Find the tests you didn’t know to write. Tell Wren what should work in plain English. Its QA agents try the paths your customers take, like going back to change an address halfway through checkout or retrying a failed payment. When something breaks, you get a replay and the steps to reproduce the bug. First 10 runs free.
Hey Product Hunt! I’m Tom, co-founder of Seldon. We built Wren because your entire test suite can pass and a customer can still find a bug five minutes after you ship.
We’re an applied research lab in SF. Our team includes researchers from MIT and Berkeley and people who’ve built products at Meta and Spotify. We put people and agents in front of the same screens and study where their decisions differ. That got us interested in a QA problem. A test can tell you whether the route you scripted works. Customers get to pick their own route.
How does Wren work?
Give it a goal in plain English, like “a new teammate should be able to accept an invite and join the workspace.”
Wren’s QA agents open your app and try different ways to reach that goal. One might open the invite while signed into the wrong account, switch accounts halfway through, and try the link again. You can test those paths without writing a separate script for each one.
When something breaks, you get a recording and the steps to reproduce it. You can run Wren alongside your existing tests in CI.
Who’s it for?
We built Wren for engineering and QA teams, from startups shipping new features every week to enterprise teams with years of test coverage. One early team told us Wren saved them days of QA before a release.
Try it on something you already test
Your first 10 runs are free. I’d start with a flow your team already has a passing test for. Did Wren catch something your suite missed? I’d love to hear what happened. We’ll be here all day.
@tom_charman Very interesting, congrats on the launch! =) Should I provide documentation about our product so your QA agents can test some real-life scenarios?
qa agents that test like real users is smart 👏 web only or mobile apps too?
The recording next to the repro steps should make a weird path much easier to judge. Can a team share one run with the person who owns that flow?
very very cool, congrats on the launch team! this would have saved us a lot of headaches for our first product hunt launch earlier this year, so cant want to try this out
@tom_charman I like how I can watch the videos very helpful to finding and replicating the issue
Nice work Tom. We build crypto exchanges, and the hardest flows to test are behind KYC and 2FA, like signup to first deposit. Can Wren run on a staging setup with test accounts, and can I block any step that would move real money?
Congrats on the launch!!
our e2e hits a real BE, so we prefix everything it creates and sweep it after. an agent that picks its own path doesn't tell us up front what it made.
does a run clean up after itself, or do we point it at a throwaway account?
BTW, this is a great idea 👍
Giving agents a goal rather than a script catches the path nobody wrote a test for, like editing an address mid-checkout, and that is where many customer-facing bugs actually live. The false-positive question in the comments is the real test: separating a genuine bug from a route no customer would take, and building on behavior models of real users rather than random clicking is the right bet. When Wren flags something, how can a team teach it that a given odd path is acceptable, so the same finding does not come back every run?
Tried this at a hackathon they hosted a few days ago. Very agent friendly. Great stuff
Been a fan of Tom, Olivia and the Seldon team for some time!
They've been at the forefront of simulation and have taken a thoughtful approach to helping teams use it to move faster building products people want that work.
Excited to get our hands on Wren and hope you are too!
As an engineer @Seldon this was one of the missing pieces in my workflow! Agents are pushing at lightning speed, to the point that Github and Cloud Providers are having increased outage incidents...reviewing at the human rate and at the rate that your team can, given your teams capacity and other ongoing and more important initiatives, means bugs slip through. Wren has saved me a few times now while pushing changes! It integrates nicely into most of your developer flows. Give it a try and give some feedback, but I can promise you this will be one of your most useful tools by day 1 and one of the easiest to integrate with; it's one file in your repo or in your local environment, that's it!
Ooo this is very useful, been looking for something like this.
Really like the section on the landing page with the "Old way vs New Way", it's excellent! Your approach in plain English looks soo much more seamless and intuitive when shown both versions side by side. Makes tests that much more fun to write lol. Bookmarked this and upvoted! Congrats on the launch!
I am a engineer at Seldon and have had a hand helping building Wren and I personally use this awesome AI agent when testing new front-end features and before and after deploying to production. What I love is how easy it is to create and review my QA test cases through a dead simple yaml file.
It’s simple and easily manageable! Check it out!
Also give us as much feedback as possible!!!!
version: 1
run:
url: https://staging.example-store.com
username: qa-shopper@example.com
password: test-password-123
testCases:
- id: cart-add-item
area: checkout/cart
name: Add a product to the cart
url: /products/classic-tee
steps:
- select size M
- click "Add to cart"
- open the cart
criteria: the cart contains one Classic Tee in size M and the cart badge shows 1
- id: cart-update-quantity
area: checkout/cart
name: Changing quantity updates the subtotal
steps:
- add the Classic Tee to the cart
- open the cart
- change the quantity from 1 to 3
criteria: the subtotal equals three times the unit price
The "tests you didn't know to write" framing is what got me — as a solo dev I mostly hand-test the happy path and find the weird stuff from users after shipping. The half-finished onboarding flows are exactly where I'd point this first. One question: does Wren work on native apps too, or is it web-only right now? Most of what I ship is native, so that's the deciding factor for me.
Writing tests in plain English and letting the agents find their own way through the app is such a good shift. It caught a confirmation that only showed up below the fold after loading, something my unit tests would never flag. The replays make it easy to see exactly what happened. Congrats on the launch!
About Seldon on Product Hunt
“Behavioral QA agents that use your product like customers do”
Seldon launched on Product Hunt on November 10th, 2026 and earned 249 upvotes and 99 comments, placing #5 on the daily leaderboard. Find the tests you didn’t know to write. Tell Wren what should work in plain English. Its QA agents try the paths your customers take, like going back to change an address halfway through checkout or retrying a failed payment. When something breaks, you get a replay and the steps to reproduce the bug. First 10 runs free.
Seldon was featured in API (98.9k followers), Developer Tools (523.1k followers) and Artificial Intelligence (483.6k followers) on Product Hunt. Together, these topics include over 244.1k products, making this a competitive space to launch in.
Who hunted Seldon?
Seldon was hunted by Chris Messina and Tom Charman. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Seldon stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Chris Messina,
Tom Charman
Hey Product Hunt! I’m Tom, co-founder of Seldon. We built Wren because your entire test suite can pass and a customer can still find a bug five minutes after you ship.
We’re an applied research lab in SF. Our team includes researchers from MIT and Berkeley and people who’ve built products at Meta and Spotify. We put people and agents in front of the same screens and study where their decisions differ. That got us interested in a QA problem. A test can tell you whether the route you scripted works. Customers get to pick their own route.
How does Wren work?
Give it a goal in plain English, like “a new teammate should be able to accept an invite and join the workspace.”
Wren’s QA agents open your app and try different ways to reach that goal. One might open the invite while signed into the wrong account, switch accounts halfway through, and try the link again. You can test those paths without writing a separate script for each one.
When something breaks, you get a recording and the steps to reproduce it. You can run Wren alongside your existing tests in CI.
Who’s it for?
We built Wren for engineering and QA teams, from startups shipping new features every week to enterprise teams with years of test coverage. One early team told us Wren saved them days of QA before a release.
Try it on something you already test
Your first 10 runs are free. I’d start with a flow your team already has a passing test for. Did Wren catch something your suite missed? I’d love to hear what happened. We’ll be here all day.