Intelligems

Operators consistently point to Intelligems for reliable split testing, especially on underused areas like the cart page, though some warn about running tests through non-split deploy paths.

“I’ve spent a ton of time vibe coding in Shopify. I think I’m pretty good at it. I don’t do it during the day. But it’s my current night, weekend, and early morning obsession. No idea why but it’s so fun and rewarding. Plus makes me more money. I’m setting up 2-3 new landing pages or multi variate CRO tests per week. Here’s a bunch of what I’ve learned and some tips on my process: Strategy is so important because of how fast you can move now. Our hit rate is higher than ever on CRO tests. I have a bunch of skills I built for CRO and insights. CRO skill - trained on CRO best practices and frameworks, all of our past intelligems tests, and site traffic to prioritize. But most importantly attached to a giant customer intelligence file that is fed via api from Typeform, listen labs, outer signal, junip, and more. Every survey we run or review we get makes this step better. I have a few different skills for building new pages or features. They kick off the insights process and competitor analysis. They build a html brief compiling all of this with some low fidelity mockups. The mockups are usually rough, even though they are using the design system. I’m sure I can architect some of the skills better, but it always makes mistakes and takes some trial and error. But I can get it looking 90% or the way there in an html file pretty easily. From there I have two workflows. One is pushing straight to Shopify. I have html to liquid skills that are trained on our theme architecture and requirements. Then using the Shopify CLI. Always building locally and pushing to a dev theme to preview. My favorite way to do this is on my phone using remote control and wispr. I often find it’s easier to polish designs in Shopify because it has all of our CSS. The other workflow is going from html to Figma. I find the Figma mcp is bad for this, so I use the html to Figma plugin. It’s not perfect but it gets the job done. I’ll have my design team polish the last 10% in Figma, and then I’ll use the Figma mcp to push back to Claude and then liquid. I find the Figma mcp much better for this part than pushing to Figma. From here I can just finish in Shopify and then I have a skill to manage the whole GitHub push/ pull/ merge/ PR process. Also been using Greptile for code reviews. I’ll often get a 3/5 at first and just feed Greptiles comments back into Claude; do 2 rounds of iterations and gets tons 4/5 and then I will submit the PR again. Before the PR I have two share skills. One is a design system audit, and the other is one I built for compliance to our theme that is based on feedback from early PR mistakes. A lot of things just trial and error. It’s like a video game; you just push, aww where you get stuck and try new things to push past it. When one approach works, build a skill to repeat it and it becomes part of hour workflow. But you’ll probably want to iterate on your skills. Happy to answer any questions or show some things I’ve built. At first I thought I was only gonna do this for landing pages. But I rebuild our cart while I was poolside last week, have a nav test, etc. I truly think one person can now run a best in class CRO/ experimentation program that encompasses strategy, research, design, copywriting, development, and analysis. Maybe it’s not the best in the world, but it would normally cost a lot more. We’re still hiring for this person. I’m essentially going to train one highly ambitious person on this workflow and give them a bunch of tokens. If that’s you, hit me up.”— @codyplof on X

Support gets strong individual praise for responsiveness and trust, though some users push back on how test results get presented and shared.

“@drewmarc I actually love intelligems tech support. I’m always willing to wait for the reply because I know your team is 100% on top of it and I even trust them to touch my code Doesn’t get better than that.”— @DylanAnder on X

The API is a standout — technical users are building Claude Code skills and automations directly on top of Intelligems data.

“last week we shipped an MCP server for Intelligems. now you can ask claude "how are my tests doing?" and actually get real answers from your data agencies are using it to generate client reports in like 30 seconds. pretty wild”— @drewmarc on X

Pricing is the most contested theme — several users find it worth it, but the $499/mo tier draws consistent sticker-shock complaints.

