100 agents in parallel sounds incredible until my staging env catches fire. Is there a concurrency throttle or do I just pray?
T
Tomas Lindqvist12d ago
The split-screen demo of agents clicking through the app simultaneously is genuinely fun to watch. Rare launch video that actually earns its runtime.
A
Ade O.12d ago
Tagline rewrite, no charge: 'Mo finds the bugs your interns pretend they didn't see.'
K
Kenji Morikawa12d ago
Benchmarking against Codex plus Playwright MCP is a spicy choice. Half expected the comparison slide to come with a diss track.
M
Marissa Vuong12d ago
Repro steps plus logs plus video is the holy trinity I've been begging QA for since 2018. If the videos are actually watchable and not 40 minute slogs, this is a buy.
D
dmitri12d ago
Procurement question: SOC2 Type 2, SSO via Okta, and does Mo need prod data or can it run against seeded staging only?
H
Hania R.12d ago
Every bug a human finds is a bug ten agents already filed and closed as dupes. Welcome to the new standup.
F
Felipe R.12d ago
We built something kinda like this internally at my old shop in 2019 but it was just a cron job that mashed buttons. This is clearly the grown-up version.
Z
Zeynep A.12d ago
The 3.8x / 9x / 0.5x stat trio in the tweet is well-structured but I wanna see the eval methodology. What counted as 'a bug'?
S
Shreya G.12d ago
Methodology is in the blog post linked at the bottom of the thread, worth the scroll. They define bug as reproducible unexpected behavior, not just visual nits.
O
Owen Banda12d ago
One more thing for the roadmap: let Mo file the Linear ticket, assign it, and tag the engineer who last touched the file. Full loop or bust.
L
Luca B.12d ago
The thumbnail with Mo's little face is doing numbers for a reason. Mascot-driven dev tools are quietly winning this year.
Work With Us
Book an intro call to explore our suite of services. We might have a waitlist.
Momentic
Mo, the AI QA engineer that bug-bashes your app before every release.
Mo, the AI QA engineer that bug-bashes your app before every release.
Tags
TLVC Rating
Community Rating
No ratings yet
to rate this launch.
Comments (12)
100 agents in parallel sounds incredible until my staging env catches fire. Is there a concurrency throttle or do I just pray?
The split-screen demo of agents clicking through the app simultaneously is genuinely fun to watch. Rare launch video that actually earns its runtime.
Tagline rewrite, no charge: 'Mo finds the bugs your interns pretend they didn't see.'
Benchmarking against Codex plus Playwright MCP is a spicy choice. Half expected the comparison slide to come with a diss track.
Repro steps plus logs plus video is the holy trinity I've been begging QA for since 2018. If the videos are actually watchable and not 40 minute slogs, this is a buy.
Procurement question: SOC2 Type 2, SSO via Okta, and does Mo need prod data or can it run against seeded staging only?
Every bug a human finds is a bug ten agents already filed and closed as dupes. Welcome to the new standup.
We built something kinda like this internally at my old shop in 2019 but it was just a cron job that mashed buttons. This is clearly the grown-up version.
The 3.8x / 9x / 0.5x stat trio in the tweet is well-structured but I wanna see the eval methodology. What counted as 'a bug'?
Methodology is in the blog post linked at the bottom of the thread, worth the scroll. They define bug as reproducible unexpected behavior, not just visual nits.
One more thing for the roadmap: let Mo file the Linear ticket, assign it, and tag the engineer who last touched the file. Full loop or bust.
The thumbnail with Mo's little face is doing numbers for a reason. Mascot-driven dev tools are quietly winning this year.