Research Agent Brief: Source Discovery, Evidence Review, and Citation Table
Directs an AI agent to plan source discovery, grade evidence, build a citation table, and support a decision without claiming live browsing occurred.
341 prompts · last added
341 results for “two or three landmarks” · page 10 of 15
Directs an AI agent to plan source discovery, grade evidence, build a citation table, and support a decision without claiming live browsing occurred.
Writes a sincere apology for a mistake at work or in personal life that names what happened, owns the impact, avoids excuses and says what changes next.
Checks a claim you saw online against primary sources, traces where it came from, and returns a verdict with a confidence rating and the evidence on both sides.
Tightens an overlong text by about 30 percent without losing meaning, then lists what was cut and why.
A save-ready SKILL.md that has your coding agent review a branch before merge: correctness, security, tests and migrations, with findings ranked by severity and no style nitpicks.
Creates a close-up, oddly satisfying video of a knife slicing a fruit made of glass, with crisp crackling sound, the ASMR format popular on short-video feeds.
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.
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.
Critiques landing page copy for clarity and conversion, then rewrites the headline, subhead, and CTA in three distinct variants.
Get 8 predicted interview questions for a specific job, each with a STAR model answer built only from facts in your CV.
Writes both ChatGPT Custom Instructions boxes for your role and style preferences, each under 1,500 characters, with test prompts to check them.
Converts a successful chat transcript into a reusable prompt template with at most three named variables and a one-line note on when to use it.
Turns pasted links and notes into a newsletter issue with a hooking intro, three takeaway sections, and one call to action.
Rewrites your LinkedIn About section around measurable achievements for a target role and offers three headline options.
Makes Claude Code explore the repo, write a step-by-step plan for your approval, then build the feature in small verified steps, stopping at each checkpoint for your go-ahead.
Has Codex review a pull request and return comments sorted into blocking, should-fix and nit, each with the file and line, the risk, and a suggested change.
Creates a full-body editorial lookbook photo of a model wearing your coat or outfit while crossing a snowy cobblestone square.
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.
The February 2026 caricature trend: a warm, exaggerated cartoon of you surrounded by the tools and in-jokes of your work, built from your photo and what ChatGPT knows about you.
Shows what your actual room could look like restyled, keeping the walls, windows and layout while changing furniture, colours and decor to the style you choose.
Creates a same-day recap email and a three-touch re-engagement sequence from meeting notes. It helps a rep confirm commitments and decide whether a quiet deal should be chased, reframed, or closed out.
Writes five meta title and description pairs for a page, each within Google's display limits with character counts, matched to the target keyword and the reason to click.
Gives codex exec a non-interactive procedure to diagnose a failing CI output, apply a minimal fix, rerun the checks and stop after three attempts with a clear report.
Writes an age-appropriate script for explaining a difficult topic to your child, plus calm answers to the questions they are likely to ask.
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.