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
22 results for “agent-evaluation”
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 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.
Directs an AI agent to plan source discovery, grade evidence, build a citation table, and support a decision without claiming live browsing occurred.
Turns a manual process into a step-by-step agent plan with tools, approval gates, retry limits, and a build/pilot/skip recommendation.
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 pasted agent trace to find the first real failure and proposes exact prompt rewrites or tool changes, each with a test.
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.
Produces a set of testable guardrail rules for your coding agent, covering blocked commands, approval gates, secret handling and hook checks.
Produces a 3-5 subagent roster with system prompts, minimal tool permissions, model tiers and explicit handoff rules for your project.
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.
Turns a vague GitHub issue into a self-contained task with context, testable acceptance criteria, files to touch, and tests to add, so the Copilot coding agent can finish it.
Converts your pasted Cursor .mdc rules into a single AGENTS.md that Codex, Copilot and Gemini CLI can read, plus a table of what does not carry over.
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.
Designs a four-agent pipeline for your report type with each agent's prompt, inputs, outputs and handoff format.
Writes a ready-to-deploy orchestrator system prompt that delegates to your workers, tracks progress in a ledger, merges results and stops on defined conditions.
Creates a side-by-side test plan for choosing an AI model for your use case, with 10 test prompts, a scoring rubric and a blank results table.
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.
Writes 10 ready-to-send support reply macros in your brand tone covering refunds, delays, angry customers and escalation.
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.
Builds a dated moving checklist counted back from your move date, covering notice periods, utilities, address changes, packing by room and first-night essentials.
Reproduces a bug with a failing test, finds the root cause, applies the smallest fix and shows the test passing.
Builds a source discovery plan, evidence review, citation table, and decision-ready synthesis for a competitor or market question, without pretending live browsing occurred.
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.