How I turned Claude into a self-improving PM assistant | Daniel Blum (PM, Melio)

0:00Daniel Blum:I cannot describe how powerful it is. I'm really able to do in a day now what used to take me a week. But more than that, I'll say it's a lot of deeper work. There's things that I do today that I just wasn't able to do before. Whether it's more in-depth research, whether it's being more data-backed, anything you do today, you can do it almost at the top level. One of the things, even at a company level that I tell people, is, look, you got to go through the pain of switching your systems. and it's not going to be as efficient. And yes, of course, like the old way will be faster because it's muscle memory.

0:35But if you get to the next level, not only will you have a system that works better for you, but everybody will have more skills.

0:42Daniel Blum:Today, I say I manage about 70 to 80 % of my time in front of the computer with co-work alone. We've seen a couple of morning briefs, but I want to see what you think makes yours different. In this daily brief, my co-work runs through my recent slacks, my emails, my journal notes, and it looks for context that it doesn't understand in these things. And it says like, oh, if there's a file I wasn't aware of, there's a milestone, there's a goal. It would ask me about it and say, hey, like, what is this? Is this important? Should I read this? And this is, I think, where the real magic happens. This is really genius.

1:11I'm curious how this scales beyond you. So you have your system, your, you know, 10xpm now. Congratulations.

1:19Daniel Blum:How does this affect the team? How do they use systems like this?

1:25welcome back to how iai i'm claire vo product leader and ai obsessive here on a mission to help you build better with these new tools today i have daniel bloom and he's going to show us his claude co-work system to rule them all it self-heals it self-optimizes and it's way better than the morning briefing you have going on let's get to it optimizely agent platform for marketers is built on a bigger idea, a whole directory of agents now joined by a newly revealed squad of virtual teammates, each with a defined role and a personality of their own. This isn't about faster drafts, it's about handling the coordination too.

2:07The research, the approvals, the handoffs, the routing, the back and forth that quietly eats your week and never makes it into anyone's highlight reel. Get the story behind it all. Hear the confessions from marketers who have handed off the busy work, meet the squad and understand what virtual teammates can do for you at optimizely.com slash how I AI. Daniel, welcome to how I AI. I am so excited to have you on this episode because every week, every month, I think things get better. And I'm always impressed with how much more organized everybody but me seems to get with their AI and their personal productivity.

2:53And so tell me, like, what brought you to building this big system and what problem are you trying to solve?

3:00Daniel Blum:Cool. Well, Claire, thank you so much for having me. I'm really excited to be here. As somebody who's been an early adopter of AI for quite a while, I think it took already like a good few months ago or even a year ago, we were able to solve some of the big or at least improve some of the big jobs to be done for PMs with even with simpler tools like with gems. You could improve your specs and you could improve your research. But I think as I was progressing with my AI adoption, I really felt that one of the biggest things that hangs over me and really makes my day to day more difficult is all this just overhead of being a PM, of coordinating a bunch of things, remembering endless tasks that arise on Slack and meetings and action items, and just trying to maneuver this whole chaos that happens every single day, while at the same time wanting to do in-depth work and focus and really think, I felt that that was something that was really, really difficult for me.

4:00Daniel Blum:And I was getting nowhere near solving it until I was able to actually build a system with co-work that I'm actually still a little bit surprised at how powerful it is and how much it's helped transform this problem for me. So tell me about your personal AI stack as a PM. How did you pick the tools that go into it? And then I want you to show us how it all kind of works. Perfect. So I'll say I think most of my choices were made by my company, Melio, and the tools are in our stack. But thankfully, I'm pretty satisfied with those. So for a long time, we only had like the Gemini Enterprise and we were using that.

4:44Daniel Blum:And just a few months ago, we got the Cloud Enterprise and Cowork. And that's when things really changed for me. and besides that I'm basically bound to whatever whatever tools we have and use so this is this is what I work based off of. Okay so this is good for everybody out there who is stuck with the tools that they're stuck with you can still make it look at work I think that Claude is obviously like a big part of this stack was co-work just the big unlock for you like where did you when did you start building this and what was the early tools versus what you use now? Yeah, so I think, first of all, in your first saying, I think it's very correct.

5:24Daniel Blum:And in general, I'll say like, I was bound by constraints of an average PM all the time in terms of having, you know, not endless tokens and needing to work within budgets and bureaucracy. And I think it's very possible and very doable within all those constraints that, you know, real PMs face. And I think it's very important to say. And in terms of the tool, so Cowork was definitely the big unlock for me. But I think while I love Cowork, it's not Cowork in itself. And I think Codex could be great for this as well or ChagPT work. I think the real importance is for a system to A, be able to rewrite its own core files.

