Planning and execution are not the same. Most browser agents treat them the same, and it's costing you.
Behind the build with @zachbellay, he's responsible for 90% of momentic's memes ⚡️
Momentic
@MomenticAI
The AI-native test automation platform. Trusted by Notion, Xero, Bilt, and 100+ others.
- Here is a trailing 15min pull of data that illustrates the distribution across the collection of ads that are actively being served. I could probably tailor the algo a bit. It shouldn't be a totally random equal distribution, but neither do we want all traffic to the top bidder.
- Say no to noisy tests 🪦☠️Our agent now triages every test failure for you > alerts your team if it's a real bug > fixes the test and opens a PR automatically when the user flow changes. Beta testers already cut triage time by 30% 🔥
00:00 - Love getting customer shoutouts like these 😭
- We've seen vast improvements in speed, accuracy and resolution latency since migrating to @ClickHouseDB. In this post, @HenryHaefliger shares the playbook to successfully moving from PostgreSQL at high volume.
- Momentic reposted
Testing is painful, but quality shouldn't be. With AI Actions, you can just 1/ just describe the goal 2/ watch the agent plan, generate steps 3/ let it optimize user trajectories and self-heal 4/ guardrails with pre and post-conditions Now with goal-based caching, making it
00:00
