How to Become a Builder PM (n8n, Claude Code, OpenClaw)

1. 0:00 – 1:53

   Intro

   1. MYMahesh Yadav0:00

      I would love to send this message to all PMs that this is our time to shine. There is a lot of misconception there that, you know, if you start using Claude Code or if you configure OpenClaw, you become a builder PM.

   2. AGAakash Gupta0:13

      Mahesh Yadav, who's been a PM everywhere, Microsoft, Amazon, Meta, last but not least, Google.

   3. MYMahesh Yadav0:19

      This is the time to build your own world, and I believe in that future, and that's why I left, and I have zero regrets. If you know your skills, you can build it in Claude Code and delegate that work to agents. I don't know its limitations. It does anything that I want it to do. This is an open challenge I have given to anybody, that if you can do a job, just tell me the job and this agent will do it better than you three sixty-five days, twenty-four hours. Everything which used to take you almost two to three months first to write the PRD to get to mocks, from mocks to a real working prototype, from there to getting customers and seeing the signals, all that is getting squeezed with this Claude Code, and you become the builder PM that the world needs. The ability to sandbox these agents in a controlled way, that's an unsolved problem. And that I think is what I am excited about.

   4. AGAakash Gupta1:11

      Google isn't gonna allow you to just give your company access to an OpenClaw.

   5. MYMahesh Yadav1:17

      Yeah, no, I 100% agree. I think the idea is-

   6. AGAakash Gupta1:22

      Before we go any further, do me a favor and check that you are subscribed on YouTube and following on Apple and Spotify podcasts. And if you wanna get access to amazing AI tools, check out my bundle, where if you become an annual subscriber to my newsletter, you get a full year free of the paid plans of Mobbin, Arise, Relayapp, Dovetail, Linear, Magic Patterns, DeepSky, Reforge Build, Descript, and Speechify. So be sure to check that out at bundle.aakashg.com, and now into today's episode.

2. 1:53 – 6:04

   What is a builder PM

   1. AGAakash Gupta1:53

      PMs are now being asked to push PRs. PMs are being asked to code. This is the rise of the builder PM. But what is a builder PM? Today, I have Mahesh Yadav, and today he's gonna help you understand, how do I become a builder PM? How do I use n8n? How do I use Claude Code? How do I use OpenClaw in order to become a more effective and efficient PM, even if I'm not building AI feature? Mahesh, everybody loved our last episode. Thanks for coming back.

   2. MYMahesh Yadav2:21

      Oh, thank you for having me. And I think this is the time of urgency, so I would love to u- use your platform to send this message to all PMs that, uh, this is our time, and we should be ready when this time arrived. I was always preparing for this time, and now the time is right for all the PMs to shine. It's just little bit that we need to go learn. And if we learn what we need to learn, this is our moment.

   3. AGAakash Gupta2:44

      So what is a builder PM, and how does a PM become one?

   4. MYMahesh Yadav2:47

      Ah, that's a very good question, right? I was always right, uh, means I had an engineering background. I was not a traditional PM who came from a B school and then went to McKinsey and then became a PM. I had a very gradual move to PM. I was an engineer, and I was always building. And then I became a PM because I was always building what is customer wanted or working backward from customers rather than just building for the sake of building, which is very popular at Microsoft, if you don't know. So, [laughs]

   5. AGAakash Gupta3:17

      [laughs]

   6. MYMahesh Yadav3:17

      uh, for me, a builder PM is-- Like as PMs, we are always building. Our job is to build the right thing. And now, earlier, if you had the tools, you would have built the whole product, but it was very hard to build anything, or you need at least three or six months of rigorous coding, testing, deployment, all that was needed to go build things. But in the new age, even like people who are engineers all alongs are saying that they are not writing code anymore. They are talking to customers, and the Claude Code does coding for them. In that age, the skill that becomes important is like what to build and what does customer want, and that you have. And if you use on the right-hand side the tools to do the right prototyping and then build at least the first version of your pro- product, then you become the builder PM that the world needs. And I think all of us need to grow into that, whether engineers, designers or PMs, because without that, we will not be able to diffuse the benefits of AI into economy. So for me, a builder PM is somebody who is-- who has taken the responsibility to diffuse the benefits of this awesome AI we have today into econ- into the economy so that we can all derive the benefits that is-- that large companies and research labs are putting so much money into to build. So for me, nutshell builder PM is somebody who can take, talk to customers, figure out what needs to be built, and build the first version and get to ten customers without talking to an, any developer at all.

   7. AGAakash Gupta4:59

      Amazing. Can you show us an action? What are the skills and concepts we need to understand in order to get there?

   8. MYMahesh Yadav5:04

      Yeah, I think there is a lot of misconception there that, you know, if you start using Claude Code or if you configure OpenClaw, you become a builder PM. Uh, I think it's the, the hype is right because this is the first time people see that they can manage their calendar, they can delegate work to other party, or they can just say things and it just happens. But AI, my, my-- I've been in AI for the last ten years and bu- built things all along. I think just knowing the layers or understanding how these things work is the first step or of building these things. And for me, I start my journey with, and obviously you talked about a lot of tools. So I s- will start my journey in first understanding these concepts. So I will start in a earlier day, I will start with something like TensorFlow or PyTorch and understand what a model is or train a model and then inference a model. In the new world, in the agentic AI,

3. 6:04 – 12:32

   Building an agent from scratch in n8n (live demo)

   1. MYMahesh Yadav6:04

      I will start with something like n8n and then go and say, "Hey, okay-"What is an agent? How it interacts with model? What is a model? What are the limitation of it? What is memory? What is tools? And maybe I can just show you if it's cool. Maybe I just share my screen and show you because it's not very hard to learn these things in n8n. n8n has done a good job, to be honest. Uh, maybe it's an obsolete tool in building workflows now with Claude Code, but I think it's still an amazing tool to learn. So let me just share quickly with you, like what it takes to build or what it takes... What are the components involved in building these agents. So just if, uh, a revision, revision from last time. If you look at last time, right, we talked about this idea that as we grow as humans, a kid is born, they first need to have the knowledge of the world. So this is how the world works. Great. Okay, I understand that, and I can build my intelligence on that, and I can also update it. And second, I need you to understand what is the current state of the world. So if I want to do anything, I want to know. We teach our kids all the time. When they are born, we will say to them that, "Hey, this is hot, this is cold." All those signals, which is current state of the world. Yeah, we know that this is a thing that gives us power, or this is where we cook, but this is the current state of the world. So this is your signals or memory tells you what is the current state of the world.

   2. AGAakash Gupta7:51

      Okay.

   3. MYMahesh Yadav7:51

      And then if you did a good job, you can ask your kids to get a glass of water for you, and that's the tools where they can use a tools like a gla-glass and then open a tap and then move, hold it, and get it back to you. So that's the tools piece. And then we learn the guardrails, the laws, what is possible in this country. If you are moving on a road, then you need to look left and right. It's your responsibility, not the responsibility of the driver, especially on a high, [chuckles] uh, especially on a busy road. So we tell our guardrails and laws. Right?

   4. AGAakash Gupta8:28

      Yeah.

   5. MYMahesh Yadav8:29

      If we do all this, and if we just replace humans here with a model. So this model is analogous to what you get from OpenAI or Anthropic or Google. The model is just the intelligence layer. It just trained to predict the next word and now have some reasoning. But you need all this harness, harness, or people call it scaffolding, to actually build something that can solve problems or build impact for you. So this harness is called agents, and then we use these frameworks like n8n to build these agents.

   6. AGAakash Gupta9:14

      Mm.

   7. MYMahesh Yadav9:14

      Right? And then if you look at every agent that we have built so far, or what people have built, has one of these four things in it, or the good ones have all these things in it.

   8. AGAakash Gupta9:25

      Mm.

   9. MYMahesh Yadav9:25

      So let me show you, like if you want to build these agents, what is the memory? Why you need this knowledge piece? What will happen if I don't add the knowledge? So let's spend like maybe 10 minutes and understand the basics first before we get into how can you automate your world with this latest agent and how you become a builder PM. So in my story, I would say the first step of becoming a builder PM is just getting into knowing the basics. So if you look at this, maybe... So this is my just n8n, and what I'm doing here is maybe I start from scratch because what's the point of, uh, doing, uh, doing an Aakash show without, with, with, with nets. Let's do it without nets because, uh, that's the Trump-ese acts without nets, so.

   10. AGAakash Gupta10:13

       [laughs]

   11. MYMahesh Yadav10:14

       So on the right-hand side, you just take an AI agent, and you search AI agent, you get an AI agent. So AI agent has a model, which is the intelligence layer, which I was just talking about. So now I am connecting an OpenAI chat model. You can pick any model you want. I will just save money because expensive models, uh, [chuckles] so I'm, I'm gonna be a little cheap here and pick the GP-GPT 4.1 mini.

   12. AGAakash Gupta10:41

       Oh, wow.

