Copy · adapt · ship
AI prompt library
Reusable prompt templates for production workflows, organized by use case, model fit, difficulty, and guardrails.
Any tool-using chat LLM
Prompt-injection resistant assistant
System prompt that treats retrieved docs, tickets, and web pages as untrusted data. Use in multi-tenant RAG and browsing agents. This is a defensive template, not an attack or bypass playbook.
Grok Bot, computer-use capable models
Computer-use agent with approval gates
System prompt for browser/desktop agents (Grok Bot, computer-use tools). Allows research and drafts, but pauses before send, purchase, delete, or production changes. Not a jailbreak or bypass guide.
GPT-5.5, Claude, Gemini after Whisper / Gemini 3.5 Transcribe / MAI-Transcribe
Transcript to summary and action items
Turn a speech transcript into decisions, owners, and follow-ups. Use after Gemini 3.5 Transcribe, Whisper, or MAI-Transcribe. Do not use on raw audio; transcribe first.
MAI-Image 2.5, Qwen-Image 3.0, SDXL, Firefly, Midjourney
Product image generation prompt
A reusable image prompt for catalog and hero shots: subject, lighting, lens, negative constraints, and text-in-image rules. Works with Firefly, Midjourney, MAI-Image, Qwen-Image, and SDXL. Not for photorealistic people or brand-logo cloning.
Any strong chat LLM used as a judge
LLM output evaluation rubric
Judge a model answer against a task, retrieved evidence, and pass/fail thresholds. Use for golden-set grading and regression evals. Not a substitute for human review on high-risk decisions.
Models with JSON / structured-output support (GPT-4o, GPT-5.5, Gemini, Claude)
Strict JSON extraction prompt
Extract structured fields into JSON that matches a schema. Pair with provider structured-output / JSON-schema modes when available. Do not use when the output is meant to be prose.
Cursor Composer, Claude Code, GPT-5.5, Claude Fable 5
Repo-aware coding agent system prompt
System prompt for Cursor, Claude Code, or similar coding agents. Prefers small diffs, tests, and existing repo patterns. Do not use for greenfield architecture brainstorming with no codebase.
Any chat LLM with a retriever (GPT-5.5, Claude, Gemini, Bedrock)
Grounded RAG answer with citations
Copy-ready system prompt for retrieval-grounded answers. Use when the model must cite retrieved chunks, refuse empty retrieval, and never invent sources. Skip it for open-ended brainstorming with no corpus.
Amazon Bedrock
Model Evaluation Rubric for Production LLMs
A repeatable rubric for comparing production LLM candidates across quality, latency, cost, tool use, safety, and operational fit.
Amazon Bedrock
Vector Embedding Pipeline for Enterprise RAG
A design template for enterprise embedding pipelines covering chunking, metadata, tenancy, indexing, refreshes, and retrieval evaluation.
Amazon Bedrock
RAG Pipeline System Prompt Template
A production system-prompt template for retrieval-grounded answers with citation, access-control, and empty-retrieval handling rules.
Amazon Bedrock
Bedrock Converse API Integration Pattern
An implementation checklist for Bedrock Converse API integrations covering model IDs, retries, streaming, tool calls, IAM, and observability.
GPT-4
API Error Triage Workflow
A structured approach to identifying, categorizing, and resolving API errors in production systems.
MarketingGPT-3
Marketing Landing Copy Variants - Optimized
Generates multiple variants of marketing landing page copy for A/B testing.
SalesGPT-3
Sales Discovery Questions Framework - Tailored
Generates customized discovery questions for sales calls to uncover client needs.
RecruitGPT-3
Data Pipeline Debugging Protocol - Comprehensive
Evaluates candidates for machine learning positions based on technical and soft skills.
SupportGPT-3
Empathetic Support Ticket Reply Generator - Advanced
Generates replies to customer support tickets with a focus on empathy and resolution.
LegalGPT-3
Contract Clause Extraction - Extended
Extracts key clauses from legal contracts with enhanced accuracy.
GPT-4
HR Policy Q&A Framework with Citations
A framework for generating HR policy-related questions and answers with references to legal statutes or company guidelines.
GPT-4
ML Role Interview Evaluation Criteria
A detailed rubric for evaluating candidates for machine learning roles, focusing on technical and interpersonal skills.
GPT-4
Data Pipeline Debugging Protocol
A structured approach to identifying and resolving issues in data pipelines, ensuring data integrity and reliability.
GPT-4
Empathetic Support Ticket Response Strategy
A framework for crafting empathetic replies to customer support tickets, enhancing customer satisfaction and retention.
GPT-4
ML Role Interview Rubric
A structured rubric designed for evaluating candidates in machine learning roles.
GPT-4
SQL Explain-from-Schema Analysis
Tool for understanding SQL queries based on schema details.