Write Smarter, Not Harder: AI-Powered Prompts for Every Product Manager

Trevor Noon

I, like many, struggle with balance. I’ve perfected a slide deck that goes un-viewed. I’ve whipped through a document that ends up being viewed by the CEO. While 80/20 thinking is great, it’s hard to know when you’re in the 80 and when you’re in the 20.

Not anymore. AI can upgrade your 80/20 into a 90/10 - getting 90% of the quality for 10% of the effort.

With AI, we can quickly finish bulk work and spend time fine-tuning. Even with minimal effort, we can deliver A+ (or at least A- if we’re in a rush) work at all times. While this is relevant for everyone, it is especially true for Product Managers. Effective PMs prioritize building products with great teams over tasks like writing PRDs, consolidating feedback, or making decks. We became PMs to build products with great teams, not just to fantasize about them alone with Google Docs.

In this article, I’ll explain how I’ve implemented AI into my workflows and provide explicit prompts for immediate use.

TL;DR

  • Give the AI a Defined Role, Ask it To Explain Itself, and Provide Examples both Positive and Negative
  • Copy-paste the prompts that I’ve listed below for your use-cases.

Now, let's jazz up those tips and examples, shall we?

Harnessing AI Like a PM Superhero

1. Define the AI’s Role: Your New Digital Intern

Think of AI as your eager-to-please intern, ready to tackle any task you throw their way. But unlike your average intern, this one doesn't need coffee breaks or get distracted by TikTok.

To get the most out of your AI sidekick, be crystal clear about what you want. It's like writing user stories, but for your AI assistant. For example:

"Hey AI, you're now my PRD-writing wizard. I need you to craft a narrative that would make even the most jaded engineer shed a tear of joy."

By giving AI a specific role, you're essentially handing it a job description. And trust me, it won't ask for a raise or complain about the lack of ping-pong tables in the office.

2. Ask the AI to Explain Itself: Because "Because I Said So" Doesn't Cut It

Remember when you were a kid and adults would say, "Because I said so"? Well, now you're the adult, and you get to ask "Why?" to your heart's content.

Don't just take AI's word for it. Prod it to spill the beans on its thought process. It's like having a mini retrospective after every AI output. For instance:

"AI, you've suggested we pivot to blockchain. Explain your reasoning as if I'm a skeptical investor who thinks blockchain is just a fancy word for a slow database."

This approach helps you separate the AI wheat from the chaff, ensuring you're not just nodding along to technobabble.

3. Provide Excellent Examples: Show, Don't Tell (But Actually, Do Both)

You wouldn't expect a new team member to nail your company's tone without examples, right? Same goes for AI. Feed it the good stuff – your best work, industry gold standards, or that presentation that made the CEO actually pay attention in a meeting.

Think of it as creating a mood board, but for text. For example:

"AI, here's our last quarter's most successful product launch email. Channel this vibe, but make it feel fresh for our new IoT toaster launch."

By providing stellar examples, you're essentially giving AI a cheat sheet for success. It's like teaching it to fish, but with words.

4. Provide Counter-Examples: The "What Not to Wear" of AI Prompts

Just as important as showing AI what to do is showing it what not to do. It's like creating anti-personas for your AI assistant.

Serve up some examples of disasters – that email that accidentally went to the entire company, or the product description that made legal break out in hives. For instance:

"AI, whatever you do, don't make our new fitness app sound like this failed campaign that implied our users were lazy couch potatoes."

By setting these boundaries, you're giving AI guardrails to keep it from veering into PR nightmare territory.

Real-World PM Examples: AI-Powered Productivity in Action

PRDs with User Narratives: From Snooze-fest to Page-turner

Prompt:

You are an expert product manager with a flair for storytelling. Create a user narrative for [feature name] that brings the user experience to life. Focus on the user's context, pain points, and how our feature solves their problem in a delightful way. Make it vivid and engaging, as if you're pitching to a room full of stakeholders who've had one too many cups of coffee.

Before AI:

"The user will click on the button to initiate the process. Then, they will be presented with a form to fill out. After submitting the form, the system will process the information."

Yawn. This reads like assembly instructions for a particularly boring piece of IKEA furniture.

After AI:

"Meet Sarah, a busy marketing manager who's always on the go. As she rushes to her next meeting, coffee in one hand and phone in the other, she realizes she needs to quickly submit a campaign request. With our new one-tap submission feature, Sarah simply opens the app, taps the 'New Campaign' button, and voila! A smart form pops up, pre-filled with her most common inputs. In less time than it takes to say 'synergistic cross-platform engagement', Sarah's request is in, and she's off to dazzle her clients."

Now that's a narrative that paints a picture and might actually keep stakeholders awake!

