Excited to share this new experiment by @erictli that helps you get fast usability feedback.
We built a tool that let's you test designs in minutes without needing to scheduling sessions or recruit participants.
Here's how it works: 👇
1. Upload your figma prototype and choose the screens you want to test.
2. An AI persona walks through it like a real user
3. You get a report with feedback and recommendations.
This is something between a heuristic evaluation and a usability test. It's not a replacement for testing with users but it's a quick way to get a second pair of eyes and catch issues before doing more research.
Comment below or DM me if you'd like to try it out!
You can now add more runs to an existing AI user test in Versive without recreating the setup. Same test, same config, just more participants.
Iterating on a study no longer means starting over.
You can now translate a Versive study through the API. A single call covers the questions, participant messages, and conditional logic in every language defined for the study.
Study follow-up is easier now: see who was invited, how many times, when they were last emailed, and whether they completed.
Filter by Unsent, Sent, Incomplete, or Complete before sending the next follow-up.
Shipped: proper hyperlink support in the Versive question editor. Select text, click the link icon, paste a URL or bare domain.
Works inside the editor and in the participant view. No more raw URLs cluttering your study questions.
New in Versive: an "Ignore content accuracy" toggle for AI tests on Figma, Image Upload, and Website.
Tell the AI to skip placeholder content (fake names, lorem ipsum, blurred logos) and focus on usability instead.
Spent 12 hours building a 12-second AI video ad.
Tried Kling V3 Pro, Kling O3, and Veo 3.1. Learned that shorter clips give you more control, and that taking the last frame of each clip as the input for the next one is the best trick for keeping things visually consistent across scenes.
Then I showed it to friends and no one got it
Ad below, lmk if you also didn't get it.
You should watch these 2 talks from AI Engineer Europe, from the "Vienna school of agentic coding":
@badlogicgames "Building pi in a World of Slop" https://t.co/MlXOb7kfGT
@mitsuhiko / @cristinaponcela "The Friction is Your Judgment" https://t.co/CY2htvix9w
They're very good.
Voice interviews in Versive now handle interruptions, respond in real time, and can discuss Figma prototypes mid-conversation.
Also shipped: Cmd+K global search across every study, insight, and template in your org.
Both live now.
We just released our voice-to-voice modality on our Versive studies! 🚀
The best part of these are the ability to get the full power of Versive studies with close ended questions and prototype testing in a live conversation format.
Demo below, also check out scratch for notes: https://t.co/26V4cfW4go
Here's exactly what I did:
1. Download your existing slides and drop them into your project directory
2. Clone your website repo into the same directory
3. Open Claude Code and tell it: "Look at the slides in this folder and the code in this repo. You can also reference the live site at [your URL]. Build me a slide deck as a website that matches the visual style of the slides I shared, so I can use it for sales"
4. ABC
My co-founder @erictli is one of the best designers I know, which is great for our product but also means you can always tell which slides he made and which ones I made.
There's a noticeable drop in quality around slide 4 and that's bc slide 4 is mine.
I've been watching Claude get really good at design so I dropped our deck into Claude Code and asked it to rebuild everything as a website, and it came out really good. I used the same instructions on Notion's website so you can actually see what it looks like.
One of the things that surprises me most talking to research teams: they've fully accepted that depth and speed are a tradeoff.
But the bottleneck isn't the research. It's everything around it. Finding participants, scheduling, moderation. The actual interview takes an hour. Getting to it takes three weeks.
That's starting to shift. Research repos that write up documents for you. Note takers that turn sessions into insights. AI interviews that conduct the conversation themselves.
When people see what's actually possible now, the assumptions they had about what research has to cost them in time start to fall apart pretty quickly.
We see this a lot with customers at Versive. When they see an AI interview that actually probes and follows up, the assumption that qual has to be slow starts to look a lot less like a constraint and a lot more like a habit.
We are completely humbled by the amazing response to our launch last week! 🫶 Now, we want to help you get the absolute best results from Stitch.
In this new video, David East walks you through how to consistently get premium results.
We also launched a new prompt enhancer (located under ‘+’ menu) to help you quickly collaborate on your vision before you submit your first prompt.
Stitch doesn't replace the design process—it is a tool for fast exploration and refinement, which is most effective when you step into the role of Creative Director.
Here are David's top strategies for taking your designs from generic to amazing:
🧠 Start with Intent: Define exactly who the design is for and how you want them to feel before you start building.
🎨 Enhance your prompt: You can use the new prompt enhancer (under the ‘+’ button’) to teach you design language and swap abstract words like "sporty" for tangible aesthetic descriptions like "high-end stationery" or "architectural limestone".
📐 Master Color Hierarchy: Treat colors as visual weight—Neutral for the canvas, Primary for ink, and Tertiary for your loudest accents.
Watch the full breakdown and see the transformation here👇images in 🧵