The Growth Podcast

Today’s episode
Most PMs start every day like this. Open the calendar. Open the CRM. Open Slack. Open the meeting notes. Open LinkedIn. Piece together what matters. Lose 30 minutes before real work even starts.
That is not how the best PMs are working anymore. The best PMs are running one command in the morning and getting everything they need in five minutes. Their calendar, their deals, their market intel, their career gaps, all pulled together automatically.
That shift is what today’s episode is about.
I sat down with Dave Killeen, Field CPO at Pendo.io. He has worked at BBC, Mail Online, and now runs the field product function at one of the largest product management platforms in the world. He has 25 years in product. Over the last few months, he built a full personal operating system called DEX in Claude Code, open sourced it on GitHub, and it is getting serious traction.
In this conversation, Dave walks through his entire system live on screen. You will see how he runs a daily plan, creates PRDs from a backlog, manages parallel workstreams on a Kanban board, and tracks his career goals, all from one terminal window. And you will learn the three building blocks that make it all work.
----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by
* Pendo: The #1 software experience management platform
* Jira Product Discovery: Plan with purpose, ship with confidence
* Amplitude: The market-leader in product analytics
* NayaOne: Airgapped cloud-agnostic sandbox
* Product Faculty: Get $550 off the AI PM Certification with code AAKASH550C7
----
If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakash’s bundle.
----
Key Takeaways:
1. One command replaces your morning routine - Dave's daily plan slash command pulls from calendar, CRM, Granola, LinkedIn, YouTube, and 120 newsletters in five minutes. No tab switching. No manual assembly.
2. MCP servers are the key to connecting everything - Point Claude at any API documentation with your API key and it builds an MCP server for you. MCP provides structured guardrails that make the AI's behavior consistent and deterministic.
3. Skills, MCP, and hooks are three different things - Skills are plain English job descriptions for what the AI should do. MCP servers are structured integrations for connecting external services. Hooks are triggers that fire at specific conversation moments.
4. Session start hooks make the system compound - Every new Claude Code chat gets injected with weekly priorities, quarterly goals, working preferences, and past mistakes. The AI never starts from scratch.
5. Living markdown files are the compounding mechanism - Every project, person, and company gets a markdown file that accumulates context from meetings, messages, and intel over time. The more you use the system, the smarter every file becomes.
6. You can build a mobile app in 37 minutes - Dave built the full app with Claude and spent more time in Xcode publishing it. The constraint is taste, not building speed.
7. The AI should hold you accountable - Dave's Claude MD file includes "harsh truths for Dave" that the AI wrote after auditing his system. This gets injected into every session to prevent the same mistakes.
8. Career planning should compound like product data - A career MCP server collects evidence, runs gap analysis, and calculates promotion readiness. When review time comes, the evidence is already assembled.
9. Be precise about your goal, not the path - The kindest thing you can do for the AI is give it a very clear destination. Do not tell it how to get there. Let it figure out the most elegant approach itself.
10. Voice-first changes everything - Using Whisperflow or Super Whisper instead of typing fundamentally changes how you interact with Claude. You think out loud. The conversation flows. You build faster.
----
Where to find Dave Killeen
* LinkedIn
* Pendo
----
Related content
Newsletters
* The PM operating system guide
* How to use Claude Code like a pro
* Master AI agent distribution
* Claude Cowork and Code setup guide
* The AI PM tool stack
Podcasts
* Frank Lee on Claude Code and MCP workflows
* Carl Vellotti on Claude Code operating systems
* Rachel Wolan on AI PM workflows
* Caitlin Sullivan on building with Claude
----
PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!
If you want to advertise, email productgrowthppp at gmail.


