Data & AI prompts
Prompt engineering, AI agents, data analysis and AI-assisted research workflows. Fill in the fields, then copy for Claude, ChatGPT or Gemini.
Optimize any prompt into a reliable one
Paste any draft prompt and get a short diagnosis of what's weak plus a rewritten, copy-ready version with a clear contract, single-owner rules, and an explicit output format.
Red-team your prompt for safety, bias & security before you ship it
Paste any prompt and get a dimension-by-dimension safety, bias, privacy, and injection review, plus a safer rewrite and three validation tests you can run before it goes live.
Interview me, then write a production system prompt for my AI agent
A paste-and-go ChatGPT prompt that interviews you about your AI agent, then writes a complete, production-ready system prompt for it — with the design rationale and test cases to prove it works.
Design my RAG pipeline: chunking, embeddings, and retrieval plan
An interview-style AI prompt that questions you about your documents, your users, and your constraints, then delivers a complete, buildable RAG pipeline plan — chunking strategy, embedding model, retrieval, reranking, and evaluation.
Turn my plain-English question into a runnable SQL query
A paste-and-go ChatGPT prompt that turns any plain-English question into a correct, read-only SQL query for your exact database: it learns your schema and dialect, clears up ambiguous wording, then hands you a runnable query with every assumption spelled out.
Give me a data-analysis plan from my dataset and business question
A paste-and-go prompt that interviews you about your dataset and business question, then writes an execution-ready data-analysis plan — with the right method, the data-quality checks to run first, and the traps to avoid.
Build a few-shot example set that teaches the model my task
A paste-and-go prompt that interviews you about your task, then creates a curated set of few-shot examples — balanced, edge-case-covered, and ready to paste above your real inputs — that teaches a model to do the task reliably.
Spec my dashboard: the right charts for my metrics and audience
An AI dashboard designer that interviews you about your audience, metrics, and data, then hands you a build-ready spec mapping every metric to the right chart type and a layout tuned to the decision it drives.
Write the exact spreadsheet formula from a plain-English description
Turn a plain-English description of what you want to calculate into a correct, copy-paste-ready Excel or Google Sheets formula — with a plain-English breakdown and an older-version fallback.
Design my AI agent spec: tools, memory, guardrails, and loop
A paste-and-go prompt to design an AI agent architecture: it interviews you one question at a time, then produces a build-ready spec covering the agent's job, tools, memory, control loop, and safety guardrails.
Build an LLM eval rubric and test set for my AI feature
An interview-style prompt that helps you create an LLM eval rubric, a stratified test set, and an LLM-as-a-judge scoring prompt for one AI feature — so you catch quality regressions before your users do.
Make me a cleaning plan for my messy dataset
A paste-and-go prompt that profiles your messy dataset, then writes a prioritized, tool-agnostic plan to clean it — fixing missing values, duplicates, bad data types, and inconsistent categories.
Advise me which LLM and setup fits my use case and budget
A vendor-neutral AI advisor that interviews you about your task, volume, latency, budget, and privacy, then recommends which LLM model and deployment setup to use — with a cost estimate you can re-run yourself.
Design my fine-tuning dataset: format, schema, and examples
A paste-and-go prompt that interviews you about your task, then designs a complete fine-tuning dataset: the right format for your platform, a field-by-field schema, worked JSONL examples, a coverage plan, and a pre-flight checklist.
Plan my multi-agent workflow: roles, handoffs, and orchestration
Designs a multi-agent system by interviewing you about the work, then delivering a buildable blueprint — agent roles, handoff contracts, decision gates, and failure handling — you can implement in any framework.
Spec a synthetic test dataset that covers my edge cases
This paste-and-go prompt interviews you about your schema and system, then generates a synthetic test data spec — a field dictionary, edge-case catalog, coverage matrix, seeded generation plan, and privacy-safe sample rows — so your tests hit the boundaries that actually break code.