How I built my AI Chief of Staff
Sign in<br>Subscribe
#280 - May.2026<br>What if everyone can have a Chief of Staff who can take out the coordination burden, while partnering for strategic decisions?<br>I've been struggling for a long time to remove a burden that all managers carry: tracking and coordination. Every time I tried to focus on deep work there was one more email, one more Slack channel, one more task to add to my to-dos, one more...<br>Half of my day was mostly about catching up with a wave of information from the day before. A sense of being reactive all the time. Over the years, this got worse as the size of the team and number of projects got bigger.<br>I was using AI under the promise of removing repetitive tasks but I was scratching the surface: ad-hoc prompts here and there asking for a summary, generic questions about general things and, maybe, drafting a narrative for a business document.<br>I needed a true partner. A Chief-of-Staff that could serve as my front-line barrier to filter noise from what's important.<br>So I tried to build it. My personal Chief-of-Staff.<br>A way to connect all the relevant context with the wave of signals that crashed at the shore of each morning. I needed a system that helped me perform 10X better as a Manager, removing the admin load and allowing me to think more deeply as a Product Leader.<br>If you also struggle to make time for deeper work, I think this is for you.<br>AI agents<br>I was already playing with multi-agent workflows. But so far, most cases were about search and summarization. Useful. But not what I needed in my day-to-day.<br>So I imagined the following "ideal" morning: what if , as soon as I get to the office, I got an executive brief of how my day looks, what are the important things ahead, an update across every project I care about, a list of updated tasks under my direct ownership and a strategic prioritization recommendation on what will move the needle for my team?<br>I thought that, if this was meant to be a process with roles and responsibilities, what would that team look like?<br>I started with these what-if questions to design a solution.<br>I thought that, if this was meant to be a process with roles and responsibilities, what would that team look like? So, I decided I needed:<br>An information seeker who knows all my communication channels, what information is relevant and what is noise. This person has a big network for getting news.<br>A project organizer who understands where each new piece of information fits, what is new vs. existing. This person loves structure and order.<br>An executive assistant who knows me as a close partner. Knows about my team's goals. My personal goals. Calls out the things that I don't want to hear. And offers me perspective to make decisions. This person is my trusted advisor.<br>I couldn't hire all three as real employees.<br>So I tried to emulate them as AI agents.<br>What started as a playground for testing later became an essential part of my daily routine as a Head of Products.<br>Building the system<br>I needed a few ingredients to run this process.<br>First, a place to keep a knowledge base that could fuel all agents. I've been taking digital notes for years using Apple Notes. It has been my go-to tool for tracking reminders, to-dos, and project-specific notes.<br>But then, I found Obsidian.<br>If this is the first time you hear about Obsidian you can learn more here. In short: Obsidian is a note-taking app based on markdown files. At first it can feel overcomplicated (markdown files need to follow a specific format) but, once you get used to it, the complexity disappears. Obsidian also offers a rich knowledge graph that lets you connect and navigate between related notes. Knowledge repository: checked.<br>Second, I needed an intelligence engine . I used Claude for this. Before this system, I was already using Claude Projects. I stored documents in each Project and used them for chats. So I decided that instead of using specific Projects I was going to feed Claude with my entire Obsidian vault.<br>I can't say enough how the Obsidian + Claude combination is a super tool.<br>Local markdown files become the context. Practical and efficient. Obsidian + Claude is like having a personal Google-like repository. Intelligence layer: checked.<br>Now I needed to design the workflow.<br>I started by defining a few design tenets on how this system should work:<br>I wanted it to be fast so it can run first thing in the morning (speed )<br>I wanted it to be smart enough and use as much context as possible (useful )<br>I would like to make it flexible to propose changes when needed (adaptable )<br>I wanted to be the final decision-maker (controlled )<br>I organized the information in Obsidian using a PARA-inspired structure. This structure helped me organize a place where new information can land, one for all context files, one for all active projects and one for all the rest.<br>Vault/<br>├── 0. Inbox/ ← Default landing zone<br>│ ├── MY TASKS.md ← Central task tracker (single source of truth)<br>│ └── CONTEXT/ ←...