6:05Daniel Blum:And that means that it keeps on improving. And B, just have connections and integrations to as much of your ecosystem. When these two rules apply, there is a significant, significant opportunity to really, really improve the way you work. And while I was working with Gemini Gems earlier, and there is obviously some incredible things that can be done with those, these two elements make a system really powerful and also really integrated into your daily life, but also self-improving, which is one of the biggest unlocks here. Okay, well, let's show it to us. I want to see how you actually manage your life as a PM.

6:43Daniel Blum:Let me start with this notion board, right? So this is nothing incredible. It's just a standard PM notion board. It has three sections. One is top of mind, which are the large initiatives that I just think of, you know, on any given time. It has my this week, which is basically the priority that I have for this week. And it has inbox, which is things that arise from Slack, email, calendar, and Cowork picks up and fills them in here. Now, the cool thing about this board is not that it exists, but the fact that not only did Cowork build this completely on its own, I was working with a very simple and messy Google Doc before, and I think Cowork got tired of it and basically decided to build this for me.

7:29Daniel Blum:But also it actually manages it on my behalf. And I think that's the pretty cool thing that I want to show. And I'll walk you through how it does it. I'll say that the most important thing about this is that it knows me really, really well because I spent a lot of time and effort contextualizing it and maintaining this context and also centralizing all of my work in it, which took some time to get used to, but the ROI is just absolutely insane there. And I really felt how well it knows me just when prepping for this episode when I knew that because this is my real environment, I couldn't show names and projects and sensitive stuff.

8:10Daniel Blum:So basically I just created this skill on Claude called Demo and I just told it, replace all the terminology and specifics with generic terms. Then because it knows me so well, basically in one prompt, I was able to replace my manager's name with your manager and my top initiative, you can see here, with headline feature. And that's how well it knows me. It was just able to replace all of these and it just makes it for a really, really seamless and comfortable collaboration. Tell me a little bit about how that context is saved. Is it just that you just put everything in notion so when it's searching it kind of knows?

8:45Is there something more purposeful around your kind of personal brain? How do you inject context into the system?

8:52Daniel Blum:So I'll say when I built up the system, it was very important for me to build something scalable. So I did a lot of research on like how to build, how to set up your CloudMD and the context files. And basically I set it up so there's a context file around every topic that I have and like every area of my work and my goals and my colleagues and everything that you can imagine. I spent a lot of time manually contextualizing in the beginning, whether through like feeding it links and different decks and stuff like that. And also just a lot of, you know, whisper just dictating endless information and blabbering endlessly about everything that I can think of, which is just incredibly powerful and how much context you can give relatively easily and quickly.

9:40Daniel Blum:And then this system basically updates itself on a recurring basis. every few weeks. It runs and updates the knowledge files based on different things that have occurred and different changes. And we will see some of that just in a minute. I love it. Well, let's switch over to co-work and show us how kind of the system is architected and then how you maintain it and use it over time. Perfect. So it all starts with one recurring task, which is a composition of several skills called the weekly prep. So the weekly prep is the very basic task that helps me start my week. I'll say that I won't run this live just because I want to be mindful of time.

10:25Daniel Blum:But generally speaking, this task helps me go through all these things that you just saw in the Notion and fill them in. So we basically have the top of mind, the this week and the inbox. And what this series of skills does, it pulls in information from my entire ecosystem, from my Notion, my calendar, Slack, from Granola transcripts of meetings, and basically recommends what I should be focusing on this week. If there's new top of mind items that need to be added or removed, it would recommend that. It would recommend moving, removing, finishing things from this week. And the same with the inbox.

11:03Daniel Blum:and this basically on Sunday mornings, this is our beginning of the week. It helps me start with a very, very clear and focused list of what I actually want to do. And then finally, it helps me prep for my meetings. So it runs me through the meetings that I'm going to have and asks me how I want to prep for them, whether it's like a serious preparation that requires its own task in my weekly priority, whether it's a quick reminder or just meetings that don't really need any prep. and then I confirm all of this and I'm set to go and this is the start. And does that push all of it into Notion? Yes, and that basically, this test that I ran earlier basically created this state that we have now, the Notion that we have right now, but I'll also show you how it updates it.

11:52Yeah, let's look at that. Perfect.

11:55Daniel Blum:So the unique thing about this is that I think, and this is something I ran into after having created the first weekly prep. I think one of the things any PM can resonate with is the fact that there's two worlds, right? There's this beautiful, clean, organized world that's in our weekly priority or our roadmap where everything is very clear and beautiful and fits in. And then there's reality where, as we said, this chaos of slack and meetings and urgent priorities and executive asks and endless things that just flow in and out. And what I was feeling in the beginning is this real gap between what I was doing and prepping and what was happening in real life where I was spending all this time doing all these small tasks.

