Things keep moving fast. What should we, marketers, do when:

1. we have incredible new AI tools in our pocket

2. traditional SEO fails us

3. creators command more attention than most brands

4. our customers are overwhelmed by the avalanche of tools and content available and the frenetic pace of change?

So many good resources were published recently: let’s dive right in!

If you only check one highlight this week:

• Team leader? The AI team offsite (1st section)

• Growth Leader? A playbook to start from scratch (2nd section)

• Advanced AI user? Claude Code examples (last)

-François

Thanks for sharing these highlights with busy marketing execs around you. 🙏 

Someone forwarded you this email? You can subscribe here.

My selection of tips, news and workflows

👥 🏔️ Using team off-sites to accelerate AI usage

An exec at Ramp explains why and how his product management team went off-site to accelerate AI adoption. This is applicable to marketing teams as well.

Why an offsite for AI advancement?

Their off-site workflow with AI:

1. Step 1: Bring product insights to life - parse customer research, support tickets, calls, surveys, and data with AI. Create ICP and persona cards.

2. Step 2: Pitch with landing pages - generate landing pages showcasing product story, get funding for top ideas

3. Step 3: Vibe code your vision - generate PRDs from insights, build prototypes, create actual demos

And his conclusion: 

📚 A modern marketing playbook for an AI era with short attention spans

Kieran, SVP at Hubspot and former CMO at Zapier, details what he would do with AI if he had to build an acquisition plan from scratch today.

His post also shares some tools and rationales for doing that.

🧵 AIO again: How to get recommended by ChatGPT

We increasingly turn to AI for our searches. Google inserts AI overviews in more search results. Therefore:

Kyle interviewed Josh Blyskal who leads AEO strategy and research for Profound for this good recap:

🛠️ Findings from MKT1's B2B Marketing Tools Survey

Emily Kramer shared key findings from surveying 200+ B2B marketers on the tools they're obsessed with:

• “AI tools like ChatGPT, Claude, Gamma, OpusClip, Tofu, Mutiny, and Lovable are capturing the imagination of marketers

• Automation tools such as Make, Zapier, n8n are becoming the connective tissue of modern marketing stacks, as a middle layer between CRM and content

• Clay (enrichment and automation) is the darling of the AI-augmented GTM stack

• Companies need to shift their stacks to include tools to map their entire total addressable market, track account activity, and deliver the right message to the right person at the right time. This shift is reflected in the rising popularity of Clay, UserGems, Warmly, and Koala

We’re clearly getting augmented, becoming more creative, technical and more analytical with this new generation of tools.”

🤔 More examples of what ChatGPT, Claude, and Gemini can do

Nicole Leffer’s thread on LinkedIn collected many use cases in comments.

Going through them helps understand the various capabilities and should give you ideas.

Here’s a selection:

• A Prompt so ChatGPT evaluates your usage and recommends how to up your game.

• Uploading mp3s to ChatGPT and ask for musical analysis of pieces and recommendations of similar music

• Scheduling automated tasks in ChatGPT to research and analyze web and social media sentiment

• Feed client calls transcripts to ChatGPT and ask it to look for emotional triggers to get ideas for the right messaging and landing page copy

• Generate Braille suitable for use with an embosser for blind and low vision people.

• Decipher text handwritten in archaic, biblical-style High German using medieval caligraphy

• Generate downloadable, working QR codes directly in the chat with ChatGPT and Copilot (prompt)

• Two of mine:

  1. using vision to turn inspiration you see around you into a style guide brief for a marketing asset

  2. giving you recipes of dishes or cocktails you enjoy

🛠️ Advanced: How Anthropic’s Growth Team uses Claude Code

We are seeing more teams use Claude Code for non-development use cases. Anthropic shared how their Growth team use it. Other teams shared their use cases too.

From the Growth Team:

“1- Automated Google Ads creative generation

The team built an agentic workflow that processes CSV files containing hundreds of existing ads with performance metrics, identifies underperforming ads for iteration, and generates new variations that meet strict character limits (30 characters for headlines, 90 for descriptions). Using two specialized sub-agents (one for headlines, one for descriptions), the system can generate hundreds of new ads in minutes instead of requiring manual creation across multiple campaigns. This has enabled them to test and iterate at scale, something that would have taken a significant amount of time to achieve previously.

2- Figma plugin for mass creative production

Instead of manually duplicating and editing static images for paid social ads, they developed a Figma plugin that identifies frames and programmatically generates up to 100 ad variations by swapping headlines and descriptions, reducing what would take hours of copy-pasting to half a second per batch. This enables 10x creative output, allowing the team to test vastly more creative variations across key social channels.

3- Meta Ads MCP server for campaign analytics

They created an MCP server integrated with Meta Ads API to query campaign performance, spending data, and ad effectiveness directly within the Claude Desktop app, eliminating the need to switch between platforms for performance analysis, saving critical time where every efficiency gain translates to better ROI.

4- Advanced prompt engineering with memory systems

They implemented a rudimentary memory system that logs hypotheses and experiments across ad iterations, allowing the system to pull previous test results into context when generating new variations, creating a self-improving testing framework. This enables systematic experimentation that would be impossible to track manually.

From other teams:

5- End-of-session documentation updates

The team asks Claude Code to summarize completed work sessions and suggest improvements at the end of each task. This creates a continuous improvement loop where Claude Code helps refine the Claude.md documentation and workflow instructions based on actual usage, making subsequent iterations more effective.

6- Building dashboard apps

Despite knowing "very little JavaScript and TypeScript," the team uses Claude Code to build entire React applications for visualizing Reinforcement Learning (RL) model performance and training data. They give Claude control to write full applications from scratch, like a 5,000-line TypeScript app, without needing to understand the code themselves. This is critical because visualization apps are relatively low context and don't require understanding the entire monorepo, allowing rapid prototyping of tools to understand model performance during training and evaluations.”

🔄 More details about how I write certain sections of this newsletter with AI

I wrote about my sausage making techniques a few weeks ago. I gave a lightning talk to share more details.

Here are the slides and the lightning talk recording where I explain how I:

• capture and synthesize talks first in Granola

• then have Claude write in my style, and

• generate an image with ChatGPT 4o

Final Words

François | LinkedIn 

I'm a CMO, advisor, and "CMO Wingman". Yes, that's a thing :-). Ask the CMOs I support: in this AI era, CMOs need a strategic proactive advisor more than ever. I’m former CMO at Twilio, Augment Code, Apollo GraphQL, Decibel, Udacity and Head of Marketing for LinkedIn Talent Solutions.