“EVERYONE asks me what split testing platforms to use. I’ve spent 100+ hours in each em. Here’s the unfiltered truth #notsponsored @getshoplift has overall been the best fit for most of the brands that use @heatmapme. I send most of our customers to shoplift to between pricing and ease of use. Nice and simple UI too @Intelligems price testing feature is legendary and something the others don’t have. If you’re doing advanced testing like custom css selectors I’ve had some struggles on. Tbh this goes for shoplift too, but I’ve been suuuuper into price testing lately. That’s when I say go to intelligems. Def more expensive than the others @Visuallyio has the most advanced features of the three. If you want to go hard in the paint and aggressive on CRO, visually is typically my rec What NOT to use in the Shopify world: Convert(.)com I believe is more in the lead gen/B2B space for testing. Shopify integration sometimes clashes and it’s difficult. Haven’t had the best experiences with em. If you’re B2B, not bad. Just not for Shopify, don’t use em. AB tasty/optimizely/dynamic yield/contentsquare are wickeddddd expensive BUT they have mind blowing features the previous ones don’t. If you don’t have 20m+ sessions/mo, don’t use them. They have exclusion tests (badass) and some other test types that the Shopify testing platforms don’t have, fortune 1000s should 100% use these ones @heatmapme has integrations with all these platforms, trying to give love to my partners but true honesty for the community ✌️🤓❤️”— @DylanAnder on X

Most see the data as accurate and actionable, though a few flag that on-site test wins can be muddied by downstream ad channel effects.

“The cart is the most underrated testing area of your store. Most brands I talk to set it up once (usually with an app), never touch it again, and leave a solid 5% RPV on the side. The reason they don't test is because most apps also don't have accurate A/B testing and tracking. This is one of the main reasons we also go with custom code. Testing is as easy as duplicating the theme and setting it up in Intelligems (not sponsored btw). We always aim to test multiple cart features: → Free shipping bar (static threshold vs animated progress) → 2-tier reward bar (free shipping + free gift) → Sale promo banner directly above the cart drawer → Upsells bar with discounted price anchoring → Trust strip below ATC (payment logos, secure checkout)”— @ArijanJanes on X

A clear growth area — users are layering AI agents and Claude skills on top of Intelligems to automate test selection and reporting.

“I've been deep in the Intelligems API for weeks. And here's what I keep noticing: - The people getting real value from it are technical. - Not always developers, but people already into AI. - They know Claude Code. They know how to build skills. They know how to wire up automations. That's maybe 5% of the people who could benefit from this data. So I asked myself: what if I could package everything I've learned into something where none of that matters? Not a skill someone installs in Claude Code. That still assumes they know what Claude Code is. Something more complete. Here's what I built: An Intelligems agent using the Claude Agent SDK. - It already knows the API. - It already has the Slack connection. - It already understands report templates. You just tell it what you want. In the demo, I went from zero to a working Slack automation in under 5 minutes: > Asked for sitewide analytics > Said "send this daily at 8am" > Picked a template > Added live experiment data > Added revenue per visitor screenshots > Hit send That's the entire workflow. Just prompting. Here's why this matters beyond my specific use case: Every organization has powerful tools that only a few people know how to use well. The Claude Agent SDK lets you take the road you've already traveled and pave it so smooth that anyone can walk it. No terminal. No skills files. No API documentation. No learning curve. Just: "here's what I need" and it works. This is how AI scales inside real teams. Not by training everyone on the technical stack. By removing the technical stack entirely.”— @victorpaycro on X

Comparisons are mixed: some switched to Intelligems from competitors like Convert, others are questioning its value against Shopify's new free native testing.

“@jchdotme @seanmcginnis Almost everyone switched to intelligems from convert”— @runtraffic on X

Smaller but positive theme — users prefer Intelligems for general testing while pointing to other tools for deeper personalization needs.

“Built an AI agent with Claude SDK that analyzes my Shopify orders every week and automatically sends to my Slack/Whatsapp: - Bundle deal recommendations - Co-purchase frequency analysis - Statistical validation (confidence, lift, support) - Revenue projections for each bundle - Top 10 product pairs to bundle These findings can give you a constant loop of test inspiration for @intelligems Fully automated. Pretty cool 🤖”— @victorpaycro on X