12:40Daniel Blum:And I think I've built a system to really work alongside me. And part of the fact that it knows me really well is also that it knows how I work. So for example, I'm inbox zero, both on Slack and on email. So it knows that if something was saved on Slack and is no longer, it means it's likely done. Or if something was on inbox in Gmail and is no longer so, then it probably means I already read it. And that really, really helps in how we collaborate smoothly. So basically, let me run to my next scheduled task. And this is called the morning brief. And this is, I think, where the real magic happens.

13:17Daniel Blum:So actually, we're going to run this live right now. I had to laugh because I think folks' AI setup is a real reflection of their internal personality. And you strike me as somebody who is organized and thoughtful. You're an inbox zero person. person I am sorry to anybody that tries to text or email me I am like a chaos reigns person I cannot put my stuff in a table I cannot put my stuff in a kanban board I need just a bot and I need when it's two in the morning or it's six in the morning or it's two in the afternoon I just need to be like dear bot what's going on what's going on and so it's always fascinating to me to watch people who I just pre-AI have like a much more structured approach to their work.

14:10And then post-AI, I think it really reflects in how you build your system because mine looks, it probably should look like something like this, but it looks nothing like this.

14:21Daniel Blum:Well, I think I'll say first of all that you are correct in me being quite an organized person, But I will say, like, again, in reality, a lot is a mess and a lot is like I've found out how much is like business logic in my brain. And I've had this experience with the system where I continuously like do discovery on myself and how I work. And I continuously run into this places where the system is not good enough because it doesn't cover this. And what it doesn't cover, like it has a blind spot, then it becomes much less powerful. so over time I've like covered all different angles and I think it's doable I think it's doable and up until recently I would say in a way I was also operating chaotically you know some of the tasks were in saved and slack some of them were like in my inbox others were just like tabs that are open in Chrome and I've just had Claude like learn to work with all of these and say all right I'll take unfortunately it can't take an open tab as a task but everything else I just learned to look at the same way I do Well, let's look at this morning brief because we've seen a couple of morning briefs, but I want to see what you think makes yours different.

15:29Daniel Blum:OK, so I think there's several things, but I'll walk through this very quickly and show the different parts and I'll highlight the interesting things. So the first part is that this brief basically walks me through my meetings. I think one of the biggest pains of PMs is we have a ton of meetings. We need action items. We need to act on them. Almost every meeting creates new work, but we have to run to the next meeting. And oftentimes it's back to back until the end of the day. And then, you know, so this helps me kind of catch up on yesterday's meetings and it shows all the different things. And basically you can see this takes the granola transcripts and it gives me a one liner about each meeting and if there's an action item.

16:08Daniel Blum:So here I can see from all of these meetings, looking through them, there is one action item to share the walkthrough and recording of a write up in the feature channel with go to market. And that's it. So it's going to offer me to expand or draft any summaries. I'm going to say, no, let's continue for now. And we're going to walk on over to the next phase, which I think is pretty cool. One of the things that I think is super powerful with cowork and with these harnesses is that you can set them up for improving themselves. And one of the things I've done is I've over time, I'm building up towards Claude being more agentic and being more able to act on itself.

16:50Daniel Blum:and I'll show you this and I think it's pretty visible in this flow. This part is pretty cool where basically one of the difficulties in life is keeping the context clear, right? So you have the system, you contextualize it in those things, but then how do you make sure that it keeps track? So this is one of the ways I've thought of. So basically what it does is imagine in this daily brief, my coworker runs through my recent slacks, my emails, my granola notes, and it looks for context that it doesn't understand in these things. And it says like, oh, if there's a file I wasn't aware of, there's a milestone, there's a goal.

17:24Daniel Blum:It would ask me about it and say, hey, like, what is this? Is this important? Should I read this? So here it flagged something. Let's see what it is. A term I didn't know. The settlement cap. All right. This is some payments thing. And it says like I read the thread and understand it's a limit working through. Want me to save? Yeah. So I'll say save. Yes. Save it to the context. So basically, this is how Claude helps me keep it contextualized and not lose track of things. This is really genius. And I want people to just take a pause and reflect on what this is, because it looks like for your context, you are making sure that Claude understands internal definitions, terms, goals, etc.

18:05And so many of us work inside companies where the things that we say are not in the training data. Well, not yet, at least. They're not in the training data. And so actually proactively prompting Claude to say, like, I don't understand what you're talking about here. Can we define it together? And then I'll save it to my context and I'll know what you're talking about. Moving forward is really, really sharp and something we haven't seen on the podcast yet. I love this.

