Podcast Summary: Marketing Against The Grain

Episode: Can AI Actually Make Good Ads? Replit Ad Maker Review

Date: April 2, 2026
Hosts: Kipp Bodnar (A), Kieran Flanagan (B)

Overview

In this episode, Kipp Bodnar takes listeners on a hands-on, critical exploration of Replit4’s new AI-powered ad creation feature. The main theme centers on evaluating how effective AI is in actually delivering "good" ads, dissecting not only the technical process but also the real-world results and limitations. The journey includes live prompt engineering in Claude, practical walkthroughs of generating and iterating ads, and a frank review of the creative output—giving marketers actionable insight into where AI shines and where it still lags behind.

Key Discussion Points & Insights

1. The Promise & Value Proposition of AI Ad Tools

[01:29–03:20]

• Kipp introduces Replit4's new ad creation feature, highlighting the tool’s intent: making ad creation fast, easy, and available to both solo entrepreneurs and large teams.
• Value prop: “The value prop here is simple—they’re trying to reduce the friction of creating ads. The question is, are they really reducing the friction? Are the ads actually good and would we run them? That is a big, big question.” (A, 03:04)
• Example: Testing book titles for a new project by quickly spinning up ads to see what resonates.

2. Secret Weapon: Prompt Engineering with Claude

[03:21–07:40]

• Kipp walks through his "secret step": using Anthropic’s Claude Opus 4.6 to craft and refine comprehensive prompts before feeding them to Replit.

• Emphasizes the huge impact of a well-researched and tailored prompt on final ad quality and cost efficiency:

  “It takes a while and it takes a decent bit of credits and usage… I’m going to save a lot of time and I’m going to save a lot of money if I iterate on the prompt in text before I actually go and create the ads themselves.” (A, 05:39)

• Key prompt elements:

  • Instruct Claude to do deep research (product benefits, positioning, platform best practices).
  • Ask for three ads each for LinkedIn, Instagram, Google AdWords.
  • Give clear creative direction and iterate on specific angles for each platform.

3. Iteration—The Heart of AI Ad Quality

[07:41–11:38]

• Kipp stresses that iterative editing, both of prompts and AI outputs, is essential for good results.
• Practical note: It's cheaper and faster to perfect the prompt than to repeatedly generate new ad assets with poor instructions.
• Commentary on Replit's UI and skills:

  "A lot more design and creative elements … they're trying to merge instructing it in natural language as well as being able to do what’s called a graphical user interface." (A, 10:24)

• Comparison: Mentions other tools like Super Scale, Canva, Base44, but spotlights Replit’s new Canvas editor.

4. Honest Review: AI-Generated Ads Under the Microscope

[12:23–20:47]

LinkedIn Ads – Copy: Good, Creative: Awful

• Example:

  “77% fewer tickets, 0 new hires, NutriBee customer result. I like the data. The graphic drives me insane. That is a terrible, terrible image. Right. In theory, the ad concept is good. In terms of copywriting, the creative is not.” (A, 13:53)

• Issue: AI-generated images/logos are off-brand, visually weak, and often irrelevant (e.g., incorrect HubSpot logo).

• Critical note:

  “This is one of the worst ads I’ve ever seen. Please redo it. And I’m not trying to be mean. This is just a bad ad.” (A, 15:48)

Google Search Ads – Where AI Excels

• Copy-focused platforms (like Google) fare much better:

  “This is actually really good. I like the fact that it’s not just giving me like plain text copy. It designed what it would actually look like … that visualization is really helpful.” (A, 17:13)

• Examples include specific, punchy copy and multiple headline variations.

Instagram Ads – Needs Directives to Avoid Weirdness

• AI produces “weird, post-apocalyptic illustrations” and sometimes ignores brand guidelines.
• Takeaway: Give AI a clear “not do list” (e.g., forbidden styles, off-brand colors) to get closer to desired output.

5. Real Talk: Limitations, Costs & the Human Touch

[21:05–24:50]

• Iteration is non-negotiable even with top-tier AI; expect to invest hours, not minutes, to achieve A-level work:

  “A lot of people out there are like, oh, you can do this so easy. It’s five minutes, it’s free. No, you’re going to have to iterate on this. And even iterating on it, you’re probably going to run through a good amount of credits.” (A, 20:24)

• Skill gap: For non-designers, these tools are game-changers. For professional designers, conventional tools like Canva might still be faster for some needs.
• Key strategic advice: Always provide brand guidelines and constraints up front in prompts to cut down on revisions and avoid off-brand creative.

Notable Quotes & Memorable Moments

• Prompt Engineering Wisdom:

  “Getting that prompt right up front is hugely critical … it’s really important to take this step of working to refine and iterate your prompt before you go and actually create the assets, because it takes a while and it takes a decent bit of credits and usage that you’re paying for to go and do this.” (A, 05:15)

• Brutally Honest Creative Review:

  “The image has nothing to do with the product. The copy isn’t as strong as the other two. You have an image overlap over the word support that makes it illegible ... This is one of the worst ads I’ve ever seen.” (A, 15:41–15:50)

• Caveat for Marketers:

  “You’re not going to get the perfect outcomes one shot unless you’re giving it a ton of existing sample creative to build off and you’re really continuing to iterate your prompt.” (A, 22:09)

• Pro Tip: The ‘Not Do’ List:

  “One of the things that I should have done … is give it a not do list. Like, don’t do these style of illustrations. Don’t use any color that’s not on the brand style guide.” (A, 20:19)

Key Timestamps

• 00:00 – 03:20: Setting the stage—overview of Replit4's ad tool, value for marketers.
• 03:21 – 07:40: Deep dive into prompt engineering with Claude.
• 07:41 – 11:38: The importance of iterative editing and first look at the Replit4 ad creation workflow.
• 12:23 – 20:47: Live, critical review of generated ads (LinkedIn, Google, Instagram); strengths and failures.
• 20:48 – 24:50: Cost, iteration, realistic expectations, and best practices for using AI ad tools.

Actionable Takeaways for Marketers

• Iterate Before You Generate: Invest time in crafting superior prompts before generating assets; it saves substantial money and time.
• Leverage AI where it Excels: Use AI for copywriting and search ads; scrutinize and manually adjust image-heavy creative.
• Always Apply Brand Constraints: Include style guides, brand colors, and forbidden elements in prompts.
• Set Realistic Expectations: AI can speed up early drafts, but achieving high-quality, brand-ready ads still requires meaningful human oversight and iteration.
• Use “Not Do” Lists: Guide AI by specifying not just what you want, but what you definitely don’t want.

Summary Verdict

Replit4's ad maker delivers on its promise—eventually. For marketers without design resources, AI tools like Replit can jump-start your ad pipeline, especially on copy-focused platforms. But plan for multiple rounds of prompt and creative iteration, be precise with brand constraints, and expect to spend credits and time to reach results you’d be proud to ship. AI isn’t a set-and-forget solution—yet.

For more hands-on tactics and real marketing talk, drop your feedback, check out the newly announced Marketing Against the Grain newsletter, and tune in next week!