Launching today
OpenIngress
Can AI agents use your UI?
8 followers
Can AI agents use your UI?
8 followers
OpenIngress checks whether AI agents can actually get around a live UI - public sites and internal tools - click the right things, find screens, and finish tasks instead of bouncing off broken nav, unlabeled buttons, or flows that only work for humans. We map what an agent can see and do, then report where navigation breaks.
hey Product Hunt 👋
we built OpenIngress after auditing live UIs for whether AI agents could actually use them - starting with ecommerce (product → cart → checkout), and the same failure pattern showed up on internal tools too: unlabeled controls, drawers, modal traps, state that only humans can see.
humans usually made it. agents often didn’t. the useful output was always the same: the job, where it broke, what to fix.
today we’re open-sourcing the engine for live sites. paste a URL, crawl, explore, get coverage + break points.
findable ≠ usable. if agents are going to browse for people, you’ll want those failure points before the traffic shows up.
self-host it, try your site, tell us what breaks. for custom journeys / authenticated / internal tools, reach out!
One thing that would help us a lot is letting us upload a customer journey script and then comparing how different agents perform on that exact path side by side. Right now the tasks feel generic so we have to handcraft each test, which gets tedious when we want to validate changes after every deploy.
@muammer1177418 thanks! our OSS keeps jobs generic so you can start fast. for exact customer journeys + comparing agents on the same path, that’s something we do with teams on the enterprise side. feel free to reach out and we can set that up!
Would love to see an option to replay a failed agent session step by step and see exactly which click or page tripped it up, makes the report way easier to act on.
@enayocakllsubz appreciate it! step-through on failed runs is high on what clients ask for. we handle that in enterprise engagements; feel free to reach out if you want it on your flows!
A dashboard view comparing scores across multiple test runs would be huge, so you can see if a recent deploy made the site more or less navigable for agents. Right now it sounds like each audit is a standalone report, but tracking that trend over time is what teams would actually act on.
@edanur1076469 yep! OSS is per-run by design. tracking navigability across deploys is something we set up with enterprise clients. hit us up if that’s what you need!
The "what breaks" framing in the report output is genuinely smart, way more useful than a generic pass/fail score. Nice to see something built for agent traffic that doesn't just slap a chat box on a crawler.
@eymenr25420 thank you!!! the “what breaks” framing is a huge point to the value prop for iterating on site dev! glad it landed!