LLM Evaluation Framework Builder
Build a framework to evaluate LLM outputs — accuracy, relevance, safety, cost, latency, and A/B comparison tes...
Browse and customize AI prompt templates for ChatGPT, Claude, Midjourney, and more. Copy-ready prompts with fillable placeholders.
Build a framework to evaluate LLM outputs — accuracy, relevance, safety, cost, latency, and A/B comparison tes...
Design a multi-agent AI system — agent roles, communication patterns, task decomposition, and human-in-the-loo...
Generate a code audit checklist based on OWASP Top 10 2021 — with specific code patterns to check, fix example...
Design and implement a Zero Trust security architecture — identity verification, network segmentation, least p...
Implement secret management — vault setup, automatic rotation, access policies, audit logging, and emergency c...
Design a normalized database schema from business requirements — tables, relationships, indexes, constraints,...
Optimize slow SQL queries step by step — EXPLAIN analysis, index strategies, query rewriting, and caching for...
Design a complete database backup and recovery strategy — automated backups, point-in-time recovery, cross-reg...
Design a Git branching strategy tailored to your team size, release cadence, and deployment model — GitFlow, t...
Generate production-ready GitHub Actions workflows for testing, building, and deploying your application with...
Get step-by-step guidance to resolve complex Git merge conflicts with context-aware strategies and prevention...
Generate a comprehensive PR review checklist tailored to your tech stack, covering code quality, security, per...