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
177 results for “json-ld” · page 3 of 8
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.
Drafts a calm, polite reply that holds your stated boundary and is hard to misread, with a short version and a misread check.
Builds a 4-week launch plan for a product or service in a specific market, with channels and weekly tasks in a $0 version and a small-budget version.
Audits an old article for outdated facts and missing subtopics, proposes new sections and rewrites the intro for your target keyword.
Holds a casual conversation at your CEFR level, corrects mistakes inline in brackets, and recaps new vocabulary every 10 turns.
Turns a raw keyword list into intent-based page groups, each with a recommended page type, title and build order.
Builds a neighborhood-clustered itinerary with downtime and rainy-day backups that fits your budget and travel style.
Build a zero-based monthly budget from typed income and spending amounts, flag overspending and get three realistic cuts, with no account access.
Builds a day-by-day revision timetable counted back from your exam date, with practice tests, review days and buffer days sized to the hours you really have.
Builds a customer persona from your actual reviews or survey answers: jobs, pains, words they use, objections and buying triggers, with quotes as evidence and no invented demographics.
Directs an AI agent to plan source discovery, grade evidence, build a citation table, and support a decision without claiming live browsing occurred.
Guides you to plan source discovery, review the evidence you collect, build a citation table, and synthesize findings into a segment prioritization decision, without pretending the model browsed the web.
Turns your common support questions and policies into ten reusable reply macros with a warm tone, the right policy detail, and a placeholder only where agents must personalise.
Turns a list of links and your quick takes into a readable newsletter issue with a subject line, an opening, short summaries and your own angle on each item.
Plans a walkable two-day city trip around what you actually enjoy, grouped by neighbourhood, with costs, opening-hour checks and a rainy-day swap.
Turns a repetitive task into a build-ready automation spec with triggers, AI steps, human checkpoints, failure handling and a test plan.
Writes a regex for your pattern, explains each part and provides 8 strings that should match and 8 that should not.
Gives a funny but kind roast of your resume or LinkedIn profile, followed by the five fixes that would improve it most, ranked.
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.
Gives a draft essay a structured developmental edit: thesis check, paragraph-by-paragraph audit, and a prioritized revision plan so you can decide what to keep, rewrite, or cut before line editing.
Turns pasted account material and a source discovery plan into a evidence-labeled research brief. It helps a rep decide whether to pursue an account, which persona to target, and which outreach angle to use.
Audits an existing multi-agent pipeline for failure modes and produces retry limits, fallback paths, escalation triggers, and a test plan. Supports the decision on what to harden before wider rollout.
Splits a research question across parallel research agents, defines source discovery and evidence review steps, merges findings into a citation table, and produces a decision memo without claiming live browsing.
Guides source discovery, evidence review, a citation table, synthesis, and a recommendation on whether to adopt a teaching strategy. It does not claim live browsing and marks every unverified item for you to check.
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.