   13. MYMahesh Yadav10:42

       So you can just pick that model. So now you got model. So this is the agent. This is like a little baby, doesn't know anything about your world, and now it has intelligence. So okay, if it has intelligence, we should be ready to go. So I can ask it some questions like, hi, what is, what is, what are neural networks? It can answer those questions. So now what happens is this goes to the agent, the agent calls the model, and one beautiful thing about this is that you can look at like what the message was sent, what the input and output were from this screen here. Okay? It gave me an input. It gave me because it's trained on these things. Okay then. But if I ask it very simple question like, hey, what is the... What President Trump said about ending the conflict in Iran?

   14. AGAakash Gupta11:45

       Oh.

   15. MYMahesh Yadav11:45

       What do you think? It will answer that question or not?

   16. AGAakash Gupta11:48

       [laughs] Its training data probably ended in like 2023. Let's see.

   17. MYMahesh Yadav11:53

       Great answer. Let's see what happens. I ask this question, and it says, "Hey, my knowledge cutoff is June 2024," because you're cheap. You're picking a cheap model.

   18. AGAakash Gupta12:04

       [laughs]

   19. MYMahesh Yadav12:04

       So that means that it doesn't have that knowledge, so it can't answer the question. So maybe we need a tool for latest, greatest things.

   20. AGAakash Gupta12:12

       Yeah.

   21. MYMahesh Yadav12:12

       So let's give it a tool, and the tool can be Tavely, which is a searchTool. So this allows it to search the model to do things. So now I go and I say, Taveli-

   22. AGAakash Gupta12:25

       I think it's A-V-I.

   23. MYMahesh Yadav12:27

       Yep.

   24. AGAakash Gupta12:28

       There we go. [laughs]

   25. MYMahesh Yadav12:28

       This is the one. You got it. [chuckles]

4. 12:32 – 14:18

   Ads

   1. AGAakash Gupta12:32

      If you've been enjoying this episode today, Mahesh's classic whiteboard style, his awesome labs and demos, then you will love Mahesh's cohort-based course. It has amongst the highest reviews on Maven, and I challenge you to go check this yourself. His courses are always rated four eight, four nine. That's because of the 13 years in big tech at Microsoft, Google, Amazon, Meta. He's actually built the things, [chuckles] he's not just talking about it. And his course, everybody I know, my mentees who have taken his course have had a positive opinion of it because it is so interactive. You get the first principles that you're sensing from the podcast today. The coolest thing about his new course, Building OpenClaw and with Claude Code, is that you get a Mac Mini. So take advantage, use the discount code that I have below in the description, so you get a discount on his course. Get your Mac Mini. Better yet, get your company to pay for it. He's gonna teach you not just how to become a builder PM, but he's gonna be in the trenches with you. As he said, he will even give you AI PM interview advice. So it's an all-in-one course to becoming an AI builder PM. Check that out on the link just below, and back to today's episode. Today's episode is brought to you by Amplitude. Replays of mobile user engagement are critical to building better products and experiences. But many session replay tools don't capture the full picture. Some tools take screenshots every second, leading to choppy replays and high storage costs from enormous capture sizes. Others use wireframes, but key moments go missing, creating gaps in your understanding. Neither approach gives you a truly mobile experience. Amplitude does things differently. Their mobile replays capture the full experience, every tap, every scroll, and every gesture with no lag and no performance hit. It's the most accurate way to understand mobile behavior. See the full story with

5. 14:18 – 21:35

   Adding tools and memory to the agent

   1. AGAakash Gupta14:18

      Amplitude.

   2. MYMahesh Yadav14:18

      And on query, so now I'm adding a tool. I have my account, it will go do the search. It will take the query, and where can it take the query? I can hard code the query, or I can let the model define the query. So now I'm telling it that, hey, let the intelligence layer, based on what user is asking, define what you want to search on internet. So now we connected a tool, and let's go. So now I ask the same question again, which is, what has President said about ending the conflict in Iran? And my spellings are, you can see, are not that great. But now it goes, and now it's going to the search tool. It's doing some searching. Let's see what searching it is doing. Seems like it went to these website, it found information, and then it went to lot of website, it captured all the information, and now it is able to answer the question, which is from President Donald Trump stated that conflict in Iran could end at any moment based on his decision. He mentioned there is practically nothing left to target and all that. So a lot of excitement. I'm happy about that. So what has President Trump said? Okay. Then if I ask it a question, which is, "Hey, what conflict am I talking about?" You think that will work?

   3. AGAakash Gupta15:31

      Oh, I don't know. [chuckles] It doesn't have memory, right?

   4. MYMahesh Yadav15:35

      Yeah. You, you trained well. [chuckles] So if I ask it, what, what I'm-- what conflict? I don't see any previous mention of conflict in this conversation. Could you please provide more context or specific which conflict? So if you build an agent with a tool or intelligence, it will be a stupid agent because it doesn't have memory or it doesn't remember anything.

   5. AGAakash Gupta15:54

      Mm-hmm.

   6. MYMahesh Yadav15:54

      Who wants to talk to a person who remember-- doesn't remember anything? So let's add a memory. So I will just add a simple memory, which what it does is it, uh, takes a session ID and remembers last five conversations.

   7. AGAakash Gupta16:07

      Nice.

   8. MYMahesh Yadav16:07

      So now you know what, uh, an agent is, which is just, uh, scaffolding, but the real work is happening in intelligence, memory, or tools. So if I do the same query now, and it say, "Hey, what is the President Trump ending the conflict in Iran?" And then it will do the same thing, but this time you see it updates the memory. So it has put all the conversations, all the information in memory, and if I ask my question, which is, "Hey, what is the conflict I'm talking about?"

   9. AGAakash Gupta16:39

      Mm-hmm.

   10. MYMahesh Yadav16:39

       It goes in, it fetches this from the memory. Now it doesn't call the tool because it sees like I'm looking for information. You are referring to the conflict in, in Iran, especially in the military conflict on war situation began around February 2026. So that's what it takes. But maybe, maybe you have a larger context. Maybe you have contracts in your company, and you want to ask questions on those contracts, because conflict in Iran is not gonna make me money.

   11. AGAakash Gupta17:05

       [chuckles]

   12. MYMahesh Yadav17:06

       But if I do good contracts, it will make lot of money. So can I ask a question like, "Hey, what are the clauses or what are the payment terms impact of tariffs and war in Iran on payment, payments impact, payment term impacts of tariff and end of war on our contracts?"

   13. AGAakash Gupta17:35

       Okay.

   14. MYMahesh Yadav17:35

       So I run a company, and we have contracts all over the world. I want to know that. Will that work?

   15. AGAakash Gupta17:42

       I guess right now we haven't given it like a RAG database, right, to our contracts?

   16. MYMahesh Yadav17:47

       Yay. I think I got the b- I got the best student here, right?

   17. AGAakash Gupta17:51

       [chuckles]

   18. MYMahesh Yadav17:51

       Who has all the right prompts. So now it goes in and it says, "Hey, I don't know," or I will just translate. The payment impact on tariffs and war on Iran contracts generally can include several key factor, increased cost, payment delays and all that, but it doesn't talk about my contracts.

   19. AGAakash Gupta18:08

       Yeah.

   20. MYMahesh Yadav18:08

       So I have another lab that we cover in our, uh, course where you can actually create a knowledge base or database of your knowledgeHow your world works. So this is important because the world is working perfectly, how neural network works or world information, but your company information also need to be executed or needs to be built. So what this does is, first one, just you can upload contracts. So I will just execute this workflow. Here I can upload my contracts, so I will just upload a contract from my company, and what you will see is that it will go and create a... Great. Maybe we put this MSA in. So this is a master service agreement.

   21. SPSpeaker19:03

       Mm-hmm.

   22. MYMahesh Yadav19:04

       And what it does is once I go submit, it goes and creates the chunks. Now you can see there is a data loader, you can see insert data, and now you're learning a new concept, how the data is getting into something that machines can understand. Because these agents or these machines don't understand like you and me understand text. So now you are seeing something called an embedding model. The embedding model allows you to convert text into embeddings. You're also seeing something called a data loader. What is a data loader? Oh, it takes the type of data, which is a binary, which is where your input file, converts it into text, and then does simple text splitting. Okay, maybe I can do custom splitting. Oh, so custom splitting you have to specify. But what's happening in simple one? Basically, it's taking 1,000 character with 200 character overlaps. So it divides your f- whole file into 1,000 characters, and then it goes in and puts that into a database, or it calls the embe-embedding model, which goes and creates this awesome database, which is a RAG or retrieval-augmented generation based database for you, which we have the same database where we are entering this information. And now if I go here and I ask the same question, which is I execute this workflow and... Not this one, give me this one. And I go, I select this one, and I say execute workflow. Actually, not use this trigger, just come here. And now I ask the same question which I was asking earlier. I can just say, "Hey, what is the value of contract? Does the payment term change due to war in Iran on tariffs, on tariffs based on our MSA contracts?" It goes in, it queries this tool, and this is the-- This is where you have put all your information. So now it queries the tool, it extract all the taxes information from your document that you provided, so your knowledge, and it says the document does not specify any provision. So I think we are good whether it happens or not. And now this information comes from your knowledge.