18:28Daniel Blum:Yeah. So it's super hard to just keep track. And the unlock is that you're able to say, oh, I can just ask Claude to be my partner in doing this and automatically, you know, follow up and insist on getting this knowledge. is a really, really big unlock. Amazing. So you run it weekly. You run it daily. Do you actually spend time in the Notion or are you still like navigating all this with Claude? So the main idea is that Notion is almost a read-only for me. I look at the Notion to get my focus, to remind me of my top of mind, to remind me of my priorities and focus this week. you know every so often I'll mark something as done if I just finished it but generally my goal is to have Notion as something I only look at and Claude manages on my behalf and in general I'll say this is something that has happened to me naturally but I think it's one of the core pillars of building a strong system today I say I manage about 70 to 80 percent of my time in front of the computer with co-work alone.

19:36Daniel Blum:Almost everything I do here is through co-work. And I try to do more and more of it because anything that I don't do in co-work, then the context is not as well caught as if I do it through co-work, whether it's, you know, other applications, whether it's Jira, Slack, queries, anything generally. So are you using co-work with Chrome at all? Like, are you using browser use or are you purely just using like connectors and mcps for all of this yeah so i would say in the beginning i was using like chrome a lot in my personal co-work that i have i use chrome a lot um as as time proceeds and and there's more and more mcps and connectors then obviously those are comfortable but like the chrome connector is a critical critical piece of you know of the puzzle for when you don't have these connectors and integrate integrations and you need to use the browser and do you feel like this is really saving you like what's the benefit here is it like saving you time do you feel like you just know everything are you getting better work done like why because you know again these systems take time to maintain and i think we're all sort of at this point with our ai systems we're like okay they're all super cool but like why are we why are we doing this and so i'm just curious like what is the benefit you're getting as a PM to running this system?

21:00Daniel Blum:Yeah, so it's a great question. And I think, honestly, oftentimes we make systems that don't give us great benefit. I built a personal agent that its main work is sending memes about my wife in our shared channel on Telegram, which, hey, to me is huge value, I think. It's helping me win arguments, but jokes aside. Quick pause. You need to watch our episode with Jason, the CEO of Meme Lord, who actually has a meme API. So you can plug that into your agent. That was a very weird episode that we did. So I haven't watched it yet, but I will say it's literally like the top to do task in like a cloud session that I manage my agents and what's next.

21:48Daniel Blum:The meme API is definitely the next one. Yeah. But I'll say, I think it's a really, really good question. And I will say also that probably in the beginning, it's not going to like the ROI is not going to look great, especially when you set up something that's as robust and as significant. It's going to take some time because while it doesn't know you and your personal, we can call it business logic and like the way you operate, it's going to be very frictionful. And everything it does or says or thinks, it's going to be a little bit off and you're going to lose trust and you're going to be very skeptical and then you're going to double check everything.

22:28Daniel Blum:But the value tremendously compounds. It's just incredible. The more you kind of power through these first few weeks of a contextualizing ruthlessly and continuously sharing everything you can and be centralizing whatever work you can in co-work or in your harness. even if it doesn't feel so natural over time it is just in i cannot describe how powerful it is and i'll say personally i think first of all i'm really able to do in a day now what used to take me a week and and i stand behind that it's and you know it's something that sounds like a like a hypey linkedin post headliner but it's it's it's true you know it's it's insane i i look at um i I look at the way I work through these like this week and oftentimes I can get through this week in a good day, which is just mind-blowing.

23:23Daniel Blum:But more than that, I'll say it's a lot of deeper work. There's things that I do today that I just wasn't able to do before, whether it's more in-depth research, whether it's better being more data-backed when checking things, working less off of hunches and more off of like facts and researches, whether it's competitive researchers, like anything you do today, you can do it almost at the top level, as opposed to back in the day, moving fast meant you need to, you know, operate on a lot of hunches, not work off of data, not be as robust in terms of your documentation. And today it really, really changes.

24:07I love it. I love it. You've sold me. I don't know if I'm going to get as organized as you. But I and I think that's absolutely right. One of the things even at a company level that I tell people is, look, you got to go through the pain of switching your systems and it's not going to be as efficient. And yes, of course, like the old way will be faster because it's muscle memory. But if you get to the next level, not only will you have a system that works better for you, but everybody will have more skills. And I think that's almost the more important part where this is a personal productivity system that works for you.

24:42That's great. But I'd say probably the bigger benefit is it forced you to learn how to use co-work and use these AI tools in a different way. And as a product builder, you have to know that stuff. You have to think about, well, what if my product's being used only through Claude? What do I want that to look like? And I think it's just if you are a product, it is just one of the most important things that you could do. This episode is brought to you by Jira by Atlassian. The Teamwork Graph in JIRA delivers 44 % more accurate agent results with 48 % less token usage. That's a huge difference when working with AI coding agents like Quad, Cursor, Codex, or Copilot.