npm install : 147 vulnerabilities
me watching the site load anyway:
be honest, how many AI subscriptions are you paying for right now
your agent has never worked inside a real company, then you ship it to one
era by eon generates a complete company to test it on first: saleforces, zendesk, slack, jira and more, all connected with the vendors' own rate limits and error codes.
change something, reset and run tasks again
it's live today and free
Show more
You can’t safely test an enterprise agent on a real company’s data.
So we built a company for it to work in.
Era is live today, and it’s free.
It generates a complete simulated enterprise that behaves like a real one across Salesforce, Slack, Jira, Zendesk, Gong, Deel and more, along with cloud databases and storage. Agents interact with it through live MCP and API interfaces.
People leave. Deals change. Records get duplicated. Permissions differ across systems. And because Era generated the company, it knows the exact ground truth.
Test, benchmark and improve agents against realistic enterprise workloads, use the failures for targeted post-training, then rerun the same environment to measure the impact.
Huge thanks to our research partners @NVIDIA, @Decart, @Composio, @openlayerco, @Deel, @Eragon and @Plurai, with more coming soon.
Show more
we let AI drive our cars before we let it prescribe acne cream
nolla's AI now runs the whole visit in utah:
scan, questions, a plan, and a prescription if it fits. a doctor steps in when needed
Today, Nolla Health became the first organization in the U.S. (and possibly the world) to receive regulatory approval for an AI to issue initial prescriptions.
This makes Nolla the first ever actual end-to-end AI doctor.
Show more
green checks don't mean your app works
ship tests your pull request on the deployed app.
when something breaks, it comments on the PR with the replay, the likely cause, and a button to send it to claude code or codex
Show more
Everyone got a coding agent. Nobody got a QA engineer.
Until today.
Meet Ship, your Autonomous Quality Engineer.
It tests deployed PRs, reproduces bugs from Slack and Linear, and hands Claude or Codex the context to fix them.
Try it free:
Show more
claude just asked me if it should pull an all-nighter or finish tomorrow
what do you do when you hit your AI usage limit mid task
nvm, i jinxed it
been using claude pro $20 plan every day and still haven't hit the weekly limit
did anthropic cook this time
once your move to cloudflare, there's no going back
asked claude in cursor to make a video on history of internet
we're about to build super intelligence and i still have to click on traffic lights to prove i'm human
the video i planned for a whole day got 1.3k views. the one i made without thinking got 596k+
both were made the same way, claude writing every frame in code. the only difference was me
for the 596k one:
→ opened an empty folder in cursor
→ wrote a short prompt: the topic, the feeling, and "go all out"
→ told it to compose its own soundtrack in code
→ didn't touch it while it worked
→ posted it exactly how it came out
for the 1.3k one i planned, tweaked and second guessed everything
the less i interfere, the better it does. i keep having to relearn that
Show more
a cs degree used to guarantee a job. now it doesn't even guarantee an interview
AI writes better code than you. accept it
asked claude in cursor to make a video on history of internet
been using claude pro $20 plan every day and still haven't hit the weekly limit
did anthropic cook this time
asked claude in cursor to make a video on history of video games
nothing actually changed with vibe coding
only a real tech person can make high quality software
just saw this
asked gpt-5.6 sol to build a mac mini in blender
ran the whole project state through jev before the final render