6. 21:35 – 29:47

   Multi-agent systems and evaluations

   1. MYMahesh Yadav21:35

      So similar to this, we also discuss the next stage of this learning is multi-agent systems. So single-agent systems are great, but if you want to do real checks or real things, this is a multi-agent system that we build. We use the same constructs that we just discussed. And in this one, you see that you can send an email. So right now I can just send an email and ask this information, the same information via an email. So I have pasted that, or I have published that flow, and I can just ask like I ask my lawyers. Now I can send this request and I say, "Hey, can you get me the risks in this contract before signing?" So if you send me a contract, which I d-- I, I believe one day you should send me a contract. But, [laughs] uh, but right now, l-let's say you send me a contract which is an NDA, I want to-- Before signing, I will just send this email. And if I send this email, what happens is this email hits this provider, which is my Gmail. And if you look at it, I will get this review contract key terms for this contract. Okay, if I get that, then what happens is that if we, I go to my workflow, I will show you in executions that in few seconds you will see that it will get a new running. So it automatically triggers this. I need not to do anything. It's a published workflow.

   2. SPSpeaker23:00

      Wow.

   3. MYMahesh Yadav23:00

      And now it's running. And when it is done, I will get a response which says that, "Hey, you got these risks. Contract analysis report with all the risks in it."

   4. SPSpeaker23:12

      Nice.

   5. MYMahesh Yadav23:12

      So now you start first understanding all these things, which is, hey, what does these agents do and how they work with your things behind the scenes. So these are the connectors, these are your agents. It has multi-agent system with playbooks or your database connected, and then it can do end-to-end work like humans do. And the last thing I would love to show in n8n world, which I think all of the builders PM should go build is, this is great. All this is awesome. This is sending me risk, but what about evals?

   6. SPSpeaker23:46

      Right.

   7. MYMahesh Yadav23:46

      How are we gonna evaluate these? Because these agents are not like us humans, which does a lot of self-evaluations, and you can't-- If they do a bad job, you are gonna get fired. They are not gonna lose their job. Even if they lose their job, [laughs] you are g-- It's not good for you. So what is this is then, then we create this idea of ground truths. So what I have done here is I have taken this contract, and what I do is I say, "Hey, here are the terms that you need to look at. Here is the correct value, and whether there is a risk or not based on our playbook is also returned from a real lawyer."And then you can create a workflow like this where you can run this normally in the daytime. What you do is during the day, you can have your people submitting these files. You can find all the risk, and the results are getting stored here. And in evening, what happens is you evaluate these using the judge or risk categories and modifications, and you get a fancy report. So let me just execute this. So not the eval trigger, but let's just first create this data. So if I go and execute this workflow, I can just upload a file. And on that file, what it's gonna do is it's gonna extract these terms. So now it's gonna find the risk in this contract and submit our results according to the same key terms here. So it runs in automation, and then it updates a file like a human will go find the risk. But what it does is it will just get the results first.

   8. AGAakash Gupta25:33

      Okay.

   9. MYMahesh Yadav25:33

      So now you will see once it is done, these values will be populated here. So now it's just looking for governing law, justification, agreement terms. And once it is done, which is still executing, once it is done, you will see this file getting updated, and you will get the results like a human would have done. First, it's extracting these values from the contract, then checking whether risk or not. If risk, it will justify why this is ri-risk and suggest a modification which allows you to take minimum risk if you sign this contract. This is what a lawyer does for you, by the way.

   10. AGAakash Gupta26:08

       [chuckles]

   11. MYMahesh Yadav26:09

       They will look at your contract, compare it with some values, find whether risk or not, and then give you a justification why this is a risk and modification. They never justify the risk, by the way.

   12. AGAakash Gupta26:19

       [laughs]

   13. MYMahesh Yadav26:19

       So now you see automatically that you can see the risk. And once you see these risk, then you can see the second part of this, which is you can run a quick eval on this by just going and changing it from form submission to eval. And now when I run it, what it does is it will go and run an automatic eval and suggest comparing to my ground truth here, which is my real values, and suggest that how much of these risk is correct, how much of justification is what a human or these modification is what a human will accept as is or they want to change. So you can run these evals also, and n8n has this awesome tool. So now you run this flow, and what it does is it will take it one row by one row, run your evaluations, and find whether the risk is good and what is the quality of modification suggested by the AI.

   14. AGAakash Gupta27:20

       Mm.

   15. MYMahesh Yadav27:20

       It will continue doing it. But if you can go to Evaluation tab, I can show you some of the previous evaluations. So now you see that it goes through, runs row by row, and then eventually it's telling you that, hey, you have a risk. Quality is good. You're able to detect 80% of risk correctly, but your modification quality, the suggestions AI is making, is only 30% as good as a human would have done. So you have work to do. So now you understand as a PM or as anybody who wants to survive this build wave, that it's not very hard to go s- with something very small, bring your context, make it multi-agent because the world is multi-agent.

   16. AGAakash Gupta28:06

       Mm-hmm.

   17. MYMahesh Yadav28:06

       And then run evaluations to make sure that before you deploy it, it's really good quality, so that when it does a job or when it responds to these emails, it's, it does a good job. So I got my analysis, which I sent earlier. So now it talks about all the findings. I need to set it up so that you can see it in a more-

   18. AGAakash Gupta28:28

       The formatting could be improved

   19. MYMahesh Yadav28:29

       ... formatting correctly.

   20. AGAakash Gupta28:30

       But it's pretty cool that-

   21. MYMahesh Yadav28:31

       But I just build it for you to show it quickly.

   22. AGAakash Gupta28:33

       Yeah.

   23. MYMahesh Yadav28:33

       But you see that the whole flow worked, and it does give you risk that this agreement shall be governed or constructed in the law of State of Delaware without regard of conflict of law principle. Delaware is neu- neutral jurisdiction under criteria of NDA. So it's talking about these things to you and giving you all the details.

   24. AGAakash Gupta28:51

       Yeah.

   25. MYMahesh Yadav28:52

       Okay. So this is what it takes to get first your footing on ground to get started with your building journey. So that's-- People talk about this when people talk about AI a lot. They talk about, hey, AI is, uh, you want to build a PM, just start with OpenClaw. My suggestion would be first understand what is the harness looks like, what is the harness made up. Ideally, understand how this model is built, what are neural networks, what are transformers. Uh, and we talk about that in a way that anybody can understand. But then understand the scaffolding at least, because this is where things will break even if you're using Claude Code or the Claude Code constructs like, you know, context, model, compression, knowledge, memory. First play with them and see what they are, and that's your first step in getting into building with AI.

7. 29:47 – 31:16

   When n8n falls short

   1. AGAakash Gupta29:47

      When does n8n fall short? When do you move beyond n8n?

   2. MYMahesh Yadav29:51

      Yeah. So n8n is very, like, I think it's more like a tool which allows you to get to your first 10 customers. I think it's a very powerful tool, especially with webhook. When we did the last session, I showed you how can you create your back end in n8n without any code and connect it to a Lovable or v0 front end, and then build the whole solution where you can click a button and something happens in n8n, and you can debug everything without writing a single line of code. I think it's very powerful there. But then if you want to iterate, put things in production, if you want three people to contribute to your code, if you want to have a test set or want to put a container around it and put it into productionn8n doesn't support that. And if things fall short, and the worst part of this is that there is no way for people to see the code and get to the code mode.

   3. AGAakash Gupta30:40

      Yeah.

   4. MYMahesh Yadav30:40

      Like we do this in, uh, our cohorts, and after people want to get to the next stage, which is, "Hey, I've done this, but now I want to put this in code and share it with my team so that they can see if this is good quality, bad quality, to take it to hundreds of user or thousands of users in the most efficient or latency optimized way," then n8n has no answer to those questions. So I think it just stops you beyond 10 customers, it's not the right tool I would recommend, and that's where I know what you want to get started with.

8. 31:16 – 33:39

   Ads

   1. MYMahesh Yadav31:16

      [chuckles]

   2. AGAakash Gupta31:16

      Today's episode is brought to you by Jira Product Discovery. If you're like most product managers, you're probably in Jira tracking tickets and managing the backlog. But what about everything that happens before delivery? Jira Product Discovery helps you move your discovery, prioritization, and even road mapping work out of spreadsheets and into a purpose-built tool designed for product teams. Capture insights, prioritize what matters, and create roadmaps you can easily tailor for any audience. And because it's built to work with Jira, everything stays connected from idea to delivery. Used by product teams at Canva, Deliveroo, and even The Economist, check out why and try it for free today at atlassian.com/product-discovery. That's A-T-L-A-S-S-I-A-N.com/product-discovery. Jira Product Discovery, build the right thing. Today's episode is brought to you by NayaOne. In tech buying, speed is survival. How fast you can get a product in front of customers decides if you will win. If it takes you nine months to buy one piece of tech, you're dead in the water. Right now, financial services are under pressure to get AI live. But in a regulated industry, the roadblocks are real. NayaOne changes that. Their air-gapped, cloud-agnostic sandbox lets you find, test, and validate new AI tools much faster, from months to weeks, from stuck to shipped. If you're ready to accelerate AI adoption, check out NayaOne at nayaone.com/aakash. That's N-A-Y-A-O-N-E.com/A-A-K-A-S-H. I hope you're enjoying today's episode. Are you interested in becoming an AI product manager, making hundreds of thousands of dollars more, joining OpenAI and Anthropic? Then you might wanna do a course that I've taken myself, the AI PM certificate ran by OpenAI product leader Miqdad Jaffer. If you use my code and my link, you get a special discount on this course. It is a course that I highly recommend. We have done a lot of collaborations together on things like AI product strategy, so check out our newsletter articles if you want to see the quality of the type of thinking you'll get. One of my frequent collaborators, Pavel Hern, is the Build Labs leader, so you're gonna live build an AI product with Pavel's feedback if you take this AI PM certificate. So be sure to check that out. Be sure to use my code and my link in order to get

9. 33:39 – 35:08

   When and how to use Claude Code

   1. AGAakash Gupta33:39

      a special discount. And now back into today's episode. Yes, it's the hottest tool on the market, Claude Code. Please, Mahesh, show us when should we be using Claude Code? How should we be using it?

