Happy Thursday,

AI isn’t slowing down—and neither should we. This newsletter is your shortcut to practical ideas and smarter strategies to grow, lead, and adapt as tech reshapes our industry.

To take it one step further, I’ve launched a new YouTube series. Each month, I’m sharing quick, tactical videos showing how advisors can use tools like ChatGPT to save time, think better, and scale more efficiently—starting with the work you're already doing.

Watch my latest episode here

The AI Edge

AI Application:

Lindy

Overview

Lindy is an AI agent builder that lets you create automated assistants using plain English. No coding, no complicated workflow diagrams. You describe what you want the agent to do, and Lindy builds it.

The concept of "agentic AI" gets thrown around a lot right now, and most of the tools that let you build agents assume you're comfortable with logic trees and conditional triggers. Lindy's differentiator is the conversational build process, you tell it what you need in the same way you'd explain a task to a new employee, and it constructs the underlying workflow for you.

The tool connects to your existing tools, which is where it actually becomes useful. Rather than just generating text or summarizing things, Lindy can act on your behalf — reading email threads, checking your availability, creating tasks and completing actions. It's the difference between a tool that helps you do something and one that does it while you're focused elsewhere. The premium tier runs $20/month, which is the threshold where the more powerful features unlock.

How to apply Lindy to the business today:

• Build a scheduling assistant in under an hour. Give Lindy a dedicated email address, connect your calendar, and describe how you want meetings coordinated. When you include that address on an email with a client or prospect, your AI assistant takes over the scheduling thread entirely.

• Eliminate multi-party scheduling drag. The tool shines when you're trying to coordinate with two or three people at once. Rather than that back-and-forth chain where everyone's suggesting times that don't work, your Lindy assistant checks your actual availability and proposes slots that fit — then follows up until everyone confirms.

• Personalize the assistant with your own branding. You name the assistant, define its communication tone, and set parameters like meeting length and buffer time. It signs every email as your assistant and stays in the same thread throughout, so participants are having one cohesive conversation.

• Handle scheduling follow-up automatically. When a proposed time doesn't work for one participant, your assistant proactively reaches back out to the person who can't make it, offers new options, and continues coordinating without you re-entering the conversation.

• Layer in meeting logistics. Lindy connects to Google Meet (or Zoom if you prefer) and automatically creates the video link, sends calendar invites to all participants, and confirms the booking with a final email to everyone — all without you touching it.

Advanced:

• Build agents for other administrative workflows. The same voice-prompt build process that creates a scheduling assistant works for other repetitive tasks — client follow-up sequences, document request reminders, or intake workflows for new prospects. Scheduling is just the most intuitive first use case.

• Connect Lindy to your CRM. If your CRM has an API or Zapier integration, you can instruct Lindy to log meeting confirmations, update contact records, or trigger next steps after a meeting is booked. It starts to become a connective layer between your calendar and your client management system.

• Build team-level agents. If you have a support staff member or ops person, they can maintain and refine the agent's behavior over time without involving you. The prompt-based interface means non-technical team members can adjust how the assistant communicates or modify its scheduling logic.

• Set meeting type logic. You can build multiple agent configurations for different meeting purposes — initial prospect calls at 30 minutes, review meetings at 45, planning sessions at 90 — and route different email threads to different agents depending on who you're meeting with.

• Test and iterate the agent in real time. Lindy shows you each step of what the agent is doing as it runs, which means you can see where something breaks and prompt-edit the fix without rebuilding from scratch. The refinement loop is fast enough to dial it in during a single sitting.

What could this application mean for the future of our business?

There's a version of this that matters more than the scheduling piece itself. Scheduling is just the most visible thing that eats advisor time without adding any value to the client relationship. But the underlying capability — building an agent that reads context, checks systems you're already connected to, and communicates on your behalf — is more broadly applicable than that.

The interesting question is what happens when advisors have several of these agents running across different parts of their practice. One handling scheduling, one following up on outstanding documents, one managing the intake flow for new prospects. The aggregate effect starts to look like having a small operations team, at a fraction of the cost, and without the coordination overhead.

The more significant shift is probably in what advisors choose to protect with their own time. When administrative tasks have agents behind them, the calculus on what requires a human touch changes. Client-facing moments, advice conversations, relationship maintenance — those stay with you. The rest gets increasingly automated, and clients won't necessarily notice, because the communication coming out of these agents is professional and responsive. The practices that start building these systems now are going to have a structural capacity advantage over those that are still managing calendars manually in two years.

See Lindy in action:

This demo is longer than normal. But it still shows the ability to build an agent in less than 30 minutes

In this week's demo, I built a scheduling assistant from scratch — named her Sarah — and ran her through a live three-way scheduling scenario with two different email addresses. It did not go smoothly at first, and I left all of that in. (I was the reason it didn’t go smoothly, the tech actually worked, the human was the problem!)

You'll see me troubleshoot a wrong calendar connection, send emails to the wrong address, and prompt-edit the agent mid-demo to fix the issue. But you'll also see the moment it clicks — Sarah coordinating back and forth between two participants who both have scheduling conflicts, offering new times, following up proactively, and ultimately booking the meeting and sending everyone a confirmed invite with a Google Meet link. The whole thing took under 30 minutes to build and test, and the rough edges were mostly me.

Watch to see what building your own AI assistant actually looks like, end to end.

-Matt