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

Helping advisors scale from 1 person to many people.

AI Application:

Claude.ai

I’ve done one demo of NotebookLM in the past, but so much has been added that I decided to show different features and a different use case.

Overview:

Claude Cowork is Anthropic's AI agent built directly into the Claude application - and there's an important distinction worth understanding here. When most of us think about Claude, we think about the chat interface where we type a question and get an answer back. That's Claude as an LLM. Cowork is something different. It's Claude operating as an agent, which means it doesn't just give you information - it actually does work on your behalf.

The way it works is straightforward: you give Claude Cowork access to a specific folder on your computer, describe what you want done, and it goes to work. It reads your files, writes code if needed, builds outputs, and saves them back into your folder structure. You can watch it progress in real time, ask questions or request changes mid-task, and walk away while it finishes. The result lands exactly where you need it - inside your existing workflow, not somewhere you have to go retrieve it. For advisors thinking about how AI can do more than just answer questions, this is worth your attention.

How to apply Claude Cowork to the business today:

• New prospect preparation: Drop a prospect's financial statement and intake form into a folder and ask Cowork to build a simplified financial planning spreadsheet before your first meeting. It pulls the data, runs calculations, and delivers a usable model - in under ten minutes.

• Meeting prep summaries: Give it access to a client folder with recent statements, notes, and correspondence and have it generate a concise pre-meeting brief covering current holdings, outstanding action items, and relevant account changes.

• Portfolio snapshot reports: Point it at your client data files and ask it to create a simple one-page summary of a household's financial picture - assets, liabilities, net worth, and key metrics - that you can reference during review calls.

• Proposal drafting support: Provide background documents on a prospect and ask it to draft the narrative sections of a financial proposal, pulling specifics from their intake information rather than using generic placeholder language.

• Client communication drafts: Give it a summary of a client's situation and ask it to draft a follow-up email recapping your meeting, referencing the specific numbers and decisions discussed.

Advanced:

• Automated scenario modeling: Build a standard folder structure for new clients and have Cowork generate multi-scenario financial models automatically - running conservative, moderate, and aggressive projections without you touching a spreadsheet.

• Folder-based client workflow system: Set up a folder architecture for each client household and use Cowork as a recurring task processor that updates financial models as new statements arrive, keeping your planning documents current without manual data entry.

• Intake-to-plan pipeline: Create a standardized intake questionnaire that feeds directly into a Cowork workflow, allowing the agent to move a new prospect from raw information to a preliminary financial picture before your team ever opens the file.

• Cross-household trend analysis: Point Cowork at multiple client folders and ask it to identify patterns - which clients are under-saved relative to their retirement timeline, which households have significant concentration risk - giving you a starting point for proactive outreach.

• Compliance documentation support: Use Cowork to pull relevant data from client files and draft documentation for annual review files, suitability notes, or regulatory reporting preparation, reducing the time your team spends on back-office paperwork.

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

For years, the preparation work around client meetings has been one of the biggest hidden time costs in an advisory firm. You pull statements, build models, organize notes, draft talking points - and most of that work happens before the client ever picks up the phone. Cowork starts to change that calculus.

When an agent can move from raw documents to a working financial model in under ten minutes, the question stops being "how do I find time to prepare?" and starts being "how many families can I genuinely serve well?" That's a different conversation. A solo advisor or small team that gets back an hour or two per week across their meeting load has meaningfully more capacity - not to take on more clients necessarily, but to go deeper with the ones they have.

What also strikes me is how this changes the preparation experience itself. If the model is built and the scenarios are run before you sit down, your mental energy in that meeting shifts. You're not doing math in your head or hedging because you haven't verified a number. You're having a real conversation. Over time, clients are going to start expecting that level of preparation as a baseline - and the advisors who build these workflows now will find it much easier to deliver it consistently.

See Claude Cowork in action:

I tested this cold. No practice run, no pre-built prompts - just a prospect's financial statement, a detailed intake form, and a folder on my desktop. What came back in about nine minutes was a multi-tab Excel model with a balance sheet, retirement projections, scenario analysis, college funding calculations, and a monthly cash flow breakdown. It saved the file directly into my folder. I didn't touch a formula.

Watch the full demo to see exactly what the output looks like, where it got close and where I had questions, and how I'd actually use this in a real prospect meeting.

-Matt