   2. MYMahesh Yadav33:49

      Yeah, I think, I think you should spend like good two weeks in n8n, and beyond that, you should move to Claude Code because I think what has happened is with Claude Code, um, and especially like in last, I would say three to six months, Claude Code is here for more than a year now. But in last six months, there's just so much possibilities with Claude Code and Cowork to build things and put things in production for you as well as your team. It's the same tool chain which a person who has no coding experience can use, like building with skills, creating their sub-agents, hooks, and then schedule jobs to the peop- And then on the right-hand side is people who know how to code, who has always been coding for rest of their lives. They also can build on top of what you provided.

   3. AGAakash Gupta34:38

      Yeah.

   4. MYMahesh Yadav34:38

      So this idea of having somebody to allocate or do work with, and then this idea of code is combined in Claude Code. So I think it started with something that people wanted to do code with, but then this one thing they realized is, or we all realize is that if you can build something that codes well, it can do any task well. And that is what Claude Code is, and that's what I think why it's the hottest tool in the town.

   5. AGAakash Gupta35:07

      And

10. 35:08 – 47:17

    What changed in December 2025

    1. AGAakash Gupta35:08

       you talked at the beginning about needing to harness this moment, and Andrej Karpathy talked about something changed in December 2025. What exactly changed?

    2. MYMahesh Yadav35:20

       Yeah. So I think this is like for me also, right? Um, means I'm contemplating this and I think still not have wrapped my head around it. What has changed is if you look at like last three years where I, I was at Google and we were building AI, but I thought we are not building AI fast enough. So I left Google, I started on my own. I'm building this company where we thought we can go and automate back office and build AI or the benefits AI faster than what I could do at Google with my own agency. Obviously, Google is doing great, uh, with their agency. And if you look at all the companies in last three years, what they did with AI is they took these models that we had, and if you take the examples of any company, and I can put them what they do in this map. If you look at Gamma, Gamma did one thing. Gamma said, "Okay, I am gonna go and connect these models with tools and make it very easy for you to create slides, and then I will provide you connectors. Connectors to PDFs, connectors to everything, so that you can go and publish this in PPTsOr Google Slides or just PDFs. They just do one job. And this was, I think, now at billion-dollar valuation. The second kind of company. So first kind of companies that you saw was these kind of companies which go and make the model and tool working and put lot of connectors in place. So Gamma is there. The second kind companies said, "Hey, we're gonna take this model, harness it to domain-specific knowledge." So the Harveys of the world, the Lagoras of the world went and said, "Hey, we're gonna take this model and do the context engineering piece here, and say, 'Hey, we will context to the lawyers and solve their problems.'" And they become $1 to $10 billion companies in two years.

    3. AGAakash Gupta37:18

       Mm-hmm.

    4. MYMahesh Yadav37:19

       And some just went in and provided signals and memory well. And then there were third kind of companies which said, "Hey, can we provide you frameworks to build this?" Which is what you saw with Salesforce, Agentforce, Amazon Q. They said, "We'll just help you build with all these things faster."

    5. AGAakash Gupta37:39

       Yeah.

    6. MYMahesh Yadav37:39

       This was happening for last two years. You will see a lot of companies just come out, and every company was planning to do something like this. Then what happens is there is something, a breakthrough happens inside Anthropic where they are building just a tool for coding. And they thought for doing coding, let's just do one thing, which is build the agent loop. They called it Agent Loop. And the idea is it will build the context, it will take the actions, which is all the connectors and tools, and it will do the evaluations. And based on that, it can come back and keep doing that again and again.

    7. AGAakash Gupta38:28

       Mm.

    8. MYMahesh Yadav38:28

       So now what happens is, if you are a context company, Harvey, Lagora. If you're an action company, Gamma. If you're an eval company or you did evals to make sure that your actions and all this is good, all this is coming part of this product called Claude Code.

    9. AGAakash Gupta38:50

       Yep.

    10. MYMahesh Yadav38:52

        And now people realize that it's not only coding specific, you can actually do work with it. So then they release these plugins for legal, marketing, and sales. And what happens is they are able to do a better job at context management, taking actions and evaluations. Why? Because for context, there is another unblock in this world, which is what we thought-- I thought of that like the best thing that will happen with these models. But I thought maybe it is the browser where things will happen. But where things happened is this idea of computer control. And we all became normal because we thought these are coding tools, so we gave them access to two things. One, your file system, and second, your bash commands. This is how the whole world works. This is how if you're an engineer, you can control your computer. And if you can control your computer and your browser, and you can have access to your file system, you can do all the context management. And with Bash you can do all the actions. And third, it has the browser control as well. So now you have all the action powers, and on top of it they have evaluations, which is they are saying, "Hey, I can do the lint, lint checks, do rule-based checks. I can go and do UI element checks in HTML, and I can do what I was showing you, which is these LLMs as a judge. And all this I am going to do. So you don't need a third-party provider. You don't need Harvey. You don't need somebody to come in and do it for you. If you take co-work, and if you use my tested skills, you can do it yourself. So this is first time that whole intelligence layer that we were talking about, which was Claude, actually became the whole harness provider as well.

    11. AGAakash Gupta41:02

        Mm.

    12. MYMahesh Yadav41:02

        So this is Anthropic entering into everybody's lunch and saying, "Hey, we don't... We need your, the space of this also."

    13. AGAakash Gupta41:11

        Yeah.

    14. MYMahesh Yadav41:11

        And that two to three billion what you are seeing in Claude Code is basically coming right now from these valuations, which these people thought that they can go solve for each customers. But now they can't solve because everything is mostly three things. So once you have this, then on top of it, you can connect a UI layer or these three things to how they are able to teach the world. And obviously you have done a great job with all your podcast in teaching the world these skills on top of it, which is that anything that you want to do can be a skills. Anything and skills are powered by these action-taking sub-agents, which can be triggered by something called hooks. And now you can schedule jobs. With these people learning these on top of these computer control, which is powered by this context loop. And by the way, there is a bottom layer to this, which is these models like Opus 4.6 have grown and able to do long horizon jobs. What is that? They are trained in a way that they can run for 3-6 hours without breaking. This is, was not there. If you looked at, uh, the Matter benchmarkThe last six months ago, the longest horizon job they can do is three minutes.

    15. AGAakash Gupta42:43

        Mm-hmm.

    16. MYMahesh Yadav42:44

        And this has gone exponentially in last six months. So you put a long horizon job, you give me access to your bash file file system, and then the users can create these skills naturally in English language. You have unlocked what the human potential was locked inside these coding or some software, or some software provider will go and do it for you. Now it's just a skill. And if it is a good skill, and if you know your skill, and if you have your craft, you can put it in a skill which can be paralyzed with sub-agents and triggered with events like hooks, and then whole this operating system is available to everybody. And I think that's what happened with Claude Code. Claude Code people realized that they need not to do the hard piece of which I was showing you with RAG, what the chunk size needs to be, and this RAG we do it in our labs with n8n, where I show people that it's so hard to do the right retrieval. And check this right retrieval with evals. So you have to do agentic RAG, then you have to do graph RAG. All that now is responsibility of Claude Code. It goes, it gets the right context. If the context becomes too large, it compacts the context. All that is happening for you. You need not to code for it. You just pay for it, and you pay by, by like some 20 bucks or 200 bucks, which Harvey, by the way, was charging you $10,000 to do. So that's what every lawyer got now. That's what every law firm has now. And they are looking and saying, "Maybe we don't need tools." And that's how the benefits of AI are getting diffused into economy with Claude Code, then Cowork, and maybe we can talk about OpenClaw next. But that's what changed for me six months ago when I actually took hold of Claude Code with the latest, greatest model. I tried Claude Code, by the way, and I was not very impressed with it for doing things which are beyond coding. And I was like, "Yeah, it's a good tool. Yeah, but Cursor does the same thing. I have GitHub Copilot, which I got for free because I'm Microsoft, you know." So, [chuckles] uh, but then three months ago, I went to Claude Code once Opus 4.6 came out, and now it's a superpower. I don't know its limitations. It does anything that I want it to do. And that's why when I talk about it, people say that I'm scaring them to take my courses. My life is good without my courses, by the way. [chuckles] I'm just telling you that anything... Like when I looked at ChatGPT, I was very, uh, excited about it. When I looked at Lovable, I was excited. That was the second moment for me that, yes, front-end is a solved problem. And then I looked at Claude Code, and it seems like everything is a solved problem. It can replace anybody, and this is an open challenge I have given to anybody, that if you can do a job, just tell me the job and this agent will do it better than you 365 days, 24 hours. And that's what we are playing with now, right? So that's the world you live in, and this is moving each model. This long horizon jobs are shifting to more and more jobs. These context action evals are getting better inside, so you need not to worry about it. And more and more people are sharing their skills, their agents, and their scaffolding. And this is the new scaffolding layer, which is a very thin layer in English. Rather than figuring out all RAG, all of this tool calling, all of that, putting the guardrails. Obviously, guardrail is still your responsibility, but, [chuckles] but there is like, at least you can rely on these companies to not screw up because that's the only thing they need to go solve next. So that's my take on the question, right? Which is, hey, what has changed for all of us? What has changed for all of us is that if you know your skills, you can build it in Claude Code and delegate that work to agents.