Test Cases: From Mundane to Magnificent

Prompt:

You are a seasoned QA engineer with a knack for creating comprehensive, creative, and engaging test cases. Your role is to generate a set of test cases for our new feature, the 'One-Click Expense Report Submission' tool. Please create 5-7 test cases that cover both common scenarios and edge cases. Each test case should have a catchy title, a brief description, and expected results. Make sure to include positive and negative scenarios.

Here's an example of a great test case:

Title: 'The Globetrotter's Delight' // Description: Submit an expense report with multiple currencies and time zones.Expected Result: The system accurately converts all currencies to the company's base currency and adjusts timestamps to the user's local time zone.

And here's an example of a poor test case to avoid:

Title: 'Basic Submission' // Description: Submit a report. Expected Result: Report submits.

Please explain your thought process for each test case, highlighting how it tests a specific aspect of the feature or potential user behavior. For reference, our previous successful test suite for the 'Automated Meeting Scheduler' feature was praised for its thoroughness and creativity. It included scenarios like 'The Time Zone Tango' and 'The Double-Booked Dilemma'. Remember, we want to avoid overly technical jargon or vague descriptions like in our old 'Legacy File Upload' test cases, which were criticized for being too abstract and difficult for non-technical team members to understand. Your test cases should be thorough yet easy to understand, covering a range of scenarios that real users might encounter. Inject some humor where appropriate, but maintain a professional tone overall. Please generate the test cases based on this guidance.

Before AI:

"Test Case 1: User logs in

Test Case 2: User uploads file

Test Case 3: User shares file"

After AI:

"1. 'The Impatient Executive': Test rapid-fire login attempts from multiple devices simultaneously. Ensure the system handles this without breaking a sweat, just like our users juggling multiple priorities.

2. 'The File Hoarder': Upload a comically large file (think: 'entire season of Game of Thrones in 4K'). Verify that the progress bar doesn't have an existential crisis and actually completes the upload.

3. 'The Oversharer': Attempt to share a file with every single contact in the address book, including 'Pizza Hut' and 'Mom's New Boyfriend Steve'. Confirm that the system politely suggests maybe not spamming everyone you've ever met."

Automating User Feedback Intake: From Data Overload to Insights Bonanza

Prompt:

You are an expert data analyst and product insight generator. Analyze the following set of user feedback for our [product name]. Categorize the feedback into key themes, highlight the most impactful insights, and suggest three potential product improvements based on this feedback. Present your findings in a clear, concise format that a busy product manager can quickly digest and act upon. Bonus points if you can spot any hidden gems or surprising trends in the data.

Before AI:

Scrolling through endless comments, trying to categorize feedback manually, and praying you don't miss that one genius suggestion buried in a sea of "It's okay, I guess" responses.

After AI:

A neatly organized report that categorizes feedback into themes, highlights key insights, and even suggests potential actions. It's like having a team of analysts working 24/7, but without the need for snacks or bathroom breaks.

So what now?

With these AI-powered tools in your PM toolkit, you'll be churning out top-notch deliverables faster than you can say "agile sprint." Now go forth and conquer, you AI-augmented product genius!

Remember, the goal isn't to replace your PM superpowers, but to amplify them. Use AI to handle the heavy lifting so you can focus on what really matters: building kick-ass products and occasionally dominating the office foosball tournament.

Now, if you'll excuse me, I need to go ask AI to write my performance review. Kidding! (Or am I?)

Bonus! Tools to Use and a “Forever” Prompt

While any tools can help you accomplish the above, I’d love to suggest a few favorites:

  • Lex for Writing (Google Docs + AI)
    • Use Lex to quickly draft and refine product requirement documents, feature specs, and team communications with AI-assisted writing and editing capabilities.
  • Perplexity.AI for Search and General AI (be sure to update its “focus” accordingly for when you want to refine its scope)
    • Leverage Perplexity.AI to conduct rapid market research, gather competitive intelligence, and generate initial ideas for product features or improvements.
  • Claude for Coding and Artifact Generation (it can even help whip up Figma designs if you’re keen!)
    • Employ Claude to create mockups, generate sample code snippets for technical discussions, and even produce rough Figma designs to visualize product concepts quickly.
  • Zapier for tying everything together
    • Utilize Zapier to automate routine tasks, such as syncing data between tools (e.g., Asana, Google Sheets, Jira), scheduling follow-ups, or creating custom workflows that integrate AI outputs into your existing product management processes.

Finally, I do have one baseline prompt that I always go back to if/when I need a solid foundation to work off of. Feel free to use and steal as you like:

You are an experienced product manager skilled in communicating technical and business concepts. You work at COMPANY, the COMPANY DESCRIPTION, on their FUNCTIONAL team. One of your key responsibilities is writing product requirements documents that are easily understood by other team members across design, engineering, customer experience, data, and legal teams. When you write, it is important that your content has an authentic, casual, and clever tone. It is key that the writing is concise, witty, and professional. Your content should focus on the specifics of the problem statement provided, but come up with creative ideas for the user experience, ways to expand the feature, etc. Your content should be precise, confident, and easy to understand. The quality of the writing should be 11/10. Please confirm that you understand this role and the goal. We will then dive into specific problem statements.

