I Built Myself an AI Chief of Staff. And it Changed How I Think About AI.

Happy Wednesday! This week:

Let’s get started!

Our work lives can be overwhelming. In my case, between my fractional work and consultancies, writing my newsletters, networking and biz dev, and more, I take a lot of meetings and send a lot of emails. Add in the long-term projects I’m working on — well, it’s hard to keep things straight. So a few weeks ago, I decided to fix that.

I built myself an AI-powered chief of staff.

Every evening, it scans my email, calendar, chat logs, and Google Drive to see what’s new. Claude Code — that’s what I built it in — then asks me to verify what it discovered and fill in the blanks. (It can’t see in-person meetings, LinkedIn DMs, etc.) The next day, it gives me an overview of what’s on my plate with the key info I need to get it done. It also flags big lifts that I’m working on, keeping me on track. I’d share a screenshot but, as you can imagine, it has a lot of information I’m not putting into an email newsletter for everyone to see! 🧐

This has totally changed how I work — not just because I’m more organized, though. The morning briefing is served up to me in an AI chat interface, and Claude asks me how it can help move things along, usually also offering up decent-at-worst suggestions. So I kept chatting with it. I asked it to draft emails. To outline a presentation and speaker notes. To help me think through new proposals and offerings — and more. And because it was already connected to Gmail and Google Drive, it could save those drafts for me.

Claude is now my work operating system. And I’m moving 5x faster than before.

I increasingly think this is where AI use is going. And I’m not alone. Nigel Vaz, the CEO of Publicis Sapient, wrote an essay last week for TIME, saying the following:

If I'm right — and AI becomes the layer where our work actually happens — the biggest change won't be that we draft faster. It'll be how our teams coordinate and how the grunt work gets done.

Think back to what shared documents did for us. Google Docs didn't make anyone a better writer. It changed how we worked together. We stopped emailing final_v3_FINAL around, stopped wondering who had the latest version, and started working from one living document with a revision history we could trust. The leap wasn't writing — it was coordination. We moved from passing versions around to building on a single source of truth.

AI-driven workflows are the next version of that same leap. And for communications teams, I think it lands in three places.

The grunt work becomes a system, not a chore. Researching reporters — who covers your beat, what they've written lately, what they actually care about — is the kind of task that gets done by hand, a little differently every time, and walks out the door when the person who did it leaves. Built as a system, it runs the same way every time, at a scale no one person can match, and it gets better as you tune it. That's the part worth sitting with: these systems don't just copy the tedious work, they do it more consistently than a human ever would on a task they find boring.

Teams coordinate around live information instead of passing updates around. Right now a lot of comms coordination is just sending things — the morning clips email, the "here's what's happening" Slack, the weekly status doc. Every one of those is a snapshot that's stale the moment it goes out. The shift is the same one Docs gave us: an internal comms calendar or a coverage picture that everyone works from live, always current, instead of a version somebody has to keep re-sending. Fewer handoffs, less reconciling, less "do you have the newest one?"

The context stops living in one person's inbox. Supporting an executive is a good example. So much of what makes exec comms work — how they like to sound, what they've already said, what we decided and why — tends to live in one trusted person's head. Put it into a system and that context is there for whoever needs it next, the way revision history kept the story with the document. And your chatbot can read those notes and give you the key details you need — even if your colleague wrote them.

None of this replaces the judgment, the relationships, or the taste that make communicators good at the job. It clears the path to them. Same transformation shared docs gave us, one layer up: from passing versions around to building on a shared, living system.

I’m increasingly confident that this is going to be the way we work in the future — because I’m already working in this context. And I don’t see how I could go back.

Search engines and AI platforms reward brands that are mentioned, cited, and trusted across the web. PodPitch books your experts on relevant shows, creating branded mentions, backlinks, transcripts, citations, and reusable content. Only 20 demo spots are available this month. Once claimed, the offer disappears.

Appear on 3,853,234 Podcasts

Nearly fifty of you have now sat through this one with me: an hour, seven prompts, and a real working tool at the end of it. No coding experience required.

What you'll build is The Comms Gut Check, a web app where you paste in a draft and get structured feedback on clarity, jargon, tone, and where your audience is likely to push back. (I ran the Declaration of Independence through mine. The loyalists did not care for Jefferson's prose.) But the tool isn't really the point — getting comfortable enough with Claude Code to build the next one on your own is.

The next session is Thursday, August 6 at 11 a.m. ET. Same build as last time, so if you couldn't make the earlier ones, this is your chance. Save your seat.

A bit of setup before we start, so we can get through the whole build in the hour:

If you'd rather see the full walkthrough of what we build and why, here's the issue where I broke it all down.

And if you want me to run a guided build for your team, get in touch.

One more proof point for my thesis above — or, at least, someone else who shares that thesis — is this conversation between Ragan and Sirui Hua, head of audience and analytics at NowThis. Hua isn’t a traditional communicator — he’s focused on channel strategy and AI adoption, not media relations or exec comms or the like. And the biggest mistake communicators make with AI, according to Hua, is thinking of it primarily as a writing tool.

Hua argues that drafting copy is only a small fraction of AI's potential; the real value comes from using AI to manage entire workflows. (Yes, that’s effectively the point I made above.) Instead of asking AI to write a press release or social post, communicators should think of themselves as managers who set goals and quality standards while specialized AI agents handle research, data gathering, reporting, formatting, and other repetitive tasks before a human reviews the final output.

Hua points to NowThis's own AI-powered paid social workflow, where multiple AI agents collaborate to monitor campaigns, analyze performance, and recommend optimizations using information pulled from Slack, emails, contracts, and data systems. He also recommends starting small: identify one recurring task your team dislikes — such as compiling status reports or analyzing thousands of audience comments — and automate that process end-to-end. His underlying message is that AI's greatest benefit isn't better writing, but freeing communicators to spend more time on strategy, creativity, and judgment.

Whether you're trying to build systematic AI adoption across your team or focused on AI search visibility for your brand or organization, I’m here to help.

I have three slots open for late August/September — learn more and book an intro call.

Looking forward to working with you — Dan

Looking for a role at the intersection of communications and AI? Here are some opportunities to check out:

Catch is an AI admin that's as easy as a conversation. Just call Catch and talk, like you would any assistant. Scheduling, bookings, follow-ups: say it once, consider it done. No apps to learn, no forms to fill. Get started at catchagent.ai and speak to your admin savior today.

Start now for free

Was this forwarded to you by a friend or colleague? Want to get this in your inbox next week? Click here to subscribe!

Quick question: how can I help?

What workflows are you struggling with? Where does AI still feel mysterious or overwhelming? What has worked that you’d like to share with others?

I’m a builder, and I’d love to help you and the rest of The Comms Stack community find great new ways to use AI.

Reply and tell me.
I read every response.

Even a one-sentence reply helps. For example:
“I wish AI could help me with ______.”

Until next Wednesday,

Dan

Advertise | Subscribe