    17. AGAakash Gupta46:43

        Can you show us this in action? What does that look like?

    18. MYMahesh Yadav46:46

        Oh, you, you like action so much, so let me show you that also. And again, right, uh, [clears throat] so there is one job I do, right? Because I started my own company. I have like at this point 20 people working with us, and once you do that, you figure out that most of your time goes into reviews. So what I built for myself here is that what I was able to do with just, uh, I just thought maybe I just do this. Let me share. As, as you can see, this is my screen.

11. 47:17 – 1:02:28

    PRD review automation in Claude Code (live demo)

    1. MYMahesh Yadav47:17

       Uh, this is my, uh, this is my Cowork. I have bunch of stuff going on. What people send me all the time is that they will send me a PRD for review. So now I have given the review job to my agent. How it works, if you send me a PRD, I will just go and say, "Hey," or I can just start a new task, and I will say, "Hey," and I will select my folder. So this is Cowork. Same like Claude Code. You can provide it a context. So I will select my review con- context. I will change my model. Opus 4.6 is too expensive, so let's do Sonnet.

    2. AGAakash Gupta47:52

       [laughs]

    3. MYMahesh Yadav47:53

       So, [chuckles] so I will go to Sonnet, uh, because I'm paying them a lot, so they are like, "Let's eat his token with Opus and give him the best results." No, Sonnet is good enough. Uh, so I go to the review folder, and now I can upload a file and say, "Hey, can you just put comments on it?" So if the good model or before this, if you were doing something like this, what will happen is you have to go and create... So now you can get... So this is a product two-pager. We are just building a new product. This is live. And what happens here is that I can go and upload this file and then say, "Hey, can you use our checklist and review this file? Put comments as I would have done."So now, if you look at this, this is some sophisticated tool that you need because now it need my checklist, which I already provided in these reviews. But first it needs to build the context. It need to understand. But now I-- you need now to build the query engine, the query to knowledge mapping. Now it automatically finds out the skill which I have built. It's my PRD review skill, and then it goes to my reviews instructions, and then it's reading my checklist. And based on my checklist, which I have provided to it, it's gonna review this file and then upload or put comments in it like I would have done. As I showed you earlier, I could have put this whole agent inside Slack, and somebody could have just asked my review, and this would have given a review in five minutes and saved me a bunch of time on basic things which people forget, of course, because they are busy with their lives. So that's the first-

    4. AGAakash Gupta49:37

       Can we see inside the, uh, PRD review checklist MD and see what that's all about and how-

    5. MYMahesh Yadav49:42

       Definitely. So let's go to my VS Code. So second thing I do is, so the same folder, VS Code, and now you can see this is my checklist. So this is my checklist. I've created this with lot of, uh, blood, sweat, which is mostly prompting-

    6. AGAakash Gupta49:58

       [laughs]

    7. MYMahesh Yadav49:58

       ... uh, to Claude Code. [laughs] Uh, but I had a checklist, uh, before, uh, because I was very fanatic on how we should write our two-pagers, and I'm a big fan of Amazon PRF, PR facts, so I like that format because with one page you can get a very gist of what's going on. So now this is our checklist-

    8. AGAakash Gupta50:16

       Sorry to interrupt you. Just based on where your face is now, can we move the camera down a little bit again?

    9. MYMahesh Yadav50:21

       Oh.

    10. AGAakash Gupta50:23

        Thank you so much. [laughs]

    11. MYMahesh Yadav50:25

        Yeah, there is this, uh, this, uh, circus we need to do because this mic thing today, huh?

    12. AGAakash Gupta50:30

        Yes. [laughs] Please continue.

    13. MYMahesh Yadav50:32

        Thank you for pointing me. Thank you. I have no clue because I get lost in these.

    14. AGAakash Gupta50:37

        No, no-

    15. MYMahesh Yadav50:37

        Thank you for pointing

    16. AGAakash Gupta50:37

        ... you're killing it. So we're just-- you're talking about how you built this. Blood, sweat-

    17. MYMahesh Yadav50:41

        Yes

    18. AGAakash Gupta50:41

        ... and tears, prompting.

    19. MYMahesh Yadav50:42

        Great. So, uh, so this is like I'm a big fan of Amazon PR facts. Uh, I have looked at all the PRD formats and still stuck with that, like we had one at Meta and we had one at Google. But still, I love this whole two-pager thing of a PR fact. And this is a checklist you are looking at with all the things that are-- like it checks does the problem has, uh, urgency is clear? Is the solution differentiated from ChatGPT co-pilots or commodity AI wrappers? So I have put my AI specific things here also because this is specific for building and evaluating AI tools. So I build it with lot of knowledge I have, but obviously prompting a lot as well. But I stand behind it. That's the deal. If you do what I have said here, you can be rejected. So as you have seen. So now what it is doing is, "Okay, good, I have read the checklist, the doc. Let me unpack the docs." Targetted. "Now let me inspect the document to find the right paragraphs to anchor each comments to." So now it's going, and it's also gonna use another skill that it has, which is updating Word documents. So it will go and comment inside the document. It will unpack the document. It will find which sections or which points it is having problem. So now it's saying, "All comment, all seven comments added. Now I need to insert the XML marker into document XMLs to anchor each comment to its paragraphs." And once that is done, you will see a file which should look like this. So this is how it will go and say, "Okay, Mahesh has put this," which is market sizing is too broad. Moat is missing. Add section explaining defensible advantage. What are the steps Datadog or Big4 consulting firms from building this? AI failure modes are unaddressed. What happens when attribution is wrong? How do you handle misclassification of AI versus human work? So not only like some wishy-washy, the real good comments which I will put in. So that's your first step. Maybe you got it right, and maybe you didn't. Maybe... So if you go and build an agent, then this should be it. If you build a chat chatbot, then this should be it. But then you will go, and I look at this and I say, "Yeah, they did a good job," but I don't like this whole section-wise. So then I will put another comment and I will say, "Hey, you know what? This thing is... This is more market specific. How can you make it..." So now I am adding my comments and I'm saying, "Looks for PR fact for write in that format. This means that a heading, problem, and solution section without question answering here. Question and answer format." So seems like format was pick-- was not taken, and that was not in R, so I added a new comment here.

    20. AGAakash Gupta53:49

        Okay.

    21. MYMahesh Yadav53:49

        So the beautiful part earlier was that, uh, yes, it did the job, but obviously it might miss few things, and I-- today I have a very different angle. One day I go and comment everything. One day I don't comment anything. So today I wanna push AI. The idea is that if AI does our work, what are we gonna do? We're gonna do and push, push it even further. So now I'm doing my job, which is I'm saying, "Hey, you go this comment," and then I look at this and I say, "Why this problem is hard? General observability tool don't understand. Workflow multi-step, multi-tool. Adoption is invisible. This is too broad." So I can say, "Hey, this is too broad. This is too broad. Make it pointing. Make it point to human story as what happens to CXOs when they can't see impact."Of their AI investments. Great. So now I have put two comments.

    22. AGAakash Gupta54:59

        Okay.

    23. MYMahesh Yadav54:59

        So, so this was a output file that you got, and now you got this whole thing. Then we-- what I build on this is that I said, "Great, now AI does the review work for me because I have these skills. I have put my instructions in the Claude Code, and it does the work." But if you have somebody who is working for you or if you work in real environments, you want it to learn from it every day. So for that, I build another skill, another sub-agent, which is what it does is it goes in and I have scheduled them to go and check for my review comments.

    24. AGAakash Gupta55:40

        Mm.

    25. MYMahesh Yadav55:40

        So what this one does is it goes and runs every two hours or every 30 minutes and checks what are the comments I am adding. It automatically is scheduled. It looks in the same folder where in the reviews I'm putting all my things, and it goes, and then what it does is it creates this file called learner.md, and it learns from my patterns.

