191 prompts
Multi-step prompts for planning, tool choice, state tracking, and action boundaries.
Design, measure, and improve the reliability of AI agent systems—distinct from capability. Based on 2026 research, emphasizes stability under repeated runs, perturbed inputs, and fault injection across four dimensions: consistency, robustness, predictability, and safety/fault tolerance.
Design autonomous agent systems that learn from experience, persist knowledge across sessions, and grow more capable over time without manual prompt engineering. Includes skill ecosystem, multi-platform gateway, model-agnostic layer, and safety governance.
Design an end-to-end open-source deep research agent system that competes with closed commercial offerings (e.g., OpenAI Deep Research). The agent must answer complex, multi-hop questions over the open web with verifiable citations, long-horizon planning, and reproducible runs. This includes data pipeline, training recipe, inference modes, tool stack, evaluation harness, deployment topology, and governance.
An AI-powered video editing engineer specializing in post-production workflows using ffmpeg, Python (PIL), and structured EDLs. It reasons over transcripts, waveforms, and frames to make precise cuts, apply color grading, add animations, and generate subtitles — all while adhering to production-grade correctness rules such as audio-first cutting, subtitle-last application, and parallel animation rendering.
A specialist in designing privacy-first, offline-capable, and hardware-efficient AI systems that run at the edge, covering heterogeneous platforms like Apple Silicon, Qualcomm Snapdragon X Elite, and consumer GPUs.
Design a dynamic context management system for long-horizon agents that selectively preserves, compresses, rolls back, and deletes context to control growth, reduce hallucination, and improve reasoning efficiency.
Audits and hardens multi-turn agent systems against silent reasoning compression (Reasoning Drift) caused by growing context, using hard probes, CoT instrumentation, and tiered mitigations to preserve reasoning quality on complex tasks.
Design interleaved reasoning strategies for streaming autoregressive LLM interfaces to balance reasoning accuracy and user-perceived latency.
Based on the three-layer framework from arXiv 2603.14248 (April 2026) — High-level Planning, Low-level Grounding, and Replanning — this diagnostician localizes failures in GUI/web agent trajectories to provide targeted, actionable fixes rather than generic improvements.
A multimodal agent capable of sustained visual and textual search over up to 100 turns, with emphasis on context preservation, on-demand image loading, and evidence provenance.
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 multi-agent system using LLMs from different vendors to exploit divergent inductive biases, improving performance on high-stakes, ambiguous, long-tail tasks by exposing and arbitrating disagreements rather than averaging them.
Design AI agent systems with architecturally separated planning and execution to prevent irreversible harm from prompt-based jailbreaks or unauthorized actions.
Design and audit LLM agents capable of long-horizon planning by avoiding greedy stepwise reasoning, using explicit lookahead search, reward estimation, and replanning mechanisms for robust multi-step decision-making.
Design a lightweight, signal-based filtering system to identify high-value agent execution traces from production-scale logs for evaluation, debugging, skill mining, or safety review—without requiring ground-truth labels.
Guides AI coding agents on how to author efficient, safe, and executable AGENTS.md files for code repositories, serving as the core reference for agent operations.
Design a self-referential meta-agent where the task layer and meta layer coexist in a single editable program, capable of rewriting each other under bounded supervision. Applicable to code generation, paper review, robotics, and olympiad math.
A comprehensive guide to creating professional-grade audio using generative AI tools like Suno, Udio, ElevenLabs, and Stable Audio, covering genre control, instrumentation, vocal design, production terminology, and platform-specific prompt templates.
Generate a concrete, actionable implementation plan grounded in thorough analysis of an existing codebase, including problem framing, impact assessment, option comparison, and recommended path.
A binding engineering policy for AI coding agents based on 'The Pragmatic Programmer', emphasizing ownership, DRY at the knowledge level, orthogonality, fast feedback, and automation.
This prompt defines a meta-cognitive agent role focused on judiciously deciding whether to invoke external tools, emphasizing avoidance of over-tooling, assessment of knowledge gaps, cost and risk control, and ensuring each tool call reduces uncertainty meaningfully.
A disciplined diagnosis loop for hard bugs and performance regressions: reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says 'diagnose this' / 'debug this', reports a bug, says something is broken/throwing/failing, or describes a performance regression.
Prompt Guru V5 is an infinitely adaptive AI framework designed to continuously transcend capability boundaries through self-optimization and perpetual learning, while ensuring its core principles remain immutable under all conditions.
This prompt guides the AI to act as an advanced, empathetic, and effective psychological therapist, emphasizing active listening, emotional validation, and gradual problem-solving for supportive mental health conversations.