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.
336 prompts · last added
206 results for “which need reference images” · page 3 of 9
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.
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.
Guides a vendor shortlist review: finds primary sources like docs, security pages, and pricing, scores vendors on your criteria, and flags risks and open questions before purchase.
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.
Guides a source-backed evaluation of software or service vendors against weighted criteria. Ends with a decision memo covering risks, open questions, and verification steps before purchase.
Has Cursor lock in current behavior with characterization tests before restructuring a legacy module in small steps, so you can decide whether the refactor preserved behavior and is safe to merge.
Builds a behavior-based test matrix for a function or module and then generates test code in your framework. Covers edge cases, failures, and mocking boundaries, with coverage gaps stated honestly.
Create a writer-ready content brief from SERP observations you supply. It covers intent, required sections, evidence gaps, and a go or no-go call on whether the page is worth producing.
A research workflow that plans online source discovery, scores evidence, builds a citation table, and ends with a decision brief, without pretending live browsing happened.
Turns product facts, audience insight, and competitor context into a positioning statement, messaging hierarchy, and proof map so a team can approve one launch angle.
Diagnoses where a workflow slows down using your process steps and metrics, then ranks causes and produces a 30-day improvement plan with owners, measures, and risks.
Creates an editorial brief and outline for a researched article. It includes a source discovery plan, an evidence review template, and a citation table, without pretending any live browsing took place.
Take a topic and audience through a brief, outline, and first draft with a fact-check list. Designed for ChatGPT Canvas so you can edit section by section and keep claims verifiable.
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.
Analyzes weekly KPI data against targets, separates signal from noise, proposes ranked root-cause hypotheses, and produces owner-assigned actions and an escalation list for a team operating review.
Combines your Docs, Sheets, meeting notes, and outside sources into one decision memo. Separates internal evidence from external research and logs conflicts, gaps, and next actions.
Has GitHub Copilot review your branch diff against the base branch, flag defects and missing tests, and draft a PR description with evidence. Use it to decide whether to open the PR or fix issues first.
Builds a blog post outline for one keyword by first deciding the search intent, then structuring headings, questions and examples that match what searchers expect to find.
Writes three short cold emails for one prospect type, each opening with a different relevant trigger, under 90 words, with a low-effort ask and two follow-ups.
Writes a 250-word cover letter that picks the employer's top three needs from the job post and answers each with a specific example from your resume.
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.
Teaches any topic one idea at a time with plain explanations and analogies, makes you explain it back, re-teaches the gaps, then ends with a marked quiz.
Designs a three-agent content pipeline where a researcher, writer and editor pass structured handoffs, with the exact fields each agent receives and returns and checks between stages.
Turns the transcript of a recorded walkthrough into a numbered SOP with prerequisites, steps, screenshots to capture, decision points, and common mistakes, ready for a team wiki.
Guide
Nothing that fits? Write a prompt with AI.
336 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 Midjourney (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.