuring high contrast shadows and an elegant European summer vibe.
3008 Curated Prompts
Discover curated ChatGPT prompts, AI prompt templates, and prompt engineering examples for coding, writing, RAG, agents, safety, and evaluation workflows.
Editor-curated high-quality prompts
An editorial-style photograph of a Mediterranean man in a linen shirt, featuring high contrast shadows and an elegant European summer vibe.
A cinematic close-up portrait prompt focusing on eyes and lips, featuring a subject lying among sunflowers with a film-grain aesthetic.
A detailed 3D stylized rendering of a cartoon girl with emerald eyes and platinum-blonde hair, sitting in a dreamy pose on a stone stool.
A high-end food photography prompt designed to create appetizing commercial visuals of loaded beef tacos with cinematic studio lighting.
Ranked by site-wide copy counts; falls back to editor picks when empty
A striking close-up fashion editorial prompt featuring futuristic minimalism, sleek styling, and sharp studio lighting.
Prompt Library
A highly detailed, documentary-style prompt for a realistic portrait of a person sitting on the veranda of a traditional Japanese house in summer.
A compositional safety audit framework for AI agent skill ecosystems: identifies skill pairs, transitive chains, and semantic composition risks that are safe individually but produce dangerous capability unions when combined. Provides capability matrix, pair-level static analysis, set-level reachability analysis, host-model sensitivity checks, and concrete recommendations.
A creative photography prompt where a subject holds a Pixar-style miniature version of themselves, utilizing image reference and bokeh backgrounds.
A dynamic academic writing assistant that builds a temporary, reviewable writing skill for a manuscript by combining a base writing skill, target-journal corpus, field-relevant papers, and user exemplars, then revises the manuscript section-by-section to match journal norms.
Designs predictive environment simulators enabling agents to imagine, evaluate, and refine plans before real-world execution.
Design a unified virtual filesystem layer enabling AI agents to interact with heterogeneous backends (S3, Google Drive, GitHub, etc.) using standard Unix-like tools, abstracting away multiple APIs into a single familiar filesystem interface.
Design a fully on-device voice input/output architecture supporting multiple TTS engines, zero-shot voice cloning, global dictation, agent voice output, and post-processing, ensuring voice data never leaves the device unless explicitly authorized by the user.
Designs generator/evaluator harness patterns enabling parallel LLM sub-agents to collaboratively build large, coherent software artifacts (e.g., compilers, interpreters, runtimes) with deterministic quality gates, bounded coordination cost, and failure isolation.
Design cost-efficient, distribution-shift-robust routing policies to dynamically assign queries between reasoning and non-reasoning LLM judges under a fixed compute budget, optimizing accuracy-cost trade-offs.
Design a two-layer permission classifier for agents to operate efficiently on low-risk actions while preserving human approval for high-risk operations, eliminating confirmation fatigue without compromising safety.
Evaluate whether structural prompt compression (e.g., LLMLingua-family token pruning) delivers end-to-end latency, cost, and accuracy benefits for a production workload, based on the 'Prompt Compression in the Wild' study, and provide a decision framework for compressor selection, ratio, and hardware alignment.
Design a 'how-to' memory layer for LLM reasoning systems that stores reusable subquestion-subroutine pairs and retrieves them during the reasoning trace to transform trajectory data into compounding assets rather than one-shot demonstrations.
Showing 12 of 27