Writing suffers when humans don’t

This edition is brought to you by our friends at Venngage.

You ran the survey. You have the research. Don't let it sit in a spreadsheet nobody reads. Venngage AI turns raw data into a chart-driven infographic people actually stop to share, with no design team needed.

Here's how it works: start with a text prompt, feed in your data, and your Venngage AI builds the charts, layout, and color for you in minutes. It suggests the structure as you go, so you spend less time designing and more time telling the story your data deserves.

Whether it's a client report, a research recap, or a data-driven blog post, your infographic is ready to publish, present, or send in minutes.

This month, Superpath readers get 30% off any Venngage plan with code SUPERPATH30. Try Venngage today → www.venngage.com

⭐️ Featured Job Post

DAK Mortgage | Sr. Financial Editorial Strategist & Writer (Fractional)

→ Full Job Description

Hey folks, it's your content friend Eric here.

The whiplash from AI has really gotten to this old dog lately.

Daily eureka moments followed by complete letdowns. Unbelievable time savings combined with even more time-wasting. Unlimited possibility mixed with unlimited workslop.

As many of you know, I’m a one-person marketing team for a startup with pretty ambitious marketing goals for our size. I’m basically paid to be obsessed with productivity, efficiency, and scale. But I keep running into situations where trying to be efficient is just getting in the way of good work.

I’ll give you an example:

I recently started tinkering with Claude Design to help me lay out landing pages for our website. My old process used to be something like:

This uses pretty nearly every skill in my toolset, so it’s mentally exhausting work. Plus, switching back and forth between writing and designing often grinds the process to a halt.

I typically try to use AI for tasks that are (a) time-consuming and (b) not in my wheelhouse, so I figured Claude Design could help me skip a lot of the Figma steps.

Without going into too much detail, our designer has already given Claude Design our design system, so I can just provide the page copy, and it will create a beautiful landing page. I can make edits by prompting, which is way faster than dragging boxes around in Figma. And then I can just give that mockup to the designer and they can use AI magic to get that into Figma and/or Webflow.

The first page wireframe I made was an immediate win. Hours saved. Boom.

But then… if you want to imagine an AI Angel on one shoulder and an AI Devil on my other shoulder, that’s about when the AI Devil asked, “What if you could save even more time?”

For the next page, instead of writing it by hand and describing each section to Claude Design, I basically handed over my raw notes and said: “write and design a page.” The output was pretty good.

But then I tried it for the next page and the output was terrible. So I tried getting Claude (chat) to write the prompt for Claude Design. Even worse. Surely I can prompt my way out of this! Surely we can recapture the magic!

I tried it again for 3 or 4 pages with varying levels of prompt specificity and could never get it to work as well as the first time. Ultimately, I realized I was spending more time undoing bad AI work than I would have by just grinding through by hand.

I also realized that drafting the page with AI was immediately sending me into “editing” mode rather than “creative” mode. The AI output anchored me in one possible solution rather than my usual process of exploring multiple solutions. I ended up just throwing a lot of features on the page rather than selling a vision.

This week, I’ve gone back to pen and paper to force myself to lay out the pages from scratch and really mull over the problem more deeply before I throw anything into Claude. “Touch paper,” if you will. It’s helped a lot.

It’s made me (once again) realize: with many creative tasks, the difficulty of the work is the work. Something ephemeral emerges from the grind. A-ha moments don’t come without failures. Some stuff just takes hours and hours and hours to figure out.

You’ll find that theme pop up a few times in this newsletter today.

Coincidentally, Jimmy wrote this perfectly timed blog post on a similar topic: how his attempts to systematize writing unintentionally made him skip some of the most essential steps to great writing. Give it a read!

Cheers,

- Eric

PS. Don’t miss our survey below. You might win real human money!

🙋‍♂️ Survey (and $100 raffle draw): What are the top 3 content marketing tools you'd like to see in action?

We're exploring a new concept where we bring in software tools for short demos for the Superpath audience.

So that begs the question: what content marketing software companies are you most eager to see in action? Ideally, choose tools that aren't the major LLMs (i.e. not Claude or ChatGPT).

🏆 On Friday, August 7th, we'll have two raffles (you can opt into either one in the survey)*

1. $100 gift card
2. One free year of Superpath Pro**

* You may only enter one raffle, and you may only submit one time.

* Only enter the free year of Superpath Pro raffle if you are an in-house, freelance, or agency content marketer. If you are not a content marketer, your entry will be voided. You may still enter this raffle if you are currently in Superpath Pro.

📝 New Blog Post: The hardest part of content hasn’t gotten any easier

As I alluded to above, Jimmy’s back with a great blog. Here’s the thesis:

Jimmy explains how the laboriousness of writing something—struggling with it, coming back to it, maybe even giving up on it—is a necessary step in making something great.

Definitely worth a read if you’re feeling like something is missing from your AI writing.

📆 Upcoming Superpath Community Events

To get the invitations to our member events, join Superpath Pro. You get 30 days free, so you can attend all these events!

🎙 New on Content, Briefly: Should you build your own productivity tool?

At last month’s Superpath AI Show & Tell, a few folks presented personal productivity tools they had vibe-coded for themselves. That got us thinking…

Alex, Ruth, and I have each spent hours vibe-coding a tool that was never touched again. But we’ve also built tools that we use every day. So how do you figure out what’s worth the time investment before you build it?

We discussed:

It was fun to nerd out. Enjoy!

Listen here.

💬 Great Slack Threads This Week

Here were some great discussions in the Superpath Slack community this week:

📙 The Reading List

Here are some links that got the Superpath Slack community talking this week:

🆓 Get a free 30-day trial of Superpath Pro

Superpath Pro is our paid community membership. On your free trial, you'll get access to:

👉 Sign up for the 30-day trial here

"Most professional groups boast about their member numbers. Superpath intrigued me for the opposite reason: they deliberately shifted from a massive free community to a much smaller, paid one - so they could focus on it, nurture it, and make it genuinely excellent. And they absolutely deliver."

— Farah Cormack, Senior Marketing Leader