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.