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.
336 prompts · last added
67 results for “self-correction” · page 1 of 3
Designs verification checks, error handling, and a self-correction loop for an agent task before it runs, based on likely failure modes.
Converts a casual selfie into a moody black-and-white studio portrait with hard side light and deep shadows, the monochrome portrait trend shared widely on Instagram.
Turns a messy list of what you did this year into a self-assessment organised by your company's review criteria, with impact stated plainly and one honest growth area.
Combines a current photo and a childhood photo into one Polaroid where your present self hugs your younger self, the younger-self trend that went viral with Gemini and ChatGPT.
Turns an ordinary selfie into a soft, natural-light portrait that looks like it was shot by a photographer beside a large window, with your face kept exactly as it is.
Has GitHub Copilot review your branch diff against the base branch, flag defects and missing tests, and draft a PR description with evidence. Use it to decide whether to open the PR or fix issues first.
Holds a casual conversation at your CEFR level, corrects mistakes inline in brackets, and recaps new vocabulary every 10 turns.
Names likely blind spots from your goals and struggles, quotes your own words as evidence, and suggests three small experiments as reflective coaching, not therapy.
Turns one selfie into a glossy studio Christmas portrait of you seated on a giant candy cane among floating ornaments.
Build a research plan that shows where to find competitor evidence, how to judge sources, and how to log citations. It never claims live browsing happened, so you can verify each source yourself.
Runs a realistic roleplay conversation in the language you are learning, at your level, and corrects your mistakes briefly after each reply without breaking the flow.
Merges a current photo and a childhood photo into one instant-film snapshot where the adult you hugs the child you, with soft flash and a white Polaroid border.
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.
Turns your photo into a chunky plasticine stop-motion character doing an activity of your choice on a miniature handmade set.
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.
Guides Gemini through source discovery, evidence review, a citation table, and a recommendation for choosing between vendors, tools, or technologies. Keeps evidence, inference, contradictions, and open questions separate.
Creates a cinematic golden-hour scene of your adult self shaking hands with your younger self using your current and childhood photos.
Turns your selfie into an authentic 1986 mall-studio style portrait with period hair, makeup, wardrobe, a laser-grid backdrop and film grain.
Turns a smiling selfie into a kraft-paper bouquet on a pink background where every bloom is a cut-out of your face with a different expression.
Generates a cozy tilt-shift scene in which you smile down at a palm-sized version of yourself wearing the same outfit.
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.
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.
Creates an editorial brief and outline for a researched article. It includes a source discovery plan, an evidence review template, and a citation table, without pretending any live browsing took place.
Analyzes weekly KPI data against targets, separates signal from noise, proposes ranked root-cause hypotheses, and produces owner-assigned actions and an escalation list for a team operating review.
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.