Gleap
AI-native customer support for software teams.
4.9•10 reviews•320 followers
AI-native customer support for software teams.
4.9•10 reviews•320 followers
Support, feedback and coding agents, finally on the same team. Customer reports turn into fixes your team reviews and ships, and customers hear back on the ticket they opened. Inbox, live chat, email, bug reports, roadmaps and AI agents in one place.
This is the 4th launch from Gleap. View more
Kai Resolve by Gleap
Launching today
Kai Resolve is the AI agent for support tickets your docs can't answer. It reads the screen recording, logs, account data and your code, read-only, then answers the customer or escalates with a diagnosis. Confirmed bugs become coding tasks your team reviews.
Free Options
Launch Team / Built With
Hey, Luca here, software engineer at Gleap 👋
I built the setup and settings for Kai Resolve and worked a lot on answer quality. What surprised me was how often fixing one case would quietly break another. Testing every change against all our scenarios slowed us down, but it’s why I trust the answers now.
If you try it and something feels off, please tell me here. I’d much rather hear it today than read it in a ticket next week 😄
Reading the screen recording and the logs before answering is what makes this interesting, since most support tools just paraphrase the help center and call it AI.
Thanks @karimbenkeroum , that's exactly the gap we wanted to close 🙌
Help-center answers are great for "how do I…" questions, and Kai Support already handles those. But when something is actually broken, the answer is rarely in the docs. It's in what the user did and what failed along the way. So Kai Resolve starts with the evidence (the replay, the logs, the account data, the code) instead of the knowledge base.
That also changes what your team gets when it can't solve a ticket itself: not "customer says it's broken", but what happened, where it failed, and the likely cause.
Congrats Isabella and the Gleap team. Having the agent read the session recording and logs before a ticket ever reaches a human is the step most support bots skip. On the 75% figure, how do you count a resolution when the customer simply stops replying, and does a likely-bug handoff to engineering count as resolved or as escalated?
@genedai thanks so much! 🙌 Glad the digging part stood out, that’s exactly what we built Kai Resolve for.
The 75% comes from our own workspace during the beta. Every closed ticket gets an AI review 24 hours after it closes, which reads the whole conversation and decides whether the customer’s problem was actually solved.
When the customer stops replying: if the last reply fully answered the request and the customer never came back with an objection, it counts as resolved. If the customer still owed us information when they went quiet, the ticket is left out of the rate entirely.
A likely-bug handoff isn’t counted as resolved or escalated on its own. What counts is how the ticket ends: it’s resolved once the fix has shipped and the customer’s problem is actually solved. A ticket that only got a workaround counts as partial, not resolved.
Congrats on the launch, Gleap team! At MailerCloud (mailercloud.com) we deliver 6 Billion+ emails every month, and our support team runs on Gleap. The slow part of every ticket is the digging: logs, account history, figuring out whether it’s a bug or a setup issue. Having Kai do that before a human picks it up is exactly what we need. Excited to roll it out!
@amar_cp Excited to see what Kai Resolve can do for you and the team 😻