    26. AGAakash Gupta56:05

        Oh.

    27. MYMahesh Yadav56:05

        So now if you look, it's updating this file, which is a learner.md, which Claude Code did not provide it. This is what as a human I added. So it goes [clears throat] and put all my files. First, every day, whenever this job is done, because I'm a PM, I do a good job of organizing things because I need to evaluate, because I understand these concepts. So every time a job is done, it creates a folder here which says who did the job, what was the job about, when it happened.

    28. AGAakash Gupta56:40

        Mm-hmm.

    29. MYMahesh Yadav56:40

        And inside that it creates this, that this is the checklist I used. This was the input document. This is the output document, and this is what the user modified document looks like. So it create all the artifacts, so if you want to go back, check, you have all the data that you need to debug or see what happened in this story. And then each 30 minutes, Claude goes and compares these two files and creates this learner.md file, which says, "Hey, I looked at this job folder, and user added these comments. And with that, I have these new learnings."

    30. AGAakash Gupta57:19

        Yep.
12. 1:02:28 – 1:05:15

    Competitive analysis, mocks, and prototypes

    1. MYMahesh Yadav1:02:28

       So this is our first lab that you can use, which says, "Hey, creating agents in Claude Code." We talk about all the basic things that you need to do, and this one just does competitive analysis. So this is building your own competitive analyzer, so it will go research the web and gives you insight. So this is a lab which we give our creating subagents. Here you create subagents, which basically what they are doing is y- we have a lot of subagents now inside Claude Code, and they will go and look at different competist- competitors you have and what's the insider news, what's the outsider news, and generate a report for you. Oh, that's not enough. Then this one allows you to create mocks. So okay, you can create-- Once you do your user research, market research, you can create PRDs in Claude Code, but you can create mocks and visualization, which earlier you were waiting for your design teams to do. Oh, but that's not fun maybe. Maybe you can clone your mocks from the source and then modify the mocks to build an end-to-end prototype of your product. So now with here we build a whole product from the mock. So we take these screens, and we modify them and build an end-to-end working prototype that you can publish and customers can f- feel, touch, and give you feedback. Not in mocks, as a real product. And then you can analyze data. So you can see who is using, how they are using, where things are failing. So then we give you this lab which allows you to not only just give you data, but also analyze this data and create fancy dashboards, which shows you how many contracts have been analyzed, what is the processing time, what is the average rating, compliance rate, bug reports, all. So your app gathers the data, and now you are creating these dashboards. So everything which used to take you almost two to three months first to write the PRD to get to mocks, from mocks to a real working prototype, from there to getting customers and seeing the signals, all that is getting squeezed with this Claude Code. And all this you can do with Claude Code, and we give you labs for that, and the labs are public. So for all our cast audience, we will even do one-hour free sessions, whatever it takes. Because the mission is to make sure that everybody can build in this new age because there is lot of spend on these. This technology is very expensive, and if we can't build, if we can't diffuse the benefits of this technology to economy, we all are going to fail. So with that, at least I'm will do my part, and Akash is doing his part by allowing all of us this platform to spread whatever we have learned or whatever we have seen out there.

13. 1:05:15 – 1:22:06

    OpenClaw deep dive and delegation

    1. AGAakash Gupta1:05:16

       So Claude Code, it's obviously great. It's a session-based power tool. What are the limitations of Claude Code, and when should PMs be thinking about using OpenClaw?

    2. MYMahesh Yadav1:05:27

       Oh, another one. So [chuckles] this is a, this is an amazing session. We start with like chatbots, then we go to n8ns, then we go to Claude Code, and now the beau- most beautiful thing called OpenClaw. So as we talked about this agentic loop, right? What happened, this is the another exciting thing that happened in December, and generally what happens is November, December, people get time to actually do things and like sit down and not just run through these errands of life. So what happened with that is that Peter, who is a developer from Australia, by the way, and all these things needs to come from developers and not from big companies. That's the one pattern you are seeing, that the big breakthrough came from ChatGPT, which is like an OpenAI, one team, few people launch something in, and then they could see amazing thing happen. Similarly, Lovable, a team outside US just build something and became overnight sensation. And then you saw OpenClaw. So what is OpenClaw? So OpenClaw said, "Hey, now this agentic loop is open. Anybody can build on it." So initially, what they said is OpenClaude, because this agentic loop is coming in agent, Agent SDK. So I can write the same tool like CoWork or Claude Code. Anybody can write that. And the beautiful part is that it can connect to any model.So when Claude built it or Anthropic built it, the agentic SDK was open that it doesn't only work with Claude models, it can work with any models. So what he did is he said, "This loop is great, but people are having problems connecting to different channels." So first layer, what he did is he connected to these channels, which is WhatsApp, Signal and Slack.

    3. AGAakash Gupta1:07:29

       Telegram, everything. Yeah.

    4. MYMahesh Yadav1:07:31

       And at this point, like hundreds of these. And then he created this gateway which automatically opens a port and makes sure that these are good. So he did the hard work of taking the formats and making sure that all can be processed. And then what I was passing through my email when I get this example, you were sending this email, but I was passing it to the model. He takes all these inputs or puts this agent SDK and then says, "Hey, this is the intelligence layer. And now anybody sending me these messages here, I will process it here and then come back and you can connect your tools, you can connect your models same way. And all this is coming as one thing called OpenClaude.

    5. AGAakash Gupta1:08:24

       Mm-hmm.

    6. MYMahesh Yadav1:08:24

       And by the way, I am going to open source all of this and give everybody free access to it, so it's not tied to any company. It's out there. Anybody can audit it. It's not something... So this is the first version of OpenClaude. So he said, "I'm gonna open source Claude," which by the way, like today, yesterday, the c-code got leaked. But this is the code, code getting leaked in a very nice way. And now if you look at it, because it's developed by a developer and because it has two things that Claude Code didn't have at that time. One, it allowed everybody to just go and delegate work to it. So as you were talking about like the session, the idea of Claude Code was that it was built for developers, and developer does iterations. But here there was not iterations. Here what they did is they did delegate the work. So you can delegate the work. I will go do, do, do the work, and when the work is done, I will come back to you. And you need not to bother about it because I'm directly coming to you through your channels, and you need not to be in terminal with me and go back and forth. So one idea is the delegation idea. Second idea is this idea of a shell or this sandbox. So instead of you giving me permissions on every file, every folder, why can't you just install me on a machine? So install me on a Mac Mini. That's why Mac Mini is out of, uh, uh, out of orders or three weeks delay now.

    7. AGAakash Gupta1:10:00

       Mm.

    8. MYMahesh Yadav1:10:00

       Because if I can install this, this is the new operating system.

    9. AGAakash Gupta1:10:06

       Mm.

    10. MYMahesh Yadav1:10:06

        These b- these tools became the UI or the mouse clickable things that you can assign things, and now this whole compute works for you. And the third unlock was you can connect any model and even open source models, and you are no more tied to the limits that Claude Code basically everybody's hitting every day.

    11. AGAakash Gupta1:10:26

        [chuckles]

    12. MYMahesh Yadav1:10:27

        So now you can tie it to any open source model. So that is OpenClaw for you. So OpenClaw, one-- So this is the template that you will see everywhere now. So this template is gonna be the next operating system if my predictions have been right, and I'm predicting all these trends all along, by the way. I've said agents will be great in 2023. Then I said, "Hey, you know what? Uh, we are gonna go to multi-agent and orchestration in 2025." And this year I've been saying that this pattern that you have seen here will be copied all over again and again and again, and everybody will build on top of these. So now this is the new agentic layer, or this is the new agent definition. And now you can give the work, and the work is getting done by the agent, and you get the w- output back. So you can measure input and output rather than measuring tools, evaluations and all. So that's OpenClaw for you, and you can just see it in action as well because I know you will just say, "Hey, can you show me in action?" So [chuckles] I have-

    13. AGAakash Gupta1:11:38

        You know the transition. [chuckles]

    14. MYMahesh Yadav1:11:40

        Now I know, right? Uh, I've done it enough times with you. So what I have done is I have, by the way, I have my Mac Mini here also. But for today, what I have done is I have done simple installation because it's hard to just show you my Mac Mini, and there is just a lot of things going on that which I can't share a lot about. But what-- There is another way to put Mac Mini, uh, or OpenClaw beyond Mac Mini is this UTM. So on your Mac machine, you can create this new VM using this tool. And I have my whole setup. By the way, we have labs for these. So you can see that this is my session. You can see my overview. You can see which channels I have connected. I have connected only WhatsApp as a channel, and now you can see my usage of it, which is pretty okay because this is not what I use daily. The daily is in the Mac Mini.

    15. AGAakash Gupta1:12:32

        Mm.

