Quaso - AI automation agent to get stuff done across apps or browser
by•
Quaso turns your busywork into automation across all of your apps and the open web. Simply prompt what needs to get done and it builds and sets it up for you. Connects to 3000+ integrations (Gmail, Slack, Linear, Stripe, etc.) and picks up a real browser when there's no native API. Runs on schedules, triggers, and on demand. Fork templates or save any thread as your own reusable skill. Tag @Quaso in Slack so your whole team can put it to work. Just relax and get stuff done.
Replies
Notte
Hey Product Hunt! 👋
Lucas here, co-founder of Notte, the team behind Quaso. We've spent the past year building browser infrastructure for AI agents, and 200+ companies run their agents on it in production. We also released Anything API, which turns any site into a custom API. That's all great, but one thing was still missing: people kept asking for more complex flows across their apps, and that was still painful to wire up.
Every time we personally wanted to automate a multi-step workflow involving both browser automation and apps (Calendar, email, Linear, etc.), we had to wire up everything by hand. So we built this layer on top of Notte and Anything API. Start with a simple prompt, and your busywork gets done for you.
We didn't build this to launch it. We built it because we wanted it, have been using it daily for weeks, and eventually figured other people probably want it too. A few hundred people have been running it daily for the past few weeks.
All of it under one roof:
A real browser it drives itself: cloud sessions you can watch live. It fills forms, checks availability, extracts data from pages with no API 🌐
Your actual apps: 3,000+ integrations (Slack, Gmail, Linear, Stripe, Notion…). It doesn't just draft the message, it sends it 🔌
Durable automations: any task can become a scheduled or event-triggered agent, a thing that just… runs when you sleep ⏰
Multiplayer. Just tag @Quaso in Slack and your whole team gets to use it 👏🏻
It’s not perfect yet. Complex multi-step browser tasks may need a retry, and self-repair fixes most breaks, not all of them.
Try it: start with a template (morning briefing, support triage, Stripe revenue reports) or just describe something you're tired of doing by hand.
We'll be here all day, so ask us anything, and tell us what you'd want your agent to take off your plate. 🙏
Notte
@Quaso @giordano_lucas "just describe something you're tired of doing by hand" - this
the web is UI over-load, context-switching uses mental bandwidth, Quaso frees it 🕊️🕊️ just start with a prompt
Notte
@Quaso @giordano_lucas @samatnotte 🥐
The cross-app + browser automation angle is the interesting part — most "AI agent" tools pick one lane (either API integrations or browser control) but rarely both reliably. How are you handling auth/session state when it drives a browser vs. calling an app's API directly — does it fall back to browser automation only when no integration exists, or do you let users force one path over the other? Curious how flaky the browser leg gets on sites with heavy bot detection.
Notte
@noctis06 , great question.
If an integration exists, the agent picks that up by default, it's faster and more reliable. If the integration can't do what's needed, or none exists, it falls back to browser automation automatically. You can also tell the agent to prefer one path over the other for finer control, it's not purely automatic if you want to steer it.
For auth, we use Notte profiles: you log in once, browser state (cookies, session) gets saved, and future runs reuse it instead of logging in fresh each time. If a session expires, the agent will prompt you to log back in rather than silently failing.
On the browser side, we're not starting from scratch, that's the whole reason Notte exists. A year of building stealth browser infra for agents (residential proxies, fingerprinting, session persistence) carries straight over into Quaso.
It's still not bulletproof. Heavy bot detection sites (aggressive fingerprinting, active challenge-response) can still trip it up, that's honestly the harder 20% of the problem. But it's a much stronger starting point than agent tools building browser automation for the first time on top of a launch.
Notte
@noctis06 Great questions! Think Lucas responded it all. Meanwhile, did you get the chance to try?
Notte
🥐
Notte
@ogandreakiro pronounced qwah-so 🥐
Notte
been telling all my non-dev friends about this and the feedback has been amazing, hope everyone gets as much use out of Quaso as me and my friends have :)
even just a simple lead generation triaged in my inbox in every morning, or significant updates in the AI/ML scene arriving in my inbox every morning so I don't get lost in the context switching of X and the web
genuine time saver, has changed my daily routine for the better, highly recommend anyone to drop one prompt about what you want automated see what it does!
P.S. the Slack to Linear integration flow has been 👌, uber seamless :) -- just @Quaso
Notte
@Quaso @samatnotte quaso-maxxing
The agents fallback to browser automation for tasks MCPs don't support - that's actually really cool! Really looking forward to trying this out 👀
Notte
@parthkoshti Thanks Parth! Looking fwd your feedback!
Loved the idea! But how does Quaso decide when to use an integration vs pick up the browser?? Like can a single workflow seamlessly switch between both?
Notte
@lak7 hey! quaso prefers picking up integration if they exist and your task is feasible with what they expose through their APIs/MCPs etc. if this is not possible, browser enters the play! both can work together on a single automation as well
The winning AI agents seem to be the ones that quietly become part of someone's daily workflow rather than trying to do everything.
Curious—what's the first workflow where Quaso consistently becomes a habit instead of just something people try once?
Notte
hey @aryan787544, I think the first sticky workflow is the one that closes the gap between conversation and execution.
We live in Slack all day, and that's where bugs, feature ideas, and "we should do this next" moments naturally surface. Quaso turns those messages into structured work, tracks it in Linear, and, because it's connected to our codebase and the same tools our team uses, can help close the loop by starting on fixes and features.
Beyond that, we use it daily to be reactive to a bunch of recurring stuff: customer support, Sentry errors, payment issues in Slack, automatic replies for churn signals, meeting prep and enrichment, user behavior analysis across Supabase and PostHog. All things we used to do manually and just offload to Quaso now.
That's made us dramatically more reactive to ideas and incidents: Quaso is present right where work already happens, rather than being another destination the team has to remember to open
@giordano_lucas Love that philosophy—being present where work already happens instead of becoming another destination.
Feels like there's more depth here than fits in a Product Hunt thread. If you're open to it, what's the best email to continue the conversation?
Notte
@aryan787544 Following up Lucas response - did you get a chance to try? :)
Self-repairing UI mechanics are super clever congrats @ogandreakiro how does quaso recover when an unexpected modal or popup breaks a selector?
I run most of my business ops through AI agents already, and the failure mode is never the happy path — it's the scheduled run that silently half-completes while I'm not watching. Does a Quaso run flag me when it hits something ambiguous, or make a judgment call and log it? The browser fallback for tools with no API is the part I'd use daily.