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
54 results for “treat outputs as exploration” · page 1 of 3
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 pasted feature spec into independent coding-agent tasks with file ownership, interface contracts, a merge order and a done command for each task.
Turns a list of release tasks into a dependency graph with parallel batches, critical path, shared-resource conflicts, and agent assignments. Supports the decision on what to run now versus wait on.
Turns an agent idea into a build-ready design: the job, the tools with their inputs and permissions, guardrails, failure handling and a set of evaluation cases to test it.
Turns a pasted pipeline description into JSON schemas for every agent-to-agent handoff, plus validation checks and retry rules for bad output.
Analyzes a recurring manual task and produces an automation blueprint with trigger, steps, data mapping, error handling, and a test plan. It also helps you decide whether the task is worth automating at all.
Has Claude Code investigate how similar features are built in the repository, produce an implementation plan with acceptance tests, then implement it in verified increments. Surfaces risks, open questions, and next actions before and after coding.
Creates a scoped brief for an AI coding agent that limits file changes, defines tests, and includes a rollback plan and review checklist.
Turns a set of abstracts into a comparison matrix of methods, samples, findings and limits, then maps where studies agree, conflict and leave gaps for your review.
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.
Builds a transparent market size estimate from discoverable sources, compares top-down and bottom-up methods, and flags weak assumptions before a go or no-go call.
Produces a least-privilege tool inventory, function definitions, and approval rules for an agent that calls APIs or internal systems.
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.
Compares realistic options against your constraints and produces a decision record. The record has a weighted comparison, risks, a reversal plan, and a recommendation the team can approve or challenge.
Turn a crawl export and Search Console data into a scored, sprint-ready technical SEO fix list. It separates facts from assumptions and flags what needs verification before developers start work.
Guides Claude Code to build or refactor a dependency-aware DAG scheduler for agent phases, with cycle validation, bounded parallelism, join policies, retries, and an append-only run ledger so interrupted runs resume without redoing finished nodes.
Has Claude Code review a branch diff like a skeptical maintainer, producing severity-ranked findings with evidence and a clear merge, fix, or block recommendation. Use it before opening or approving a pull request.
Designs verification checks, error handling, and a self-correction loop for an agent task before it runs, based on likely failure modes.
Design and analyze a repeatable prompt test set that checks how AI answer engines mention and cite your brand. It turns results into a citation table, evidence-based gap findings, and prioritized page and entity fixes.
Produce a decision memo that compares pricing options using your numbers, with scenario math, customer risk, and a test plan. Helps a founder or manager decide whether to change prices and how.
Runs a behavior-preserving refactor in Codex exec. It pins current behavior with characterization tests, refactors in small verified steps inside an allowed scope, and ends with an evidence-based handoff for the merge decision.
Has Gemini inspect uploaded images, screenshots, charts, and PDFs, extract what is visible, and verify claims against online sources. Ends in a findings log with confidence ratings and next steps.
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.
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.