How to Leverage AI in Product Development

The more I used AI to build, the less magical it felt. After spending weeks trying to rebuild our platform with Claude/ChatGPT, I realized a hard truth: What started as a productivity hack turned into a full-time prompt engineering job. Don't get me wrong, AI is mind-blowing at what it does. But you have to think of it the right way: Even with recent updates like Claude Code + Sonnet 3.7, AI still needs your architectural vision and continuous feedback to deliver production-quality results. I recently shared my experience with AI coding, and dozens of engineers and leaders jumped in with their own battle-tested insights (original post in comments). These were the strongest insights and recommendations: - Design the architecture first, then let AI do the implementation following YOUR architecture. - Instead of asking AI to build the whole car at once, ask it to build individual parts separately. - Iterate and guide: Aiming for perfection on the first prompt response will not work. - Start with AI-written unit tests to ensure your expectations align with the output (hello TDD 😉). - And finally, remember that AI can only code as well as you can architect and explain. These insights are from engineering professionals who are making AI work instead of creating more work. The gap between using AI and using it WELL is wider than most realize, and the teams closing this gap are the ones getting real results. What's your most effective technique for integrating AI into your development process? — Big thanks to Antons Kumkovs, Michael Rollins, Winner Emetuche, Drew Adams, Domingo Gómez García, Ryan Booth, Michael Fanous, David Cornelson, Youssef El Hassani, and Michael L. whose comments are included in the carousel 👇

AI has fundamentally changed how I work—and the shift’s only accelerating. At Demandbase we’re deep into building with AI every day. But it’s also reshaping how I operate personally across product, strategy, and execution. A few ways I’m using AI regularly: 1. Strategy framing & content generation Need a vision narrative, roadmap framing, or design partner FAQ? I start with AI. Press releases, product naming, OKR drafts—it’s faster to pressure-test ideas and get out of blank-page mode. 2. Research & insight gathering Market analysis, competitor moves, customer behavior patterns—what used to be slow or outsourced is now async, overnight, and high quality. I’ll queue research at night and review insights in the morning. 3. Prototype iteration Late-night product ideas? I use tools like Cursor, Claude, and Windsurf to spin up frontend mockups or workflows—just enough to challenge assumptions and drive clarity in vision. 4. Meeting prep & content reviews Heading into a customer pitch or exec review? I’ll use AI to summarize notes, dig through CRM content, or surface potential gaps. It’s a second brain for context I don’t have time to gather manually. The byproduct? My expectations are shifting. Not just for AI itself—but for how quickly high-leverage work should now move. We’re not just building AI at Demandbase. We’re operating with it, every day. #AI #Agentbase #ProductLeadership #ExecutionMatters #EnterpriseAI #GTM #Demandbase

Here are four things to turn your team into an "AI-first team". They're pretty simple but require putting in the work. It's worth it: I'm seeing first-hand at Augment Code the agility of a team that uses AI all the time. I didn't expect they'd have this much fun doing it. AI-first teams start with "How can I use AI for this?", from mundane tasks to strategic projects. They: - automate their work and that of others - move much faster, - produce better work, - bring more value to customers and… - enjoy their work more! 1️⃣ Equip and empower your team. Even starve it a little - Find and elevate your AI champions—they'll pull the team along - Create dedicated time for sharing AI techniques and learnings: offsites, afternoon blocks, a “demo my AI workflow” section at every all-hands - Unlock significant budgets for AI tools and training. Get them approved by IT & Security. Your team should not fear using them - Gradually reduce resources for tasks AI can handle. This creates pressure to adopt new approaches 2️⃣ Enable your primary LLM, as you enable Sales - Whether ChatGPT, Claude*, or Google Gemini, set one up as the primary tool with your knowledge bases. Create GPTs, gems, on top of it - Task Product Marketing with adding and maintaining foundational knowledge as essential context to these models, so the rest of the team benefits and is on message. Include messaging docs, persona cards, ICP, competitor intel, battle cards, case studies, brand voice and tone style guide... The output of the team’s work will be on-brand and relevant to customers. 3️⃣ Hiring: assess for AI-first skills and mindset. Go deep - Dedicate a whole focus interview to assessing AI skills and mindset. Ask these questions: - Innovation: What are three effective ways you have leveraged AI recently? - AI leadership: What role did you play in enabling your extended team? - Continuous learning: How do you learn and get new ideas about the latest AI tools and best practices? What resources do you recommend I use and why? If you give an assignment, explicitly encourage using AI. Require that candidates share their process. See if and how they use it. 4️⃣  Inspire, assess, and reward your team - Ask “How will you / have you used AI for that?” in every one-on-one (put a sticky note by your/their desk) - Make “Acting AI-first” a key chapter of performance reviews - Recognize, give more scope to, and promote your AI champions. Fast and visibly - Lead by example, of course This list is not exhaustive. If you did other things that worked well, don't hesitate to add them in comments. 

Are you a product manager looking to find how AI can help you be more productive and innovative? Recently, I've been researching the art of getting quality responses from AI using well-structured prompts. In many tasks, it's increased my productivity and creativity significantly. I'm certain it can do the same for you. Here are five tips that might help you in your daily work as a product manager or in product development: ✅ Drafting User Stories: Provide clear instructions and let ChatGPT draft detailed user stories for your product features. This saves you time and ensures consistency. ✅ Creating Questionnaires: Simplify your interview preparations by using ChatGPT to generate tailored questionnaires. Well-crafted questions lead to insightful user feedback. ✅ Predicting Trends: Explore future possibilities by asking ChatGPT to analyze data and predict trends. This helps you stay ahead and make data-driven decisions. ✅ Brainstorming Features: Use ChatGPT to generate new ideas for features or product extensions. Fresh perspectives can spark innovative solutions. ✅ Enhancing User Experience: Analyze the customer journey with ChatGPT to identify pain points and suggest improvements. Enhance user satisfaction with actionable insights. The key is in providing clear, detailed instructions. The more context you give, the better the output. While AI can’t read minds (yet!), it can certainly help you work smarter, not harder! Found this insightful? Give this a thumbs up and follow me as I share my insights around digital transformation, product development and being an AI Power User. 😎