This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe

Today’s episode
Most PMs are using AI the same way they used Google in 2005.
Type something in. Get something out. Move on.
That is not how the best PMs are using it. The best PMs have stopped treating AI as a search engine and started treating it as a team member. One that already knows their product, their writing style, their strategy. One that does not need to be briefed from scratch every single time.
That shift is what today’s episode is about.
I sat down with Lisa Huang, SVP of Product at Xero, an $18 billion finance platform. She built the AI assistant for the first generation Meta RayBan smart glasses. She created Gemini Gems at Google. She has been an AI PM at Apple, Meta, and Google - three of the most demanding AI product environments in the world.
She gave us a masterclass across Gemini Gems, building AI into hardware, running AI agents at scale inside a financial product, and what the AI PM career actually looks like from here.
In today’s episode, we discuss across three topics.
* How to build Gemini Gems and AI projects that actually work.
* What she learned building AI into a wearable device.
* What the future of the AI PM career actually looks like.
----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by - Reforge:
Get 1 month free of Reforge Build (the AI prototyping tool built for PMs) with code BUILD
----
If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakash’s bundle.
----
Key takeaways:
1. Stop briefing your LLM from scratch every time - Gemini Gems hold your context permanently. Your role, your company strategy, your writing style. Build it once and it already knows everything the next time you open it.
2. Every PM needs 3 Gems - A writing clone trained on your PRDs and emails. A product strategy advisor loaded with your company docs and competitor analysis. A user research synthesizer that ingests raw transcripts and surfaces key themes.
3. Vague instructions are the number one mistake - "Help me write better" gets you nothing. Write a full page of context. Your role, your audience, your format preferences. The more specific, the more personalized the output.
4. Gemini Gems vs ChatGPT custom GPTs - OpenAI framed GPTs as an app store ecosystem. Google focused on personal productivity instead. First principles beat copying a competitor's framing, and the GPT store never took off.
5. On-device AI is the future for wearables - Cloud is the default today but once a device is on your face all day, people want their data staying local. Privacy beats performance when the device is that personal.
6. Accuracy is the product in high-stakes AI - LLMs out of the box are not great at math, accounting, or tax. Winning agents combine deep domain knowledge with proprietary data that no general-purpose model can access.
7. Measure agents in three layers - Quality first (evals, human annotators, LLM judges). Product metrics second (adoption, retention, CSAT). Business impact third (revenue attribution, ARR). Skip to layer three without the foundation and you are measuring on sand.
8. AI will not replace PMs - it will replace the execution work. Writing PRDs, creating mocks, managing roadmaps. What stays is product judgment. The ability to look at ambiguous signals and say this is the right bet and here is why.
9. The PM role is becoming a hybrid - PM to engineer ratios will compress. The expectation is that PMs also build. Not just spec and hand off, but prototype, design, and code enough to show what they mean. The tools to do this exist right now.
10. Your company's permission is not required - Most companies are not fine-tuning models. They are using the same consumer tools you already have. Build Gems. Build projects. Build small AI products with your personal data. There is nothing stopping you.
----
Where to find Lisa Huang
* LinkedIn
* Website
Related content
Newsletters
* How to become an AI PM
* Practical AI agents for PMs
* AI evals explained simply
* AI product strategy
* The AI PM learning roadmap
Podcasts
* Claude Code + Analytics - Vibe PMing with Frank Lee
* AI evals explained simply with Ankit Shukla
* How to become an AI PM with Marily Nika
* AI prototyping mastery with Sachin Rekhi
----
PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!
If you want to advertise, email productgrowthppp at gmail.


