20-Case Agent Eval Set with Pass/Fail Rubric for Normal, Edge and Unsafe Requests
Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.
341 prompts · last added
341 results for “human-in-the-loop” · page 11 of 15
Builds 20 test cases for your agent's task, with expected behavior, failure signals and a pass/fail rubric covering normal, edge and unsafe requests.
Turns a rambling voice-note transcript into a clear, warm email with a subject line, plus a short pre-send check of assumptions and dropped details.
Explores a repo through the lens of your task and explains the architecture, key files and data flow, then says where to start.
Claude Code interviews you briefly about a repeated workflow and writes a complete SKILL.md with a precise trigger description, steps, supporting files and a verification step.
Extracts 8 genuine customer questions with standalone answers from your page and outputs matching FAQPage JSON-LD.
Pulls the central claims out of a long report or paper, with page numbers, the evidence behind each claim and how strong it is, so you can cite or challenge it quickly.
Builds a week of simple meals that reuse ingredients to cut waste, with prep time per meal and one grocery list sorted the way a shop is laid out.
Audits a user flow from screenshots or descriptions and returns an evidence-labeled issue table plus a fix-now, next, defer plan for a sprint decision.
Maps a current team workflow, finds bottlenecks and handoff failures, designs a leaner future-state process with roles and automation candidates, and outlines a low-risk pilot with success metrics.
Turns a pending business decision into a one-page-style decision memo with scored options, explicit assumptions, risks, missing information, a recommendation, and next actions an executive can approve or reject.
Lists the questions buyers ask AI assistants about your product category, checks which sources those answers lean on, and plans the pages and facts you need to be cited.
Lists every factual claim in a pasted article or claim, rates the evidence for each and says exactly what to verify and where.
Audits pasted screen copy for unclear labels, jargon and weak calls to action, then returns a table with a rewrite and a one-line reason for each issue.
Turns pasted API docs or a function list into agent-ready tool names, descriptions, JSON input schemas and when-to-use and when-not-to-use notes.
Creates a cinematic golden-hour scene of your adult self shaking hands with your younger self using your current and childhood photos.
Restyles your photo as a warm, grainy 90s Bollywood film still in a flowing saree, the vintage saree trend that spread on Instagram through Gemini.
Converts discovery notes into a one-page proposal executive summary and a dated mutual action plan. It helps a rep decide whether the deal is ready to propose and what is still missing.
Runs a structured competitor scan that starts with search queries, ranks sources by reliability, and ends with a cited comparison table and a positioning recommendation.
Has Codex review a branch diff against a base ref in read-only mode. It checks correctness, tests, security, and maintainability, and returns evidence-backed findings with severity and a merge recommendation.
Compares products you are choosing between using current reviews and spec sheets, with cited sources, real-world complaints and a recommendation based on how you will use it.
A five-minute end-of-day check that records what got done, captures loose ends, and picks three priorities for tomorrow so you can stop thinking about work.
Drafts a calm reply to a hostile, pushy or unfair email that holds your position, sets a boundary, and moves toward a resolution without escalating.
Turns a rough prompt into a structured one with role, context, task, constraints and output format, plus a one-line reason for each change.
Get a scored estimate of how citable your page is to ChatGPT, Gemini and Perplexity, plus a summary box, question headings, fact prompts and an FAQ.
Guide
Nothing that fits? Write a prompt with AI.
341 copy-ready prompts for productivity, writing, business and coding and more. Each one sets the role, the steps and the output format, and marks the parts you fill in with curly brackets.
Most are written for ChatGPT (285), Gemini (260), Claude (217) and Claude Code (42); the number is how many prompts list that tool. Each prompt page lists its tools, and most text prompts also work in any capable chat model.
Words in curly brackets, such as {audience}, are the parts you replace with your own details. Choose “Ready to use (no blanks)” in the filters to see prompts you can paste as they are.
By how often they are copied, unless you choose another order. Newest shows the latest additions first. Trending ranks prompts by copies, opens and saves over the last two weeks.
No. Every prompt is free to copy or open in your AI tool. A free account lets you save prompts to your vault.
Yes. Write with AI asks what you need, builds a short form for it, and writes the prompt as you fill it in.