Adam Moisa

Building an enterprise AI agent means constantly pushing the boundaries of web automation. Our engineering team loves working alongside @browserbase because they don't just provide a service, they collaborate with us to solve the hardest technical roadblocks in healthcare tech. From debugging complex Epic instances with enhanced session replays to keeping long-running browser sessions stable 24/7, this partnership is a major reason we can deliver clinical insights in under 60 seconds. Incredible engineering team over there. Proud to build together! browserbase.com/blog/magicare-…

AI in medicine is no longer a novelty; it is regulated infrastructure. As FDA guidance evolves, trust comes down to one thing: can a clinician easily review and audit the AI’s reasoning? I broke down the science of clinical inference and why black-box models have no place at the point of care

The best technology doesn’t add steps. It removes them.

What does Magicare actually do for a post-acute team? For one org: referral review time dropped from 38 min to 3 min in less than 2 months. SPEED That's real time back for the decisions that matter most. 🏥

38 minutes to 3 minutes. 13X faster! That's how fast one organization cut referral review time after going live with Magicare. Same team. Same volume. Smarter clinical inference.

Real talk: if you're building something that matters, your data layer can't be the weak link. Just met with @samlambert, CEO of @PlanetScale - and yes, we're very much aligned 🤝 Why we chose them as the MagicareAI database provider 👇

We r at this point in the cycle

@MayoClinic @Microsoft The best clinical AI doesn't just move data - it reasons with it. Great to see @MayoClinic + @Microsoft building toward that standard at scale. At Magic Care AI, we believe the same principle applies at every decision point in care, including the post-acute front door.

"Performance, reliability, and scaling all bottlenecked on the same root cause: we were running a fast inference engine on a slow disk." But once Magicare migrated to PlanetScale, they achieved an 85%+ reduction in query latency, 17× faster materialized view refreshes, and a 6× smaller database footprint per instance. Read their article for all the details. magicare.ai/articles/how-m…

@PlanetScale is 👑

Every org now needs a chief context officer

we r running thousands of bots every minute. @browserbase is the only reliable option. no other choice.

if you're not using @browserbase you're ngmi

The standard verifier for computer use agents is wrong 45% of the time. We got ours to 1%. We ran 96 experiments with Microsoft's FARA team to build the Universal Verifier, an architecture for grading computer use trajectories that matches human inter-annotator agreement. 🧵

X has the best information on the internet and the worst incentives & culture. meet noscroll — the AI that doomscrolls it for you and texts you just the things that matter. no feed. no brainrot. no ragebait. just signal. try it for free → noscroll.com 🙅🏼‍♂️

This launch just made every AI agent on Browserbase 99% faster. Stagehand Caching is our managed cache of every action AI can take on the internet. It's like a reverse CDN: we memorize the actions your agent does so you don't need to waste tokens and time repeating it.

@johnpalmer we just dropped these! github.com/browserbase/sk…