    16. MYMahesh Yadav1:12:33

        And then you can set up cron jobs, which is like scheduled jobs. You can define your agent skill nodes here also. So how, how can you delegate work? Okay, I can just go in here, I can go to my WhatsApp, and I can just start chatting with it. I can say, "Hey, do a deep research on what are-- what is agentic loop and long-horizon jobsCapability and how they can impact software market. Give me full report. By the way, I can say all this through my command line as well. So it goes in now. What it is doing is it's gonna process this request and give me results. And this is me sending a message on WhatsApp to a friend or to an agent on the other side of the world, and you see that it says, "Hey, here is the agentic loop. Introduction, landscape, emergence of autonomous software agents, increased demand, companies leveraging." And this is just vanilla. I've not even put my skills and everything that I have put on others. But now you can just put a channel, and in 30 minutes we give you labs as well. So for this also, we have set up labs where you can go and create your whole... Just give me one second. I think those are... Okay, this is coming down. OpenClaw. OpenClaw. So here also we have labs for you where you can go and set it up with WhatsApp, but you can also automate all of your world using this lab where you can connect your Gmail, which I have connected to my Mac Mini, which I couldn't show because just there is so much personal stuff. But you can connect and make it your personal assistant. You can ma- let it manage your calendar s- by step by step following this guide. Second thing what we have done on this one is that you can go and create a whole discovery process or whole autonomous developer for you, which goes and scans your GitHub and then fixes the bugs that are P2 or P3 for you, and then send a PR request to your development team. So now you're becoming-- If they are becoming a threat to you, you are becoming a threat to them. So you can build the whole lab where it scans your GitHub. First, the agent goes and does tests for y- your UI or a new feature, then file the bugs, and then instead of assigning these bugs to developers, it goes and try to fix the bugs as well, and then send a pull request for final approval to engineering because they still control the code. But you can build all that in OpenClaw. I'm also building a mini PM in OpenClaw, which will do all the PM jobs. But first I thought maybe I should build the dev because that's what is car city for me. Maybe the engineers are building mini PM. So that's OpenClaw. If you can take this kind of a structure, you can set and assign work to it through the channels that you are already familiar with, and then you can have this idea of this whole sandboxing or controlling a whole machine to itself, and you're just giving it that work and then permissions to go access it to do your jobs.

    17. AGAakash Gupta1:16:18

        So you've been a PM at all these big tech companies like Google. Let's be real, right? Google isn't gonna allow you to just give your company access to an OpenClaw. How should a PM at a big company mitigate security concerns? How should they be using this latest technology?

    18. MYMahesh Yadav1:16:36

        Yeah, no, I 100% agree. I think the idea is not like-- OpenClaw is not a technology. Like it's not a product. It's a pattern for me. It's a pattern on how these agents can be useful with an agentic loop. And they will copy the pattern and offer you in a sandbox way, which can be inside their Antigravity or inside their Gmail workspace or on GCP. So in GCP, if you ask, uh, somebody today and say, "Hey, uh, uh, my Kubernetes cluster is down." I can't debug that today. But with this pattern now, this message will be sent to their sandbox VM, which will be running OpenClaw or some version of similar pattern. And now it will go and simulate first to their Kubernetes cluster, try to make the same deployment, and then debug it. First reproduce the whole problem, and that's what people do. Like as humans, we will first try to reproduce that problem. We will try to make the same cluster, do it. But it-- These agents can't do it. Single loops can't do it. But now we can do it because we have the full control on a full machine, and now the agent can create, reproduce your problem, suggest a solution, try the solution, and then come back to you. And that pattern on that VM is fully controlled by Google. And as a user, all you are seeing is, I provided a solution to your problem. But you don't know that I tested it, but now I can test it. And that I think is what I am excited about. Obviously, there are challenges all around the security layer, which I think you already talked about in your podcasts earlier, where lot of skills, lot of attacks around those. But I think once you sandbox it, which I think is the next big thing. Now what is left, right? We have the agent loop. We have the whole pattern. Then what is left? I think the ability to sandbox these agents in a controlled way, that's an unsolved problem, and Google will solve it, and I think OpenAI is solving it. And that's what you saw with MyManus also. By the way, this idea of OpenClaw is not new. Like MyManus, the, the personal agent company gave you a VM and they run their code. And if you look at it, last I looked at it, I can actually log into that VM and start doing web browsing on their VM or do whatever I wanted to that VM.

    19. AGAakash Gupta1:19:01

        Mm-hmm.

    20. MYMahesh Yadav1:19:02

        So this was like this idea of enabling a lot of possibilities was always there. OpenClaw just made it so popular or so famous because it was open source.So Google will bring it to their companies in their sandboxes and solve end-to-end problems which humans used to do on their laptops, and then dismantle that based on each query or each problem they solve.

    21. AGAakash Gupta1:19:26

        So can you put it all together what we've learned today? How do we organize this knowledge? What drawers do we put it in? Where does basic knowledge about ChatGPT and n8n agents, Claude Code and OpenClaw, how does it all come together to create that builder PM?

    22. MYMahesh Yadav1:19:43

        Yeah, that's a great question. So [chuckles] you say, "Mahesh, you said a lot of things. How can I just have a plan for it?" So I think first two to three weeks, just understand the basics. Without that, you won't be able to leverage or even understand. It will become overwhelming once you reach the OpenClaw stage. So I spend with my people, like people who join our cohort, I spend like first six weeks with them explaining them what the models is, what the intelligence or knowledge is, how these tools actually are working. So spend that first three weeks. Then get to Claude Code or Cowork and automate your world, which is whatever you do now agent should be doing, and you should be building systems which basically allow agents to continuously learn or follow your patterns, which was two things in my example today, my checklist and my learner. And then this human-in-loop pattern, which was update everything every night, but keep me in loop. So that the second thing I would love you to build as a second stage. And third thing I would love you to spend another month on is just understand in and out of OpenClaw and see how can you have one thing in your lifetime, in your job that you can just give it to a machine and the machine does the work and give you results somewhere else. And the whole machine will be controlled by this agent. Give permissions left and right. Make sure that you are not giving permissions to your world. Just create a separate world for this and then see if you can delegate work and get it done. And once you have done these th- three things, then just read obviously your newsletter or take any product and see is it a variant of OpenClaw or agent loop, or it is something that is starting from scratch, like model knowledge. And then you will be able to see what are the possibilities that exist out there and, or which possibilities work for your company, for your feature, for your product that you're gonna build next. And that's your next three weeks. So this is like three weeks of first four weeks, then three weeks, then two weeks. So you're looking at nine to 10 weeks of a good work through of building with AI or becoming a builder PM.

14. 1:22:06 – 1:35:17

    How AI PM interviews have changed

    1. AGAakash Gupta1:22:06

       So you became a builder PM. Now you're trying to interview for the role. How has the PM interview changed with AI? What should PMs expect in the new AI PM interviews?

    2. MYMahesh Yadav1:22:17

       Yeah, I think there is one thing that I would love to, lo-love to share with everybody because I'm doing a lot of research on this, and a lot of people are coming to me every day. My calendar is booked for 15 minutes calls. I do four of those with our cohort members. Uh, just 15 minutes, uh, because they have interviews and I don't charge for it if you have done our cohort, uh, because I just want to help and I want to stay updated as well on what's happening. So let me tell you like three things that are happening. One is this idea, especially for level five, level six AI roles, that idea of doing normal product sense is gone. You will be given a problem, and you will be asked to solve it either in a case study or during your interview. That is becoming a pattern. And in that, people are trying to see, "Hey, do you understand where we stand? W- how the world is working? Or you are stuck in some past, like six months ago or one year ago past. So are you the person who is gonna take us to the new world or drag us with the old world making old decisions?" So that's what the first thing I'm going to check by giving you some assignment or by giving you case study or giving you a, a random problem. Second thing people are trying to assess is that, "Hey, have you done some kind of system design work?" Because still, like, there is a lot to even understand these things. So they will ask you questions on, "Hey, design a system for me. Here is a system design where you think the AI should improve with OpenClaw" or "Where within Claude Code-based agentic loop, how will you redesign the system?" Which people sometimes PM just come to me and they are like, uh [chuckles] you know, we have this story where, uh, my wife was interviewing for an MBA job after doing her MBA. She's a very good software engineer. And, uh, this was like a hybrid job. And the, uh, and the recruiter asked her what are linked list or how to reverse a linked list, which is a very basic question for engineers. But she was like expecting an MBA question, so she put down the phone. She's like, "I did the whole MBA to get away from linked list, and here they are again." [chuckles] So, so some people get offended with these like, "Hey, why is a system design question for me in an AI PM interview or a PM interview?" And becoming normal because if you don't understand the design of these systems, you are going to not find the right capabilities that we should be building on. If you-- These tools are coming up every day and each design is elevating what's possible. But if you don't understand the design, you can't see what the possibilities are, and that's why people are trying to test you there. So these are the two things, and beyond that, of course, like great product sense, great taste in the product, paying attention to detail, those are not going anywhere. But these are the two, two new things that I will add in testing whether you're a builder PM or not, and I do that all the time. Like I-If I give you a job and if you're not pulling out your Claude Code or some kind of a tool like Lovable, you're already out. Like if you just ask me like, "Hey, can I do a drawing tool or can I create mocks in Figma?" Those are the things that are like done, done. I'm not interested. So that's the new world.

