All Articles

4 New Evals and 16 Experiment Variants to Fix 1 Customer Complaint

"That is a lot of first layer opportunities there. I wish I could click on this card and be like, 'Clean this up.'" This was a Vistaly customer reviewing her first AI-generated opportunity solution tree. Up until this point, the feedback was extremely positive. But

AI Evals: A Hands-On Guide for Product Teams

AI evals have been the "it" skill for product teams for over a year. I've even called evals a new discovery habit. But I still meet product teams who only have a vague idea of what evals are. And it's not their fault. Most

The Call to Adventure

In June, I returned to Product at Heart in Hamburg, Germany. I love this event. Arne Kittler and Petra Wille do such an amazing job of curating a thoughtful lineup of speakers and they obsess over the attendee experience. If you are looking for a high-quality product conference, I

Most Package Hacks Get in the Same Way: How I Block Common Entry Points

My initial reaction to the recent package hacks was fear. But I quickly learned I can mitigate much of the risk with a handful of configuration settings. If you haven't been following along, a large number of packages (think of packages as bundles of reusable code) have been

What I Learned from the Recent Wave of Package Hacks (And Is Cowork Immune?)

I love being a builder. I feel like I have a new superpower and I can't get enough of it. I enjoy tinkering with my Claude Code workflows to make my days more effortless. I'm having a blast building AI-generated interview snapshots and opportunity solution

My Team of Agents: How I Get Claude to Do Tasks While I'm Away from the Computer

Every morning I wake up and Claude has already added several tasks to my to-do list. If I have a podcast recording on the calendar, my podcast-manager agent (powered by Claude) prepares a podcast-interview-prep task with a summary of who I'm interviewing and what

Behind the Scenes: Building AI-Generated Opportunity Solution Trees

I just finished an all-out engineering sprint. That sounds weird to me. I've been writing code on and off for several years. But I wouldn't call myself an engineer. I'm a product manager. And I used to be a designer. It's

How to Share Your AI Context and Skills Across Devices

I've been hosting Claude Code office hours for the past few months and by far the most common questions I get are around sharing context and skills. I'm hearing from a lot of people who are leading AI adoption in their companies. They've developed

Product Roadmaps: How the Best Product Teams Plan for Uncertainty

We need to talk about product roadmaps. I once worked at a startup where our product roadmap was literally an Excel spreadsheet full of feature ideas. Most of them came from our CEO. Our head of product simply prioritized the rows. Based on what, I have no idea. This is

Vibe Coding Best Practices: Avoid the Doom Loop with Planning and Code Reviews

I've written more software in the past six months than I've written in my entire lifetime. I started vibe coding in March 2025. My first foray was extraordinarily successful and then resulted in complete failure. I was blown away when Replit helped me build a custom

Outcomes vs. Outputs: What's the Difference and Why Does It Matter?

Outcomes over outputs—everyone knows the mantra. But putting it into practice can be deceptively hard. It's relatively easy to understand the concept. We should focus on the impact of what we build rather than just shipping features that people may or may not want. But it'

Conversations with Claude: Can You Conduct a Content Audit?

During one of our recent Claude Code Office Hours, a participant asked, "Can we zoom out? Help me understand what I can use Claude Code for." This is a great question. I was so focused on how to help people set up Claude Code that I forgot to

Stakeholder Management for Product Teams: Show Your Work, Don't Sell Your Conclusions

Everyone I talk to is rushing to add AI features to their roadmap. And every stakeholder has an opinion about what they should be building. The challenge is we are forgetting our discovery fundamentals. We are reverting back to a feature factory. Delivery is getting faster and easier, so it

From Customer Interviews to an Opportunity Solution Tree—In Minutes

Most product teams know they should be interviewing customers. And more teams than ever are actually doing it. That's the good news. The bad news? Many teams are struggling with what comes next. I've written before about the challenge of interview synthesis—going from a stack

Context Engineering: 5 Familiar Strategies from Real Product Teams

I've been getting a lot of questions about why I'm diving so deep into Claude Code. So I want to take a step back and provide some context. Last March, when I started building my first AI product—the Product Talk Interview Coach—I felt like

Context Rot: Why AI Gets Worse the Longer You Chat (And How to Fix It)

Have you ever noticed that AI gets worse the longer you talk to it? I first noticed this when I was trying to fix bugs on Replit. I'd spin in an endless cycle of asking the agent to fix something and it would report back that it fixed

How Does ChatGPT Work? A Guide for the Rest of Us

Everybody is buzzing about generative AI and there's a lot of jargon that comes along with it: tokens, embeddings, attention, neural networks, transformers. Whether we are talking about ChatGPT, Claude, or Gemini, the large language models all work the same way. But understanding how they work can be

Exploring What's Just Now Possible: How AI-Powered Discovery and Expert Feedback Are Driving My 2026 Roadmap

2025 was full of many surprises. Some good ones—I launched two new podcasts, I built my first AI products, I completely changed the way I work thanks to Claude Code. And some tough ones—I'm still struggling to fully recover from a severe ankle break in March,

How to Use Claude Code: A Guide to Slash Commands, Agents, Skills, and Plug-ins

I've been going deep on Claude Code. I'm finding this has been a better strategy for getting value out of AI—rather than trying every new tool on the market. By focusing on one tool, I've been able to learn how to use Claude

2026 Product Conference List

We are starting to pull together our list of 2026 product conferences. This list is by no means exhaustive. If you know of product conferences that are not on the list and you think they should be, please send an email to conferences@producttalk.org. We’ll also keep updating

How to Build AI Workflows with Claude Code (Even If You're Not Technical)

My writing process used to be messy. I'd start with a brain dump of everything that was swirling in my head. Then I would try to structure it into an outline. But I often lost patience with that. So I'd just start writing. Then I'

How to Choose Which Tasks to Automate with AI (+50 Real Examples)

Every morning, I sit down at my computer with my cup of coffee and I type /today into Claude Code. I take my first few sips of coffee as I watch Claude retrieve new tasks from my Trello board, generate a today.md file with a list of what I

Lessons from 9 AI Product Teams: Emerging Themes from Just Now Possible

Stack Overflow built four versions of their AI-powered search, then killed it. Arize's team started building when "agent frameworks" didn't even exist. eSpark's former teachers are now writing eval code in Python. Over the past few months, I've had

How to Use Claude Code Safely: A Non-Technical Guide to Managing Risk

I love that Claude Code allows me to build out my own personal operating system. I now have personal workflows for managing my to-do list, keeping up on academic research related to my work, hosting two podcasts, writing long-form weekly articles, designing courses, and much more. I used

Stop Repeating Yourself: Give Claude Code a Memory

"Can you critique the landing page for my new Story-Based Customer Interviews course?" I used to waste hours trying to get ChatGPT or Claude to adequately critique my work. I'd get frustrated by the generic feedback, the poor writing, and the suggestions that just wouldn&