Myles Sutholt

Cohort 1

Cohort 3

Cohort 2

AI advisors built from real podcast transcripts — trained on their actual frameworks, vocabulary, and opinions. Not generic AI. Their thinking.Built from 289 Lenny's Podcast episodes. Not affiliated with Lenny or any advisor. Free.

Get a second opinion from the people who shaped modern product thinking.

Most of us can't tell when we're producing low quality output with AI. Because AI is confident. It doesn't hedge. It doesn't say "I'm guessing here" or "I actually have no idea what your project constraints are." It just writes like it knows.There's a word for this. It's called work slop. It's work that looks professional but lacks substance. The formatting is clean. The structure makes sense. But half of the content is assumptions the AI made because you never told it otherwise. Here is how to prevent it.

How to Improve AI Output Quality

I&nbsp;wanted to understand what I can improve in meeting facilitation. So I built something: my&nbsp;transcripts go to AI, and it tells me what I actually did. Pulls exact quotes.&nbsp;Scores my communication and leadership. Two ways to build yours:&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;Quick (30 min): Zapier automation with the full prompt I use.&nbsp;&nbsp;&nbsp;Full (2-4 hrs): A PRD to vibe-code&nbsp;something sophisticated with role detection,&nbsp;incident flagging, daily digests. Both work. Both are useful. Neither knows your specific role in each meeting or your patterns over time.

Meeting Feedback Tool

This is an actual weekly review generated by my system every Friday. 230 lines covering priorities, progress, blockers, team health, and next week's focus; synthesized automatically from my calendar, tasks, and project docs.

Weekly Review Sample

The one file that changes every AI conversation. Learn the manual technique I used before building the full system. A simple decision log that makes AI remember what you've already decided. Includes copy-paste prompts you can use today.

Decision Log Quick Start

I'd been using Claude Code heavily for months. Dozens of projects. Thousands of messages. Then I saw a LinkedIn post pointing out that Claude Code stores every conversation locally—raw text files on your computer. I realized I had a dataset that could answer this question precisely. I'm running this analysis again in March. Similar methodology, fresh and expanded data (I will try to get my hands on other peoples data). I want to see if my friction rate drops—or if I just get better at catching it faster.

LLM Friction Analysis

Three protocols that address 80% of AI collaboration friction. From analyzing 1,577 messages: when Claude sounds certain but isn't, when "good enough" reading isn't, and when the right idea gets wrong execution. Copy-pasteable instructions for your sessions.

Friction Prevention Toolkit

How to build a system that handles the work you shouldn't be doing and sharpens the work only you can do.

Head of Product | AI for non-tech users

Head of Product who uses the system he teaches every day with his team.

Build Your AI Chief of Staff

Senior Software Engineer

Senior Product Manager Search

Product Manager

Product Associate

Product Owner

UX Designer

Senior Product Manager

Data Engineer

Booking.com

DeepL

ABOUT YOU

Zalando

TikTok

Price will increase to $749 in May.You already use AI. You probably think it is going well.When researchers measured experienced professionals using AI on real tasks, they were 19% slower. They believed they were 20% faster. (METR, 2025)"I thought I was already using AI well. Turns out I was just using it often." — Wole, Product DesignerThe gap is not your skills. It is what AI knows about your work before you start. Your projects, priorities, stakeholders, what "good" looks like. Without that, every session starts from zero.This course builds two things. First: a system that handles the recurring work and frees up roughly half a day a week. Second: AI advisors modeled on your real stakeholders that challenge your documents, prepare you for meetings, and catch what you missed."A system I use every single day. One that has increased the quality of my work immensely." — Renata, Product OwnerLimited to 20 students. Personal feedback on every submission.

Stop doing work your AI should do. Delegate, systematize, and scale yourself.

Your AI Already Knows Your Work

Automate the Work That Drains Your Week

AI Advisors That Challenge Your Thinking

Output That Is Visibly Better

A System That Compounds

No Coding Required

You already use ChatGPT, Claude, or similar tools regularly. Not just tried once. You have AI habits you want to build on.

Use AI (like ChatGPT or Cursor) regularly (not just tried once)

You need to install tools like Claude Code or Cursor. Some company laptops block this. If you are unsure, check with your IT team.

Can install software 

You will see code you did not write. AI writes it. You describe what you want in plain English. We walk you through every step.

Willing to try things that feel unfamiliar at first

You get decent output but re-explain context every session. You want AI that knows your work and challenges your thinking.

PMs, designers, engineers, data professionals. The title matters less than the work: multiple projects, documents, decisions across teams.

You want to walk into meetings having already stress-tested your arguments. You want documents that survive the first round of review.

How I Turned AI into My Best Advisor

Head of Product | 10+ years building product teams

Watch two demos that show the difference between generic AI and AI that knows your domain

Experience specialized AI in action

Take home a Zapier template + evaluation prompt you can run on your own meetings tonight

Get a working meeting feedback coach

Get free access to 35 of my advisors and try an advisor on your own documents for marketing or product management.

Access 35 expert AI advisors

See what pre-built advisors can do, and understand what it takes to build your own

Understand the gap between using and building

How I Stop Starting Over Every Time I Open AI

Create a structured file with four sections that works in any AI tool and acts as kickstarter for every session.

Build a memory file for one active project

Learn how to write documentation for AI, not for humans to effectively manage context limits.

Structure information so AI actually uses it

See what changes when AI loads context automatically instead of needing you to paste it every session

Understand the gap between pasting and automatic

How I Stopped AI from Making Things Up

Identify the patterns where AI fills gaps with made-up context instead of asking you

Spot work slop before you ship it

Learn a proven way to document context for your AI to take from one session to another.

Provide the right context first

Compare generic AI output to context-informed output on the same task, live

See the before/after of AI with and without context

How to Build a Meeting Feedback Coach (No Coding Required)

No coding needed. You leave with a working version you can set up tonight and start growing tomorrow.

Build a meeting feedback coach

Your feedback coach will help you identify strength and weaknesses and teach you how to improve.

Receive helpful feedback that helps you grow

Identify what your coach needs to know to successfully mentor you towards greatness.

The missing layer between generic and useful

Build a Shared AI Memory for Your Team

Create a simple structure that captures your team's decisions, reasoning, and open questions your team's AI can access.

Create a documentation that your team collaborate on

Connect your documentation to shared storage so any teammate can pull the same context into their next AI conversation.

Sync Team Context across devices

Learn how to bring shared context to whatever LLM (Claude, ChatGPT, or Cursor) your team uses.

Let your team pick up where you left off

Get AI Output That Beats Your Own

Head of Product building AI products for non-tech users

What's actually happening when AI produces shallow, assumption-filled work - and why more prompting won't fix it.

Why AI output feels generic

A practical workflow where AI interviews you about context, goals, and decisions before producing anything.

Flip the dynamic: How to get AI to fill the gaps

How to capture the conversation into documents that make every future AI interaction on that topic better.

Learn directly from Myles Sutholt