Working with AI AI prompts

Prompts about prompting itself: improving a draft prompt, setting a role and format, getting the model to ask clarifying questions, and checking an answer for gaps before you rely on it.

Search these 65 prompts in the app

65 Working with AI prompts

Agree with my manager on how my AI time savings get usedShows where your AI efficiency gains are being absorbed by extra work, and prepares a conversation to agree how saved time is used.
Answer my question, then critique it and argue against itGets an answer, an honest self-critique, the strongest counterargument, and a revised answer you can trust more.
Build a daily routine and prompt kit for using AI in my roleA practical routine for using AI through your workday: when to use it, ready prompts, and what to check each time.
Build a reusable prompt templateCreates a fill-in-the-blanks template for a task you repeat often.
Build an AI adoption roadmap for my team or functionA phased plan for adopting AI in sales, marketing, HR, finance, legal, engineering, support, or operations — with use cases, guardrails, and metrics.
Build an AI-assisted workflow to cut my weekly workloadTurns a time-consuming process into a step-by-step human + AI workflow with prompts, review points, and estimated time saved.
Build an evaluation set and scoring plan for an LLM featureA test set and scoring approach to measure whether an AI feature's answers are correct, safe, and improving between versions.
Build habits for using AI to sharpen my thinking, not replace itReviews how you use AI at work and builds practical habits so AI improves your reasoning instead of just speeding up answers.
Check AI output for errors and hallucinationsA verification checklist to catch fabricated facts, faulty logic, and unsupported claims before you rely on AI output.
Check an AI summary against the original documentCompares an AI summary line by line with the source to catch errors, distortions, missing points, and things the source never said.
Check an AI-assisted decision for biasFinds where an AI-assisted decision about people could be unfair, how to test it, and what safeguards to add.
Check whether a task is appropriate for AI before I startA go/no-go screen that says, step by step, whether AI should do the work, assist you, or stay out, and why.
Check whether AI is lowering or adding to my mental loadReviews how you use AI tools at work to show where they reduce cognitive load and where they add checking, prompting, or extra coordination.
Choose between a chatbot, copilot, automation, or AI agent for a taskRecommends the right kind of AI setup for a task, with the trade-offs, risks, and what you need to make it work.
Connect an AI use case to a measurable business outcomeMaps an AI use case from task improvement to workflow, operational, customer, people, and financial outcomes, with metrics for each.
Create a before, during, and after AI-use checklist for a team taskA short tick-box checklist covering tool choice, data handling, verification, disclosure, and sign-off whenever your team uses AI on one task.
Create a personal AI capability roadmap for my roleA staged plan to grow from occasional AI user to someone who builds and directs AI workflows in your job.
Create a quality-control checklist for AI output on a recurring taskA reusable checklist your team runs on every AI output for one recurring task, with pass/fail criteria and spot-check rules.
Create an audit trail for an AI-assisted processDefines what to record, what evidence to keep, and for how long whenever AI is used in a work process.
Critically review an AI answer before I rely on itStress-tests an AI answer for hidden assumptions, missing context, weak reasoning, and the strongest counterargument.
Decide where an AI agent must stop and get human approvalSets autonomy limits, approval triggers, and escalation conditions for an AI agent, plus a safe approval workflow.
Decide which decisions in my role should always stay mine, not AI'sSorts the decisions you make into ones you own, ones AI can prepare, and ones AI can handle, with a personal rule set.
Define how to monitor an AI agent and what evidence it must logMonitoring metrics, review routines, alerts, and the evidence an AI agent should produce for every task it completes.
Design an AI agent or automated AI workflowDefines an agent's goal, tools, steps, guardrails, and human checkpoints before you build it.
Design an internal knowledge assistantHow an AI assistant should answer employee questions from your documents: sources, tone, and escalation.
Design the handoffs between my team and an AI agentA human-agent workflow showing who does each step, what passes at every handoff, where people check, and how work returns to the agent.
Diagnose why my AI chatbot gives off-topic or irrelevant answersPinpoints whether the problem is the prompt, retrieval, context, or settings, and gives targeted fixes plus test cases to confirm them.
Estimate realistically how much time AI could free up in a workflowA grounded estimate of capacity AI could create in a workflow, step by step, net of review time and with clear assumptions.
Find the highest-value AI use cases in my jobRanks the tasks in your role where AI can save the most time, cut cycle time, improve quality, or sharpen decision prep.
Find where AI can help in my work or businessInterviews you about a process and identifies where AI genuinely helps — and where it doesn't.
Flag the parts of an AI answer that need an expert to reviewMarks which parts of an AI answer need legal, financial, technical, medical, or other expert review, and what to ask that expert.
Get better at directing AI, not just using itAssesses how you brief, break down, and review work with AI, then gives targeted practice to manage AI like a capable assistant.