    3. AGAakash Gupta1:25:36

       One of the distinctions that you make pretty frequently is this distinction between agentic AI versus AI specifically. So what is the difference? What do people need to understand?

    4. MYMahesh Yadav1:25:48

       Yeah. So AI is this idea that you can find patterns, so this idea that we all have data. Machine learning helps you find patterns in data. AI helps you use that da- those patterns and make money, broader AI, like AI as a umbrella. And then agentic AI is the thing which allows you to actually take actions, do jobs, and finish work. So the idea is that agentic AI need to have like these three or four components, which we talked about. Can I understand the world that I am living right now? Can I understand what's happening right now in that world? Building my context with these two. Once I have built, can I take actions, which is ba- running bash commands or calling tools or MCP servers? When I do that, can I run my own evals and make sure that I have achieved the goal or not? And if I have done all these three, then I am an agentic AI or product. Or if I just send you something like, "Hey, is it positive, negative emotion?" Then I'm doing more like an AI thing, which is I can do one thing specifically, and if you send me in this format, then I will work. Else, best of luck. That's the whole world of AI or cognitive services we used to talk in Microsoft about. But this is like a world where we are relying a lot on the model or this intelligence and giving it a loosely connected tools, knowledge, and memory, and then just trusting it to solve world hunger or any problem thrown at it. That's the agentic AI, and that's where most of the excitement and money is today.

    5. AGAakash Gupta1:27:26

       I wanna ask you a couple hot personal questions. You spent 13 years in big tech. You started in Microsoft around 2012. You left Google in 2025. Can you share the honest, what can people accept, expect in term of total compensation trajectory? What was yours over those 13 years?

    6. MYMahesh Yadav1:27:47

       Yeah, I think first, uh, it's pretty standard, right? You start with 120. I think AI worked very well for me. So I started with 120, spend all my life at Microsoft to grow it at 360, 400. And that time I felt like I have achieved nirvana. This is like the best it can be. And then when, uh, I think it got a 70% bumped when I joined Meta, and then another 70%. So this is all the AI that was there. So after that, I pretty much doubled my salary every year. Every two years, 18 months, every switch I made was a double salary switch. So if you end my last comp, it was looking at 1.3, 1.4 million is what you make easy at my level in my experience, if you're working in AI. And this is not you applying for jobs. This is them saying, "Hey, we need you. We are doing this new thing. Seems like you are the only one who have done this before. You tell us what you are getting, we will give you 30, 40% on top of whatever you are making." And then you can say, "I need 100%," and then generally they don't say no. So, and this is not only my story, right? All my friends who were at any stage, right? If they were in Meta, they are working in NVIDIA today, and their total comp is looking at two, 2.5 million.

    7. AGAakash Gupta1:29:04

       Wow, [chuckles] that's insane. So is that why you bounced around so much? 'Cause I never see people who worked at all four companies.

    8. MYMahesh Yadav1:29:11

       [chuckles] I wish. Uh, but it's not that, right? Uh, there was like, I, I loved Meta. So Meta was because I was just bored at Microsoft, and I wanted to get out of Seattle because for personal reasons, I wanted to live in Bay Area. And, uh, so Meta was a great company, and I would never left Meta. But Meta had this legal visa problem. So once I switch, I needed like my green card and need to switch my roles as like a product manager, and they couldn't do it because they had a USCIS case pending, so they couldn't file like my green card, and I was in that line for 10 years. You might have known this, uh, little that we stay. That's like one life thread that always running. So I gave them like good eight months to a year to resolve that USCIS case, but it was not moving anywhere. At that time, I needed to make a call. At the same time, I could admit that Bedrock at AWS was just building, and they needed somebody, and they threw a lot of money at me. So I could have waited more, but they didn't let me wait at all. So that was big deal. And then Google was more like a dream company, to be honest. Uh, like, uh, my wife always told me that, uh, if you are a PM and if you have not worked at Google, you are not a PM. Like, that was her way of judging me. Because, you know, if you'd-- you've done an MBA, so you need not to prove to the world. When you come from an engineering become background and you become a product manager, you have to prove to the world that you are a legit product manager. You're not a developer, just wore a suit. So that was just that. And when I-- they needed somebody who has built frameworks and actually built agents in 2024, and that I think what got me in, not my, uh, like awesome frameworks or Porter five forces. It was mostly how much I knew about AI, and so was my interview. My interview was very AI-driven, like very what I have done in AI and how I can bring AI to production. So that was my Google. So first that comp, and I think it was never driven by money. Otherwise, I would have never left, right? Uh, so, [chuckles] uh, but the-

    9. AGAakash Gupta1:31:21

       Yeah. Why did you leave 1.3 at Google when you left? And it would be something like 2.5, 2.6 now if you stayed and maybe jumped again. So why did you leave? What are you up to now?

    10. MYMahesh Yadav1:31:32

        Yeah. So idea is like, I think these companies are gonna throw a lot of money at you to keep you and then waste you. Uh, so that was my observation, especially at Google, right? Uh, means I think I'm away from them enough, and I'm not going back ever.

    11. AGAakash Gupta1:31:49

        [chuckles]

    12. MYMahesh Yadav1:31:49

        Uh, so the idea is that these are large companies, and if you look at like what happened in AI is large companies have not produced shit in AI. Like if you look at OpenAI, it was a small company which created ChatGPT. Then it was a small company, Lovable, that created Lovable. It didn't came out of Google. And then if you look at Claude Code, it was created by a very small team inside Anthropic when Anthropic was not big, and then OpenClaw. So what has happened in-- with AI is the tools are distributed, but these big companies have no environment to grow something which is-- can be imagined, put in production, and put in customer hands. I'm pretty sure I love people at Google. Most of the level three thinkers or level four thinkers live inside Google. I will go any day to stay even two hours with those people. I love them. But the company will never launch something like OpenClaw. This-- something like this will be killed. Maybe you are thrown out of the company for trying something like OpenClaw. So that's the kind of environment and that's the kind of guardrails they have put inside their whole ecosystem because it's such a big machine. Same as ChatGPT, right? Uh, like if you look at OpenAI today, they have become so big, and it's very hard for you to just come up with new ideas and throw it on Twitter, and then take feedback, and iterate for six months, and then one day say, "I have created something which is like some, uh, I think largest liked repo on GitHub." That is not possible. And for me, I reached a point in my life that I wanted to just stay unbounded as much as I could, and I was very blessed that I had this course and that was giving me lot of satisfaction of staying with people and not losing like... One threat I had, like money was like secondary, to be honest. Main problem was that you, you get so dependent on these institutions for learning, for staying up to date.

    13. AGAakash Gupta1:33:51

        Yeah.

    14. MYMahesh Yadav1:33:51

        I do miss, right? I will pay them today to be around Google, right?

    15. AGAakash Gupta1:33:55

        [chuckles]

    16. MYMahesh Yadav1:33:55

        Uh, so that is the main thing. But for me, that course that I started teaching on Maven always helped me stay even up to date than what is there. So as you see, I have tried OpenClaw. I have built my mini PM. I would have done more here than what I would have done at Google. And given a choice, I will never go, go to Google again or, to be honest, any company. It just-- They just kill every, uh, intelligence neuron you have with... Like you won't believe that, you know, for a two-page document you have to have a one page of approvals, and that takes like six weeks. In six weeks, a non-builder PMs becomes a builder PM, and then they can build anything they want ever. So that's the world we live in, and these are the companies backward. I know most of the people will watch this podcast with the branding of, you know, these big companies and the dream on how you get into. I just want to assure you that, uh, there is more you have today than you will have once you start working at these companies, especially in AI and especially for next two years. This is the time to go build. This is the time to build your own world, and I believe in that future and that's why I left, and I have zero regrets.

    17. AGAakash Gupta1:35:13

        What a way to end it. Mahesh,

15. 1:35:17 – 1:35:38

    Comp trajectory and why he left Google

    1. AGAakash Gupta1:35:17

       this is amazing. Your last episode was crazy. I think in like the first two weeks or something it hit eight thousand views, but every month since it consistently gets three to four thousand views because-

    2. MYMahesh Yadav1:35:27

       Oh

    3. AGAakash Gupta1:35:27

       ... your content delivers, it's evergreen, and this episode was a perfect demonstration of that, starting from first principles through to actions. Thank you so, so much.

16. 1:35:38 – 1:36:25

    Outro

    1. MYMahesh Yadav1:35:38

       Oh, Aakash, thanks a lot.

    2. AGAakash Gupta1:35:40

       I hope you enjoyed that episode. If you could take a moment to double-check that you have followed on Apple and Spotify podcasts, subscribed on YouTube, left a rating or review on Apple or Spotify, and commented on YouTube, all these things will help the algorithm distribute the show to more and more people. As we distribute the show to more people, we can grow the show, improve the quality of the content and the production to get you better insights to stay ahead in your career. Finally, do check out my bundle at bundle.aakashg.com to get access to nine AI products for an entire year for free. This includes Dovetail, Mobbin, Linear, Reforge Build, Descript, and many other amazing tools that will help you as an AI product manager or builder succeed. I'll see you in the next episode.

Episode duration: 1:36:25