How to run your marketing stack from one window


Hello Reader

I was on a call last month with the CMO of a global marketing agency who has 180 people around the world, clients on three continents and a team full of capable marketers who use AI every day.

The CMO looked sheepish when she explained their uncontrolled tool sprawl.

"Because of the composition of our teams, we have people using different tools,” she said. “The creatives use tools like Midjourney and Firefly. Other parts of our business use Gemini or Claude or ChatGPT. Or Copilot if it's our Microsoft team."

Each function picks its own tool and uses it independently of everyone, and everything else.

"We don't have a lot of people thinking about how to take an ongoing activity and build a workflow or an agentic workflow. We're missing that."

Most teams haven't solved the tools problem either.

Gartner found that marketing teams use less than half the capabilities in their martech stack on average.

And yet Scott Brinker's research shows marketers are using more tools than two years ago, not fewer.

This means it’s getting harder for marketing leaders to get a handle on their tech stack.

But the good news is you don’t necessarily need to consolidate — you just need to connect everything.

What your stack is missing

Most marketing teams use AI the way they use Google.

You open a tab, type a question and copy the answer somewhere else.

The AI has no idea what’s in your CRM, what last week’s campaign numbers looked like or what was in the brief your colleague sent yesterday.

If you want to fix this, there is one simple step you need to take: connecting your AI platform to your day-to-day tools.

Think of it like giving a new employee access to your systems.

Once they have the logins, they can look things up, update records and start producing work.

Claude and ChatGPT operate the same way.

Claude has a feature called Connectors which allows you to authenticate 400+ (I counted!) platforms including HubSpot, Airtable, ActiveCampaign, Google and Microsoft.

ChatGPT has the same capability through its App library and has a similar set of connections.

If your team runs on Copilot or Gemini, they work well inside their respective suite but their reach outside that ecosystem is more limited.

If your AI platform of choice doesn’t have an active connection you also have the option of creating a custom MCP connection.

This is fairly straightforward in Claude, but trickier to do in ChatGPT and if you’re using Copilot or Gemini, you’ll need to talk to your IT team.

What it looks like when you build a connected system

Once your tools are connected and they have access to your context, everything runs with fewer bottlenecks and less task switching.

A new lead comes in, your AI scores it against your ICP, pushes a personalized email or nurture to your outreach tool and logs the activity in your CRM. Your SDR reviews the copy, hits send and moves on to the next one.

Your AI queries your reporting data every Monday morning and pulls performance by channel. It generates the report in your template, with no manual export. It even creates a live dashboard you can share in the team Slack channel.

Here’s an example of an end-to-end “recipe” I run in Claude to generate publish-ready content.

Every call I take gets transcribed automatically by Granola. Claude pulls that transcript, along with my SEMrush insights, content calendar and weekly notes.

In five minutes I have a clean summary, three LinkedIn post angles, a newsletter hook and an SEO/AEO optimized landing page.

Because Claude has access to all of my platforms I no longer need to upload exports or paste content into word docs. Everything arrives ready to go in the folder I specify.

Where to start

Last week we covered workflow mapping.

This showed you how to identify the plays your team runs most often and all the manual steps costing you time.

If you did that exercise, you now have a list of workflows and their relevant platforms. All you need to do is connect the platforms, then tell Claude or ChatGPT what you want to do.

If you didn’t do the workflow mapping exercise, here are some plays to get you started:

The plays above give you a starting point, but every team's stack is different.

Before you start wiring things up, it's worth doing a quick audit of what you already have connected, what's sitting idle and where the biggest gaps are.

Use the prompt below in Claude or ChatGPT to get a clear picture of your current setup and a prioritized list of what to build next.

Claude Stack Assessment Prompt

Use this template to audit your Claude or ChatGPT environment and broader tool stack.

You are conducting a comprehensive audit of my [AI TOOL] environment and broader tool stack. Your job is to identify gaps, flag redundancy, and recommend optimizations that increase workflow speed and reduce context switching.

I am [ROLE] managing [BUSINESS/TEAM]. My work falls into these categories: [LIST 3–4 WORK CATEGORIES — e.g., client delivery, content creation, business operations, sales].

Step 1 — Inventory

Pull a complete picture of my current setup:
All skills loaded in this environment
All active connectors or apps

My broader tool stack: [LIST YOUR TOOLS — e.g., HubSpot, Notion, Google Calendar, Gmail, Slack, Zapier, Stripe]

Step 2 — Usage Assessment

For each skill, project, connector or app, evaluate:
Is it connected to a real recurring workflow?
Does it have a trigger that would fire in practice?
Is it duplicated or overlapping with another skill or tool?

Step 3 — Gap Analysis

Identify workflows I run manually or across too many tools that a skill, connector, app or automation could streamline. Cross-reference my work categories above. Flag anything where I'm losing time to context switching.

Step 4 — Recommendations

Deliver a prioritized action list in three tiers:

Quick wins — activate or wire up something already available
Build now — new skills or automations worth creating in the next 30 days
Deprioritize — skills, connectors, apps or plugins to archive or ignore

Format output as a structured audit report. Be specific and direct. No fluff.

If you run the AI assessment above, I'd love to know the result! Tell me if it was helpful or not and any improvements you would make.

Email me at tahnee@goa25.com.

Want to Level Up Your AI Game?

If your team is ready for a hands-on AI strategy session, my custom-designed workshops are built to uncover the workflows that can save you hours every week.

Prefer to start small? My YouTube channel is packed with quick, practical “how-to” videos that show you exactly how I use AI tools for marketing, content, and automation.

Planning an event or conference? I deliver high-energy AI sessions that engage audiences and leave them with actionable strategies they’ll talk about long after the event. Book me for your event here.

Did some one forward you this email? You can subscribe here.

2120 Contra Costa Blvd #1059 , Pleasant Hill, CA 94523
Unsubscribe · Preferences

AI at Work

AI at Work is a weekly newsletter on how marketing teams redesign workflows, roles, and systems with AI. Real examples, practical frameworks, and repeatable processes operators can use immediately. Join thousands of successful marketing leaders by subscribing below!

Read more from AI at Work

Hello Reader "Everyone keeps telling me to build agents and I don't even know where to start." A marketing director said that to me last week and she wasn’t the only one. We’re in full hype-cycle when it comes to AI agents. You can’t go anywhere without seeing that word splashed across digital displays, billboards and banners. Even worse, your CEO read about them over the weekend and wants you to spin one up on Monday. A vendor demo made it look simple but when you tried it for yourself it...

AI workflows

Hello Reader Most marketing leaders don't fully grasp the work required to build an AI-ready marketing function. I see it in workshops, advisory calls, and the team audits I run with clients. The conversation usually goes like this: We've been experimenting with AI, we've got a few people using tools, and when I ask what's on their workflow map, there's a long pause. They don’t have an answer. Salesforce's 2026 State of Marketing report, which surveyed 4,450 marketers, found the same pattern,...

Hello Reader Claude was a long-time cult favorite, beloved by developers and largely invisible to everyone else. Then, late last year, it swept across the AI conversation and is now one of the most popular AI platforms in the world, regularly trading places with ChatGPT at the top of the charts. People and teams love it. And almost everyone I talk to is confused by it. That confusion has a specific cause: Claude was originally designed for coders, and much of the language and systems are...