Identify the decisions in a task I should not hand to AIPinpoints the decisions, ambiguities, and exceptions in a task that a person must own, and why AI should not decide them.
List the claims and possible hallucinations to verify in an AI draftExtracts every factual claim, number, quote, and citation from an AI draft, flags likely hallucinations, and gives a verification checklist.
List the ways an AI agent could fail and how to prevent eachA failure-mode review for an AI agent: realistic scenarios, how you would notice, the damage, and the safeguard.
List what company data I must not enter into an AI toolA clear red, amber, and green guide to which of your work data can go into a specific AI tool, and on what conditions.
Make AI ask me the questions that matter before it answersMakes AI identify missing information and ask the fewest questions needed before producing a high-quality result.
Make an AI coding assistant plan a change before it edits codeA structured request that makes the assistant restate requirements, list assumptions to check, and propose file-by-file changes first.
Map approvals, sign-offs, and accountability in an AI-assisted processA step-by-step map of who verifies, who approves, when to escalate, and who owns the final decision when AI is involved.
Plan and build an MCP server that connects AI to my serviceA tool design and starter code for a Model Context Protocol server that lets AI assistants use your API well.
Plan what to do when AI gets something wrong at workAn escalation path for AI errors: how to spot, contain, report, fix, and learn from mistakes made with AI tools.
Plan what to hand to AI without losing my own skillsSorts your tasks into ones to delegate to AI, ones to keep doing yourself for mastery, and ones to do with AI as a coach.
Prepare to delegate a task to AI and verify the resultLists what you must understand, decide, and gather before delegating a task to AI, and exactly what to verify once it's done.
Redesign a process with AI and human review checkpointsRebuilds a workflow step by step into automation, AI-drafted, and human-only work, with named review checkpoints, accountability, and risk controls.
Remove sensitive information before pasting into AIFinds and replaces personal, confidential, and secret data with safe placeholders.
Reverse-engineer the prompt behind an outputWorks backwards from text, code, or an image to the prompt that likely produced it.
Review an AI tool before my government agency adopts itA pre-adoption review of an AI tool covering public records, privacy, accessibility, bias, procurement, and transparency obligations specific to government.
Review and improve a prompt I already wroteAudits your prompt for objective, context, constraints, inputs, output format, quality criteria, and verification, then rewrites it.
Run a risk check on an AI-assisted workflow before rolloutBuilds a risk register for an AI workflow covering accuracy, data privacy, bias, security, compliance, and over-reliance, with controls.
Score an AI output against the prompt that produced itA requirement-by-requirement scorecard for an AI output, separating prompt problems from output problems, with prompt fixes.
Separate AI's recommendations from the decisions I must ownSorts an AI answer into what you can accept, what you must check, and what you must decide yourself, with the questions to settle each.
Set permissions and access limits for an AI agentA least-privilege permissions plan for an AI agent: which systems, which actions, what limits, and how to review access.
Set rules for student use of AI tools in my school or courseCreates a clear AI use policy for students, with assignment-level rules, disclosure, and integrity steps.
Spot where AI could make my team overconfidentFinds the places where polished AI output could lead people to trust, skip checks, or decide too quickly, plus safeguards for each.
Spot where AI is creating more work instead of more valueFinds where AI use is adding rework, review load, content volume, or noise, and what to change so it creates real value.
Stress-test my chatbot with hard scenarios before launchA test plan with tricky, edge-case, and adversarial conversations, a scoring rubric, and a way to find what to fix first.
Summarize this chat so I can continue in a new oneA compact handoff of decisions, context, and next steps to paste into a fresh conversation.
Turn a one-off AI chat into a reusable prompt pack for my teamExtracts the prompts, fixes, and checks from an AI chat that worked into a step-by-step workflow and prompt pack colleagues can reuse.
Turn a rough request into a powerful promptRewrites your idea into a clear, complete prompt — and asks what's missing first.
Write a law firm policy for using generative AI on client workA practical firm policy on generative AI that covers confidentiality, verification of citations, supervision, billing, and client disclosure.
Write a responsible-AI policyAcceptable use, data handling, review requirements, and accountability for AI in your organization.
Write a task spec with clear checks for an AI agentTurn a vague task into a precise spec, a way to verify the output, and the standing context an AI agent needs, before you hand it off.
Write an operating contract for an AI agentDefines an AI agent's objective, scope, what it can and cannot do, success measures, and who owns it.
Write an SOP for my team to use AI safelyA step-by-step operating procedure so a whole team can use AI on the same task consistently, safely, and with review built in.
Write custom instructions for my AI assistantCustom instructions, a project brief, or a custom GPT/Claude Project setup so the AI works the way you do.

Working with AI AI prompts

65 Working with AI prompts

Other topics