Agent Run Pre-Mortem and Self-Correction Loop Designer
Designs verification checks, error handling, and a self-correction loop for an agent task before it runs, based on likely failure modes.
341 prompts · last added
217 results for “Show them at work as” · page 7 of 10
Designs verification checks, error handling, and a self-correction loop for an agent task before it runs, based on likely failure modes.
Turns your product facts, customer evidence, and competitor notes into a tested positioning statement, messaging hierarchy, and proof-gap list so a marketing team can decide what to say and what to validate first.
Converts pasted monthly KPI results and targets into a variance analysis, driver hypotheses, and prioritized actions that a leadership team can decide on in one meeting.
Turns rough notes and supplied source excerpts into a send-ready newsletter issue. It compares lead angles, flags unsupported claims, and ends with a go/no-go checklist before you hit send.
Shapes your real stories and memories into a three-to-five-minute wedding toast with a clear arc, warm humour, and a closing toast line.
Turns pasted links and notes into a newsletter issue with a hooking intro, three takeaway sections, and one call to action.
Build a topic cluster from a keyword list and existing content, then rank which cluster and pages to create first. It includes a keyword-to-page mapping table, internal link rules, and cannibalization risks.
Edits stock phrases, forced triads, em-dash habits and hype words out of an AI-assisted draft while keeping your meaning and voice, with a change log.
Converts a scene idea into a numbered storyboard and per-shot prompts for AI video generators, with consistency anchors to reduce character and style drift between clips.
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.
Builds a source discovery plan, evidence review, and citation table for a video's factual claims so a producer can decide which claims to keep, soften, or cut before scripting.
Turns a pasted transcript into five title options, thumbnail text, an SEO description and timestamped chapters.
Organizes rough symptom notes into a dated timeline and a prioritized question list for your appointment, without any diagnosis.
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.
Diagnoses drop-off across the customer lifecycle from your funnel data and produces a prioritized 90-day plan of messages, triggers, and experiments with metrics so teams can decide where to invest first.
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 an unsorted list of tasks, errands and worries into a realistic week of time blocks, with the hardest work placed in your best hours.
Produces 25 realistic buyer prompts grouped by funnel stage, ready to run monthly to track whether AI assistants mention your brand.
Compares competitor homepage copy with your positioning to map overlap, find unclaimed angles, and propose one sharper differentiating line.
Builds a short style guide from three of your writing samples, then writes a new piece in that voice and notes which rules were applied.
Extracts decisions, owned and dated action items and open questions from meeting notes, then drafts a follow-up email.
Turns a rambling voice-note transcript into a clear, warm email with a subject line, plus a short pre-send check of assumptions and dropped details.
Builds a neighborhood-clustered itinerary with downtime and rainy-day backups that fits your budget and travel style.
Extracts 8 genuine customer questions with standalone answers from your page and outputs matching FAQPage JSON-LD.
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.