Skipping upfront research is the root cause of low-quality AI slop
James Dickerson · AI marketing Masterclass: From beginner to expert in 60 minutes · Feb 9, 2026 · at 9:30
Growth marketer James Dickerson explains to Greg Isenberg why most users get poor results when creating marketing assets with AI tools.
0:00 / 0:17exact quote · 17.6s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“They hop in and they just start trying to create stuff, and that's like where the AI slop thing comes from, you know. They just go into a tool, they throw a prompt in, they get an output, they throw it out there, and then they wonder, like, why, why am I not getting good results? They're skipping kind of the boring research step oftentimes.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from James Dickerson
Claude Code unifies product and marketing workflows in one developer environment
“What's really powerful about the systems that we're going to go through today is that they exist in the same place where you're building your products and you can get your marketing work and your product work done in the same place and leverage skills and MCPs…”
Perplexity MCP excels at deep market intelligence and competitive research
“I use the perplexity MCP. I won't talk about how to set that up today, but it does a great job going out there, finding deep information on your market, who the competitors are, what the angles are that are missing out there that you can go and attack.”
Spinning up fresh Claude Code context windows yields better task results
“Typically, when I have, like, a conversation going, sometimes I stop after I use a skill and have, like, a checkpoint, if you will. So I'll spin up a fresh, kind of, context window within CloudCode with a task-based agent, with a specialized job or role to kin…”
Split Claude Code terminals to prevent research MCPs from exhausting context
“Like you could have one focus on research and using MCPs. Those can fill up like context pretty quickly. So sometimes it helps to keep that in like a split terminal and then do other work side by side. So you can like save research, save files here that you're…”
A minimal stack of three MCPs outperforms complex tool configurations
“In terms of MCPs, like I used to have like tons of them set up. And what I realized was that simple's often better. I have perplexity. I have fire crawl. I have playwright. Those are like my main ones”
AI-generated, audience-specific landing pages yield much higher conversion rates
“You can create these landing pages just with like one prompt based on the positioning frameworks, and then you can drive traffic into those, and you'll see a much higher conversion rate since those are dialed to the exact audience that you're targeting.”