This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe

Today’s episode
AI prototyping tools are redefining what it means to be a PM.
Bolt went from 0 to $40M ARR in 4.5 months. Lovable hit $17M ARR in 3 months. Every forward-thinking product team is starting to prototype earlier, faster, and at higher fidelity than ever before.
But most PMs are using these tools wrong.
They open Bolt or Lovable, type a vague prompt, get something that looks decent, show it around, and move on. No problem space work. No divergent solutions. No user testing. The prototype dies in a Slack thread and nothing changes.
In this episode, we built a LinkedIn sentiment analysis feature from scratch - live - to walk you through the complete workflow. From blank page to multi-page, clickable, high-fidelity prototype. We covered when to prototype, how to prompt, when to go high fidelity, and how to hand off to engineers with zero open questions.
If you watch, you’ll also learn why your PRD and prototype need to live together - and why that combination is the new standard for forward-thinking PMs.
----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by:
* Pendo: The #1 software experience management platform
* Testkube: Leading test orchestration platform
* Gamma: Turn customer feedback into product decisions with AI
* Product Faculty: Get $550 off the AI PM Certification with code AAKASH550C7
* Mobbin: Discover real-world design inspiration
----
If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakash’s bundle.
----
Key Takeaways:
1. AI prototyping doesn't replace problem space work - it accelerates solution space work. Before opening any prototyping tool, lock down the problem, the user story, and the rough shape of the solution. If you can't write all three in one paragraph, you're not ready.
2. Always start from your design system, not a blank page - Drop a screenshot of your existing product and ask the tool to recreate it. Save that as a team template. Every prototype you build from that point looks like it belongs in the product.
3. Build 3 to 4 divergent solutions before choosing one - The entire point of AI prototyping is that building a second and third version costs almost nothing now. We built two versions of the sentiment analysis feature live. Neither was perfect. Both were useful. That comparison is the point.
4. Use visual editing for fine-tuning, not prompting - Once you've picked the strongest direction, switch to direct visual editing. Move elements, match colours with the eyedropper, adjust spacing. It's faster because the result is immediate.
5. Single-page prototypes miss too much - Build the full end-to-end flow. The moment you start connecting pages, edge cases surface automatically. We found two edge cases in minutes that would have cost engineering time in sprint.
6. Prompt clarity beats prompt engineering - Any ambiguity in your prompt will get exploited statistically. Before running a complex prompt, paste it into a separate chat and ask it to find the contradictions. Fix those first.
7. Use discuss mode before building anything major - Don't ask the AI if it can do something. That always gets a yes. Ask what it thinks the right approach is. The answer is far more honest and useful.
8. High fidelity is for selling and usability testing - Low fidelity is for team exploration. Any prototype going in front of users needs to feel real, otherwise you get feedback about the roughness, not the experience.
9. The PRD and prototype should live together - The PRD covers edge cases, empty states, error conditions. The prototype covers the 90% flows. Together they leave zero open questions for engineers. If someone reads both and still has a question, something is missing.
10. The prototype is already standard code - A functional prototype built in Dazzle is a full server-side and client-side application. Download the project folder, drop it next to the production codebase, and tell Cursor to copy the interaction. Most of the implementation gets handled automatically.
----
Related content
Newsletters
* Product Requirements Documents (PRDs): a modern guide
* Ultimate guide to AI prototyping tools (Lovable, Bolt, Replit, v0)
* Your guide to AI product strategy
* AI PRDs: everything you need to know
* AI agents: the ultimate guide for PMs
Podcasts
* The most powerful AI workflow for PMs with Frank Lee
* How to engineer delight into AI products with Nazarin Shenel
* AI prototyping tools with Eric Simons, CEO of Bolt
----
PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!
If you want to advertise, email productgrowthppp at gmail.


This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe

Today’s episode
There is a term Andrej Karpathy coined last year: vibe coding.
We have the same for product management: Vibe PMing.
You describe the problem. The agent pulls the data. Analyzes the chart. Synthesizes the feedback. Drafts the spec. Files the ticket.
That is not theory. That is what I walked through in today’s episode with a principal PM at Amplitude who builds MCP and agent products for a living. He showed it live, on screen, in real time.
If you tune in, you’ll learn the full end-to-end workflow:
----
If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakash’s bundle.
----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by:
* Amplitude: The market-leader in product analytics
* Pendo: The #1 software experience management platform
* Testkube: Leading test orchestration platform
* Product Faculty: Get $550 off the AI PM Certification with code AAKASH550C7
* Bolt: Ship AI-powered products 10x faster
----
Key Takeaways:1. Claude Code + MCP is the most powerful AIPM workflow today - Connect your analytics tool via MCP, load your product context into a repo, and let the agent do analysis that used to take hours in minutes.2. Deep chart analysis now takes 90 seconds instead of 3 hours - Drop a chart URL into Claude Code, trigger the analyse chart skill, and the agent navigates your data taxonomy, finds anomalies, and hypothesises why metrics changed.3. Automate your entire weekly business review - Point Claude Code at your dashboards Monday morning. Get 3-5 top insights and the one urgent issue to tackle — no manual dashboard scanning ever again.4. Customer feedback synthesis across all channels in one pass - Zendesk, Gong, Salesforce, Slack, app stores all unified. Claude Code navigates the MCP, clusters themes, and surfaces what customers love and hate that week.5. PRDs write themselves from insights - Take the analysis output, point it at your PRD template in Cursor or Claude Code, and get a first draft spec in under 2 minutes. Iterate with command L or command K.6. Skills are the most important Claude Code feature - A skill is just a named prompt with heuristics and tool instructions. It loads only when relevant, preventing context bloat and giving the agent a repeatable workflow.7. The biggest MCP mistake is connecting too many servers - Every tool description burns context. Load only what's relevant to the workflow. Remove or hide tools that aren't being used for a given task.8. MCP is not for complex orchestration — it's for data access - Set the right expectation. MCP connects AI to external systems easily. It's the first step, not the whole pipeline.9. Granola has no MCP, so build a script instead - Frank used Claude Code to write a local script that dumps Granola meeting notes into his product repo. Now he can pull all meeting context with a single at-command.10. The future of PMing is vibe PMing - Chart analysis, dashboard reporting, feedback synthesis, spec writing, and prototyping — all agent-driven. PMs who adopt this workflow now will have a massive advantage in 2-3 years.
----
Related content
Newsletters:
* How to use Claude Code like a pro
* Steal 6 of my Claude skills
* Context engineering
* The AI stack for PMs
* Practical AI agents for PMs
Podcasts:
* How to build an AI-native PM operating system with Mike Bal
* AI evals explained simply with Ankit Shukla
* Advanced guide to AI prototyping with Sachin Rekhi
PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!


