Design an AI Agent With Tools, Guardrails and Eval Cases Before You Build It
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.
336 prompts · last added
85 results for “source-evaluation” · page 2 of 4
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.
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.
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.
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 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.
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.
Turns your source material into a diagnostic quiz with an answer key, a misconception map, and a reteach plan. It helps you decide who needs review and what to reteach.
Tests a specific claim or statistic against primary and peer-reviewed sources. Produces an evidence grid, a contradiction log, and a calibrated confidence rating with explicit unknowns.
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.
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.
Plan a custom GPT before building it. Produces the instruction text, knowledge file plan, conversation starters, and a test set so you can decide whether to build, narrow, or skip it.
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.
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.
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.
Creates a realistic study plan for an upcoming exam based on topics, current confidence, and available hours. It outputs a weekly schedule, practice targets, and a checkpoint to decide where to shift effort.
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.
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.
Stress-tests a plan with five strong objections, hidden assumptions, the likeliest failure path and the evidence that would change the verdict.
Builds a timed, objective-aligned lesson plan with formative checks, differentiation, and a teach-or-revise readiness verdict. It asks for missing inputs first and keeps assumptions separate.
Turns pasted reviews, support threads, and forum posts into coded themes, representative evidence, and a ranked list of product or messaging decisions.
Generates a styled top-down flat lay of your product with props, colour palette and space for text, ready for an Instagram feed post or ad.
Plans and executes a library or framework version migration in Cursor in small, verifiable batches, with an impact inventory, rollback points, and per-batch test gates instead of one risky bulk edit.
Produces a developer-ready component specification covering anatomy, variants, states, tokens, accessibility, and open questions from a short component brief.
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.
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.