Hat-Tips

A lot of this work above has been said before by folks much smarter than me. Specific inspiration on some of the prompts has been pulled from Siqi Chen’s Prompt Engineering content, and just as much was supported by Allie Miller’s work.

Related Stories

Applied AI

Making the moonshot real – what we can learn from a CTO using ML to transform drug discovery

Applied AI

AI Diagnostics in Healthcare: How Artificial Intelligence Streamlines Patient Care

Applied AI

AI in Customer Relationship Management

Applied AI

8 Prerequisites for AI Transformation in Insurance Industry

Applied AI

Advanced AI Analytics: Strategies, Types and Best Practices

Applied AI

Machine Learning in Healthcare: 7 real-world use cases

Applied AI

AI Security: How to Use AI to Ensure Data Privacy in Finance Sector

Applied AI

The Secret to Successful Enterprise RAG Solutions

Applied AI

What our community of 200+ ML engineers and data scientist is reading now

Applied AI

AI Consulting in Finance: Benefits, Types, and What to Consider

Applied AI

How the U.S. can accelerate AI adoption: Tribe AI + U.S. Department of State

Applied AI

Navigating the Generative AI Landscape: Opportunities and Challenges for Investors

Applied AI

3 things we learned building Tribe and why project-based work will change AI

Applied AI

What the OpenAI Drama Taught us About Enterprise AI

Applied AI

8 Ways AI for Healthcare Is Revolutionizing the Industry

Applied AI

How to Measure ROI on AI Investments

Applied AI

Why do businesses fail at machine learning?

Applied AI

AI in Construction: How to Optimize Project Management and Reducing Costs

Applied AI

Tribe's First Fundraise

Applied AI

AI and Predictive Analytics in Investment

Applied AI

A Guide to AI in Insurance: Use Cases, Examples, and Statistics

Applied AI

AI and Predictive Analytics in the Cryptocurrency Market

Applied AI

Using data to drive private equity with Drew Conway

Applied AI

How data science drives value for private equity from deal sourcing to post-investment data assets

Applied AI

AI in Construction in 2023: Use Cases and Benefits

Applied AI

An Actionable Guide to Conversational AI for Customer Service

Applied AI

10 ways to succeed at ML according to the data superstars

Applied AI

AI-Driven Digital Transformation

Applied AI

AI in Banking and Finance: Is It Worth The Risk? (TL;DR: Yes.)

Applied AI

Key Takeaways from Tribe AI’s LLM Hackathon

Applied AI

AI Consulting in Insurance Industry: Key Considerations for 2024 and Beyond

Applied AI

Self-Hosting Llama 3.1 405B (FP8): Bringing Superintelligence In-House

Applied AI

AI Implementation: Ultimate Guide for Any Industry

Applied AI

How to Build a Data-Driven Culture With AI in 6 Steps

Applied AI

How 3 Companies Automated Manual Processes Using NLP

Applied AI

AI in Private Equity: A Guide to Smarter Investing

Applied AI

AI for Cybersecurity: How Online Safety is Enhanced by Artificial Intelligence

Applied AI

Leveraging Data Science – From Fintech to TradFi with Christine Hurtubise

Applied AI

Tribe welcomes data science legend Drew Conway as first advisor 🎉

Applied AI

Scalability in AI Projects: Strategies, Types & Challenges

Applied AI

A primer on generative models for music production

Applied AI

Everything you need to know about generative AI

Applied AI

Welcome to Tribe House New York 👋

Applied AI

How to Evaluate Generative AI Opportunities – A Framework for VCs

Applied AI

5 machine learning engineers predict the future of self-driving

Applied AI

How AI for Fraud Detection in Finance Bolsters Trust in Fintech Products

Applied AI

How to Enhance Data Privacy with AI

Applied AI

How to build a highly effective data science program

Applied AI

Thoughts from AWS re:Invent

Applied AI

AI Consulting in Healthcare: The Complete Guide

Applied AI

Understanding MLOps: Key Components, Benefits, and Risks

Applied AI

Announcing Tribe AI’s new CRO!

Applied AI

7 Prerequisites for AI Tranformation in Healthcare Industry

Applied AI

A Deep Dive Into Machine Learning Consulting: Case Studies and FAQs

Applied AI

No labels are all you need – how to build NLP models using little to no annotated data

Applied AI

Key Generative AI Use Cases From 10 Industries

Get started with Tribe

Companies

Find the right AI experts for you

Talent

Join the top AI talent network

Close
Trevor Noon