This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe

Today’s Episode
Designing with AI isn’t about prompting.
Most PMs think they understand AI design because they can write a good prompt. They’re wrong.
Real AI design is about understanding the entire workflow, the system, the constraints, and the behaviors.
Xinran Ma runs Design with AI, one of the top newsletters on AI design. He’s been studying AI design tools for three years. And he hasn’t shared most of this information publicly before.
In today’s episode, we’re going live. We’re building real prototypes. We’re showing you the exact workflows that top 1% designers use.
By the end of this episode, you’ll know the entire workflow from PRD to prototype to product.
----
Check out the conversation on Apple, Spotify and YouTube.
Brought to you by:
* NayaOne: Airgapped cloud-agnostic sandbox
* Pendo: The #1 software experience management platform
* Maven: The cohort-based course platform powering the future of learning
* Bolt: Ship AI-powered products 10x faster
* Gamma: Turn customer feedback into product decisions with AI
----
If you want access to my AI tool stack - Dovetail, Arize, Linear, Descript, Reforge Build, DeepSky, Relay.app, Magic Patterns, Speechify, and Mobbin - grab Aakash’s bundle.
----
Key takeaways:
Key Takeaways:1. AI design covers five areas not just prompts - Prompting, ideation, design/prototyping, workflows, and staying conscious. Most people think better prompts equal better design. That's just 20% of the skill.2. Use Google AI Studio for quick design variations - Upload 2-3 visual references. Describe what you want. Generate three different design directions in 5 minutes. What used to take 3-4 hours now takes 15 minutes.3. Lovable builds functional prototypes in seconds - Describe the experience you want to build. Lovable generates a working prototype in 60 seconds. Not mockups—actual clickable experiences you can test with users.4. Match tools to specific use cases - Custom GPT for effective prompts. Lovable for high-quality prototypes. Magic Patterns for design variations. Google AI Studio for free exploration. Cursor for full-stack experiences. Claude Code as all-purpose best.5. Good design passes four layers not just visual - Visual representation, problem-solving, design principles, and implementation feasibility. Most people stop at layer one. Great design works at all four layers.6. Context matters more than prompt length - Don't say "design a button." Say "design a primary CTA button for B2B SaaS onboarding where users connect calendar. Professional brand." Specificity drives quality.7. Visual references anchor AI output - Upload 2-4 screenshots showing the aesthetic you want. These show AI what "modern and minimal" means to you. The quality difference is massive versus text-only prompts.8. Iteration speed determines final quality - The magic isn't in the first output. It's in the 10th iteration after you've refined and tweaked. Review, identify issues, tell AI how to fix, repeat.9. Always validate with real users - AI tools make generating designs easy. Only users tell you if those designs actually help. Show prototypes to 3-5 users. Watch them try to use it.10. Workflows changed from linear to parallel - Before AI: sequential steps taking weeks. After AI: describe, generate, iterate freely. This is how top 1% designers work now.
----
Where to Find Xinran
* LinkedIn
* Newsletter
* Maven course
Related Content
Newsletters:
* AI Prototyping Tutorial
* AI Prototype to Production
* How to Build AI Products
* Prompt Engineering
* Product Requirements Documents
Podcasts:
* Advanced Guide to AI Prototyping with Sachin Rekhi
* AI Prototyping for PMs
* How to Become an AI PM
* Everything You Need to Know About AI
----
PS. Please subscribe on YouTube and follow on Apple & Spotify. It helps!
If you want to advertise, email productgrowthppp at gmail.


This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.news.aakashg.com/subscribe